diff --git a/client-sdks/stainless/README.md b/client-sdks/stainless/README.md new file mode 100644 index 000000000..5d391f14c --- /dev/null +++ b/client-sdks/stainless/README.md @@ -0,0 +1,8 @@ +These are the source-of-truth configuration files used to generate the Stainless client SDKs via Stainless. + +- `openapi.yml`: this is the OpenAPI specification for the Llama Stack API. +- `openapi.stainless.yml`: this is the Stainless _configuration_ which instructs Stainless how to generate the client SDKs. + +A small side note: notice the `.yml` suffixes since Stainless uses that suffix typically for its configuration files. + +These files go hand-in-hand. As of now, only the `openapi.yml` file is automatically generated using the `run_openapi_generator.sh` script. \ No newline at end of file diff --git a/client-sdks/stainless/openapi.stainless.yml b/client-sdks/stainless/openapi.stainless.yml new file mode 100644 index 000000000..0a5dfc044 --- /dev/null +++ b/client-sdks/stainless/openapi.stainless.yml @@ -0,0 +1,608 @@ +# yaml-language-server: $schema=https://app.stainlessapi.com/config-internal.schema.json + +organization: + # Name of your organization or company, used to determine the name of the client + # and headings. + name: llama-stack-client + docs: https://llama-stack.readthedocs.io/en/latest/ + contact: llamastack@meta.com +security: + - {} + - BearerAuth: [] +security_schemes: + BearerAuth: + type: http + scheme: bearer +# `targets` define the output targets and their customization options, such as +# whether to emit the Node SDK and what it's package name should be. +targets: + node: + package_name: llama-stack-client + production_repo: llamastack/llama-stack-client-typescript + publish: + npm: false + python: + package_name: llama_stack_client + production_repo: llamastack/llama-stack-client-python + options: + use_uv: true + publish: + pypi: true + project_name: llama_stack_client + kotlin: + reverse_domain: com.llama_stack_client.api + production_repo: null + publish: + maven: false + go: + package_name: llama-stack-client + production_repo: llamastack/llama-stack-client-go + options: + enable_v2: true + back_compat_use_shared_package: false + +# `client_settings` define settings for the API client, such as extra constructor +# arguments (used for authentication), retry behavior, idempotency, etc. +client_settings: + default_env_prefix: LLAMA_STACK_CLIENT + opts: + api_key: + type: string + read_env: LLAMA_STACK_CLIENT_API_KEY + auth: { security_scheme: BearerAuth } + nullable: true + +# `environments` are a map of the name of the environment (e.g. "sandbox", +# "production") to the corresponding url to use. +environments: + production: http://any-hosted-llama-stack.com + +# `pagination` defines [pagination schemes] which provides a template to match +# endpoints and generate next-page and auto-pagination helpers in the SDKs. +pagination: + - name: datasets_iterrows + type: offset + request: + dataset_id: + type: string + start_index: + type: integer + x-stainless-pagination-property: + purpose: offset_count_param + limit: + type: integer + response: + data: + type: array + items: + type: object + next_index: + type: integer + x-stainless-pagination-property: + purpose: offset_count_start_field + - name: openai_cursor_page + type: cursor + request: + limit: + type: integer + after: + type: string + x-stainless-pagination-property: + purpose: next_cursor_param + response: + data: + type: array + items: {} + has_more: + type: boolean + last_id: + type: string + x-stainless-pagination-property: + purpose: next_cursor_field +# `resources` define the structure and organziation for your API, such as how +# methods and models are grouped together and accessed. See the [configuration +# guide] for more information. +# +# [configuration guide]: +# https://app.stainlessapi.com/docs/guides/configure#resources +resources: + $shared: + models: + agent_config: AgentConfig + interleaved_content_item: InterleavedContentItem + interleaved_content: InterleavedContent + param_type: ParamType + safety_violation: SafetyViolation + sampling_params: SamplingParams + scoring_result: ScoringResult + message: Message + user_message: UserMessage + completion_message: CompletionMessage + tool_response_message: ToolResponseMessage + system_message: SystemMessage + tool_call: ToolCall + query_result: RAGQueryResult + document: RAGDocument + query_config: RAGQueryConfig + response_format: ResponseFormat + toolgroups: + models: + tool_group: ToolGroup + list_tool_groups_response: ListToolGroupsResponse + methods: + register: post /v1/toolgroups + get: get /v1/toolgroups/{toolgroup_id} + list: get /v1/toolgroups + unregister: delete /v1/toolgroups/{toolgroup_id} + tools: + methods: + get: get /v1/tools/{tool_name} + list: + endpoint: get /v1/tools + paginated: false + + tool_runtime: + models: + tool_def: ToolDef + tool_invocation_result: ToolInvocationResult + methods: + list_tools: + endpoint: get /v1/tool-runtime/list-tools + paginated: false + invoke_tool: post /v1/tool-runtime/invoke + subresources: + rag_tool: + methods: + insert: post /v1/tool-runtime/rag-tool/insert + query: post /v1/tool-runtime/rag-tool/query + + responses: + models: + response_object_stream: OpenAIResponseObjectStream + response_object: OpenAIResponseObject + methods: + create: + type: http + endpoint: post /v1/responses + streaming: + stream_event_model: responses.response_object_stream + param_discriminator: stream + retrieve: get /v1/responses/{response_id} + list: + type: http + endpoint: get /v1/responses + delete: + type: http + endpoint: delete /v1/responses/{response_id} + subresources: + input_items: + methods: + list: + type: http + endpoint: get /v1/responses/{response_id}/input_items + + conversations: + models: + conversation_object: Conversation + methods: + create: + type: http + endpoint: post /v1/conversations + retrieve: get /v1/conversations/{conversation_id} + update: + type: http + endpoint: post /v1/conversations/{conversation_id} + delete: + type: http + endpoint: delete /v1/conversations/{conversation_id} + subresources: + items: + methods: + get: + type: http + endpoint: get /v1/conversations/{conversation_id}/items/{item_id} + list: + type: http + endpoint: get /v1/conversations/{conversation_id}/items + create: + type: http + endpoint: post /v1/conversations/{conversation_id}/items + + datasets: + models: + list_datasets_response: ListDatasetsResponse + methods: + register: post /v1beta/datasets + retrieve: get /v1beta/datasets/{dataset_id} + list: + endpoint: get /v1beta/datasets + paginated: false + unregister: delete /v1beta/datasets/{dataset_id} + iterrows: get /v1beta/datasetio/iterrows/{dataset_id} + appendrows: post /v1beta/datasetio/append-rows/{dataset_id} + + inspect: + models: + healthInfo: HealthInfo + providerInfo: ProviderInfo + routeInfo: RouteInfo + versionInfo: VersionInfo + methods: + health: get /v1/health + version: get /v1/version + + embeddings: + models: + create_embeddings_response: OpenAIEmbeddingsResponse + methods: + create: post /v1/embeddings + + chat: + models: + chat_completion_chunk: OpenAIChatCompletionChunk + subresources: + completions: + methods: + create: + type: http + endpoint: post /v1/chat/completions + streaming: + stream_event_model: chat.chat_completion_chunk + param_discriminator: stream + list: + type: http + endpoint: get /v1/chat/completions + retrieve: + type: http + endpoint: get /v1/chat/completions/{completion_id} + completions: + methods: + create: + type: http + endpoint: post /v1/completions + streaming: + param_discriminator: stream + + vector_io: + models: + queryChunksResponse: QueryChunksResponse + methods: + insert: post /v1/vector-io/insert + query: post /v1/vector-io/query + + vector_stores: + models: + vector_store: VectorStoreObject + list_vector_stores_response: VectorStoreListResponse + vector_store_delete_response: VectorStoreDeleteResponse + vector_store_search_response: VectorStoreSearchResponsePage + methods: + create: post /v1/vector_stores + list: + endpoint: get /v1/vector_stores + retrieve: get /v1/vector_stores/{vector_store_id} + update: post /v1/vector_stores/{vector_store_id} + delete: delete /v1/vector_stores/{vector_store_id} + search: post /v1/vector_stores/{vector_store_id}/search + subresources: + files: + models: + vector_store_file: VectorStoreFileObject + methods: + list: get /v1/vector_stores/{vector_store_id}/files + retrieve: get /v1/vector_stores/{vector_store_id}/files/{file_id} + update: post /v1/vector_stores/{vector_store_id}/files/{file_id} + delete: delete /v1/vector_stores/{vector_store_id}/files/{file_id} + create: post /v1/vector_stores/{vector_store_id}/files + content: get /v1/vector_stores/{vector_store_id}/files/{file_id}/content + file_batches: + models: + vector_store_file_batches: VectorStoreFileBatchObject + list_vector_store_files_in_batch_response: VectorStoreFilesListInBatchResponse + methods: + create: post /v1/vector_stores/{vector_store_id}/file_batches + retrieve: get /v1/vector_stores/{vector_store_id}/file_batches/{batch_id} + list_files: get /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files + cancel: post /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel + + models: + models: + model: Model + list_models_response: ListModelsResponse + methods: + retrieve: get /v1/models/{model_id} + list: + endpoint: get /v1/models + paginated: false + register: post /v1/models + unregister: delete /v1/models/{model_id} + subresources: + openai: + methods: + list: + endpoint: get /v1/models + paginated: false + + providers: + models: + list_providers_response: ListProvidersResponse + methods: + list: + endpoint: get /v1/providers + paginated: false + retrieve: get /v1/providers/{provider_id} + + routes: + models: + list_routes_response: ListRoutesResponse + methods: + list: + endpoint: get /v1/inspect/routes + paginated: false + + + moderations: + models: + create_response: ModerationObject + methods: + create: post /v1/moderations + + + safety: + models: + run_shield_response: RunShieldResponse + methods: + run_shield: post /v1/safety/run-shield + + + shields: + models: + shield: Shield + list_shields_response: ListShieldsResponse + methods: + retrieve: get /v1/shields/{identifier} + list: + endpoint: get /v1/shields + paginated: false + register: post /v1/shields + delete: delete /v1/shields/{identifier} + + synthetic_data_generation: + models: + syntheticDataGenerationResponse: SyntheticDataGenerationResponse + methods: + generate: post /v1/synthetic-data-generation/generate + + telemetry: + models: + span_with_status: SpanWithStatus + trace: Trace + query_spans_response: QuerySpansResponse + event: Event + query_condition: QueryCondition + methods: + query_traces: + endpoint: post /v1alpha/telemetry/traces + skip_test_reason: 'unsupported query params in java / kotlin' + get_span_tree: post /v1alpha/telemetry/spans/{span_id}/tree + query_spans: + endpoint: post /v1alpha/telemetry/spans + skip_test_reason: 'unsupported query params in java / kotlin' + query_metrics: + endpoint: post /v1alpha/telemetry/metrics/{metric_name} + skip_test_reason: 'unsupported query params in java / kotlin' + # log_event: post /v1alpha/telemetry/events + save_spans_to_dataset: post /v1alpha/telemetry/spans/export + get_span: get /v1alpha/telemetry/traces/{trace_id}/spans/{span_id} + get_trace: get /v1alpha/telemetry/traces/{trace_id} + + scoring: + methods: + score: post /v1/scoring/score + score_batch: post /v1/scoring/score-batch + scoring_functions: + methods: + retrieve: get /v1/scoring-functions/{scoring_fn_id} + list: + endpoint: get /v1/scoring-functions + paginated: false + register: post /v1/scoring-functions + models: + scoring_fn: ScoringFn + scoring_fn_params: ScoringFnParams + list_scoring_functions_response: ListScoringFunctionsResponse + + benchmarks: + methods: + retrieve: get /v1alpha/eval/benchmarks/{benchmark_id} + list: + endpoint: get /v1alpha/eval/benchmarks + paginated: false + register: post /v1alpha/eval/benchmarks + models: + benchmark: Benchmark + list_benchmarks_response: ListBenchmarksResponse + + files: + methods: + create: post /v1/files + list: get /v1/files + retrieve: get /v1/files/{file_id} + delete: delete /v1/files/{file_id} + content: get /v1/files/{file_id}/content + models: + file: OpenAIFileObject + list_files_response: ListOpenAIFileResponse + delete_file_response: OpenAIFileDeleteResponse + + alpha: + subresources: + inference: + methods: + rerank: post /v1alpha/inference/rerank + + post_training: + models: + algorithm_config: AlgorithmConfig + post_training_job: PostTrainingJob + list_post_training_jobs_response: ListPostTrainingJobsResponse + methods: + preference_optimize: post /v1alpha/post-training/preference-optimize + supervised_fine_tune: post /v1alpha/post-training/supervised-fine-tune + subresources: + job: + methods: + artifacts: get /v1alpha/post-training/job/artifacts + cancel: post /v1alpha/post-training/job/cancel + status: get /v1alpha/post-training/job/status + list: + endpoint: get /v1alpha/post-training/jobs + paginated: false + + eval: + methods: + evaluate_rows: post /v1alpha/eval/benchmarks/{benchmark_id}/evaluations + run_eval: post /v1alpha/eval/benchmarks/{benchmark_id}/jobs + evaluate_rows_alpha: post /v1alpha/eval/benchmarks/{benchmark_id}/evaluations + run_eval_alpha: post /v1alpha/eval/benchmarks/{benchmark_id}/jobs + + subresources: + jobs: + methods: + cancel: delete /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id} + status: get /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id} + retrieve: get /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result + models: + evaluate_response: EvaluateResponse + benchmark_config: BenchmarkConfig + job: Job + + agents: + methods: + create: post /v1alpha/agents + list: get /v1alpha/agents + retrieve: get /v1alpha/agents/{agent_id} + delete: delete /v1alpha/agents/{agent_id} + models: + inference_step: InferenceStep + tool_execution_step: ToolExecutionStep + tool_response: ToolResponse + shield_call_step: ShieldCallStep + memory_retrieval_step: MemoryRetrievalStep + subresources: + session: + models: + session: Session + methods: + list: get /v1alpha/agents/{agent_id}/sessions + create: post /v1alpha/agents/{agent_id}/session + delete: delete /v1alpha/agents/{agent_id}/session/{session_id} + retrieve: get /v1alpha/agents/{agent_id}/session/{session_id} + steps: + methods: + retrieve: get /v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id} + turn: + models: + turn: Turn + turn_response_event: AgentTurnResponseEvent + agent_turn_response_stream_chunk: AgentTurnResponseStreamChunk + methods: + create: + type: http + endpoint: post /v1alpha/agents/{agent_id}/session/{session_id}/turn + streaming: + stream_event_model: alpha.agents.turn.agent_turn_response_stream_chunk + param_discriminator: stream + retrieve: get /v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id} + resume: + type: http + endpoint: post /v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume + streaming: + stream_event_model: alpha.agents.turn.agent_turn_response_stream_chunk + param_discriminator: stream + + +settings: + license: MIT + unwrap_response_fields: [ data ] + +openapi: + transformations: + - command: renameValue + reason: pydantic reserved name + args: + filter: + only: + - '$.components.schemas.InferenceStep.properties.model_response' + rename: + python: + property_name: 'inference_model_response' + + # - command: renameValue + # reason: pydantic reserved name + # args: + # filter: + # only: + # - '$.components.schemas.Model.properties.model_type' + # rename: + # python: + # property_name: 'type' + - command: mergeObject + reason: Better return_type using enum + args: + target: + - '$.components.schemas' + object: + ReturnType: + additionalProperties: false + properties: + type: + enum: + - string + - number + - boolean + - array + - object + - json + - union + - chat_completion_input + - completion_input + - agent_turn_input + required: + - type + type: object + - command: replaceProperties + reason: Replace return type properties with better model (see above) + args: + filter: + only: + - '$.components.schemas.ScoringFn.properties.return_type' + - '$.components.schemas.RegisterScoringFunctionRequest.properties.return_type' + value: + $ref: '#/components/schemas/ReturnType' + - command: oneOfToAnyOf + reason: Prism (mock server) doesn't like one of our requests as it technically matches multiple variants + - reason: For better names + command: extractToRefs + args: + ref: + target: '$.components.schemas.ToolCallDelta.properties.tool_call' + name: '#/components/schemas/ToolCallOrString' + +# `readme` is used to configure the code snippets that will be rendered in the +# README.md of various SDKs. In particular, you can change the `headline` +# snippet's endpoint and the arguments to call it with. +readme: + example_requests: + default: + type: request + endpoint: post /v1/chat/completions + params: &ref_0 {} + headline: + type: request + endpoint: post /v1/models + params: *ref_0 + pagination: + type: request + endpoint: post /v1/chat/completions + params: {} diff --git a/client-sdks/stainless/openapi.yml b/client-sdks/stainless/openapi.yml new file mode 100644 index 000000000..eff01931f --- /dev/null +++ b/client-sdks/stainless/openapi.yml @@ -0,0 +1,13653 @@ +openapi: 3.1.0 +info: + title: >- + Llama Stack Specification - Stable & Experimental APIs + version: v1 + description: >- + This is the specification of the Llama Stack that provides + a set of endpoints and their corresponding interfaces that are + tailored to + best leverage Llama Models. + + **🔗 COMBINED**: This specification includes both stable production-ready APIs + and experimental pre-release APIs. Use stable APIs for production deployments + and experimental APIs for testing new features. +servers: + - url: http://any-hosted-llama-stack.com +paths: + /v1/chat/completions: + get: + responses: + '200': + description: A ListOpenAIChatCompletionResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListOpenAIChatCompletionResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inference + summary: List chat completions. + description: List chat completions. + parameters: + - name: after + in: query + description: >- + The ID of the last chat completion to return. + required: false + schema: + type: string + - name: limit + in: query + description: >- + The maximum number of chat completions to return. + required: false + schema: + type: integer + - name: model + in: query + description: The model to filter by. + required: false + schema: + type: string + - name: order + in: query + description: >- + The order to sort the chat completions by: "asc" or "desc". Defaults to + "desc". + required: false + schema: + $ref: '#/components/schemas/Order' + deprecated: false + post: + responses: + '200': + description: An OpenAIChatCompletion. + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/OpenAIChatCompletion' + - $ref: '#/components/schemas/OpenAIChatCompletionChunk' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inference + summary: Create chat completions. + description: >- + Create chat completions. + + Generate an OpenAI-compatible chat completion for the given messages using + the specified model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIChatCompletionRequestWithExtraBody' + required: true + deprecated: false + /v1/chat/completions/{completion_id}: + get: + responses: + '200': + description: A OpenAICompletionWithInputMessages. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAICompletionWithInputMessages' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inference + summary: Get chat completion. + description: >- + Get chat completion. + + Describe a chat completion by its ID. + parameters: + - name: completion_id + in: path + description: ID of the chat completion. + required: true + schema: + type: string + deprecated: false + /v1/completions: + post: + responses: + '200': + description: An OpenAICompletion. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAICompletion' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inference + summary: Create completion. + description: >- + Create completion. + + Generate an OpenAI-compatible completion for the given prompt using the specified + model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAICompletionRequestWithExtraBody' + required: true + deprecated: false + /v1/conversations: + post: + responses: + '200': + description: The created conversation object. + content: + application/json: + schema: + $ref: '#/components/schemas/Conversation' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Create a conversation. + description: >- + Create a conversation. + + Create a conversation. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateConversationRequest' + required: true + deprecated: false + /v1/conversations/{conversation_id}: + get: + responses: + '200': + description: The conversation object. + content: + application/json: + schema: + $ref: '#/components/schemas/Conversation' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Retrieve a conversation. + description: >- + Retrieve a conversation. + + Get a conversation with the given ID. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + deprecated: false + post: + responses: + '200': + description: The updated conversation object. + content: + application/json: + schema: + $ref: '#/components/schemas/Conversation' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Update a conversation. + description: >- + Update a conversation. + + Update a conversation's metadata with the given ID. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/UpdateConversationRequest' + required: true + deprecated: false + delete: + responses: + '200': + description: The deleted conversation resource. + content: + application/json: + schema: + $ref: '#/components/schemas/ConversationDeletedResource' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Delete a conversation. + description: >- + Delete a conversation. + + Delete a conversation with the given ID. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + deprecated: false + /v1/conversations/{conversation_id}/items: + get: + responses: + '200': + description: List of conversation items. + content: + application/json: + schema: + $ref: '#/components/schemas/ConversationItemList' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: List items. + description: >- + List items. + + List items in the conversation. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + - name: after + in: query + description: >- + An item ID to list items after, used in pagination. + required: true + schema: + oneOf: + - type: string + - type: object + title: NotGiven + description: >- + A sentinel singleton class used to distinguish omitted keyword arguments + from those passed in with the value None (which may have different + behavior). + + For example: + + + ```py + + def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: + ... + + + + get(timeout=1) # 1s timeout + + get(timeout=None) # No timeout + + get() # Default timeout behavior, which may not be statically known + at the method definition. + + ``` + - name: include + in: query + description: >- + Specify additional output data to include in the response. + required: true + schema: + oneOf: + - type: array + items: + type: string + enum: + - code_interpreter_call.outputs + - computer_call_output.output.image_url + - file_search_call.results + - message.input_image.image_url + - message.output_text.logprobs + - reasoning.encrypted_content + - type: object + title: NotGiven + description: >- + A sentinel singleton class used to distinguish omitted keyword arguments + from those passed in with the value None (which may have different + behavior). + + For example: + + + ```py + + def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: + ... + + + + get(timeout=1) # 1s timeout + + get(timeout=None) # No timeout + + get() # Default timeout behavior, which may not be statically known + at the method definition. + + ``` + - name: limit + in: query + description: >- + A limit on the number of objects to be returned (1-100, default 20). + required: true + schema: + oneOf: + - type: integer + - type: object + title: NotGiven + description: >- + A sentinel singleton class used to distinguish omitted keyword arguments + from those passed in with the value None (which may have different + behavior). + + For example: + + + ```py + + def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: + ... + + + + get(timeout=1) # 1s timeout + + get(timeout=None) # No timeout + + get() # Default timeout behavior, which may not be statically known + at the method definition. + + ``` + - name: order + in: query + description: >- + The order to return items in (asc or desc, default desc). + required: true + schema: + oneOf: + - type: string + enum: + - asc + - desc + - type: object + title: NotGiven + description: >- + A sentinel singleton class used to distinguish omitted keyword arguments + from those passed in with the value None (which may have different + behavior). + + For example: + + + ```py + + def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: + ... + + + + get(timeout=1) # 1s timeout + + get(timeout=None) # No timeout + + get() # Default timeout behavior, which may not be statically known + at the method definition. + + ``` + deprecated: false + post: + responses: + '200': + description: List of created items. + content: + application/json: + schema: + $ref: '#/components/schemas/ConversationItemList' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Create items. + description: >- + Create items. + + Create items in the conversation. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/AddItemsRequest' + required: true + deprecated: false + /v1/conversations/{conversation_id}/items/{item_id}: + get: + responses: + '200': + description: The conversation item. + content: + application/json: + schema: + $ref: '#/components/schemas/ConversationItem' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Retrieve an item. + description: >- + Retrieve an item. + + Retrieve a conversation item. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + - name: item_id + in: path + description: The item identifier. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: The deleted item resource. + content: + application/json: + schema: + $ref: '#/components/schemas/ConversationItemDeletedResource' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Conversations + summary: Delete an item. + description: >- + Delete an item. + + Delete a conversation item. + parameters: + - name: conversation_id + in: path + description: The conversation identifier. + required: true + schema: + type: string + - name: item_id + in: path + description: The item identifier. + required: true + schema: + type: string + deprecated: false + /v1/embeddings: + post: + responses: + '200': + description: >- + An OpenAIEmbeddingsResponse containing the embeddings. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIEmbeddingsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inference + summary: Create embeddings. + description: >- + Create embeddings. + + Generate OpenAI-compatible embeddings for the given input using the specified + model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody' + required: true + deprecated: false + /v1/files: + get: + responses: + '200': + description: >- + An ListOpenAIFileResponse containing the list of files. + content: + application/json: + schema: + $ref: '#/components/schemas/ListOpenAIFileResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Files + summary: List files. + description: >- + List files. + + Returns a list of files that belong to the user's organization. + parameters: + - name: after + in: query + description: >- + A cursor for use in pagination. `after` is an object ID that defines your + place in the list. For instance, if you make a list request and receive + 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo + in order to fetch the next page of the list. + required: false + schema: + type: string + - name: limit + in: query + description: >- + A limit on the number of objects to be returned. Limit can range between + 1 and 10,000, and the default is 10,000. + required: false + schema: + type: integer + - name: order + in: query + description: >- + Sort order by the `created_at` timestamp of the objects. `asc` for ascending + order and `desc` for descending order. + required: false + schema: + $ref: '#/components/schemas/Order' + - name: purpose + in: query + description: >- + Only return files with the given purpose. + required: false + schema: + $ref: '#/components/schemas/OpenAIFilePurpose' + deprecated: false + post: + responses: + '200': + description: >- + An OpenAIFileObject representing the uploaded file. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIFileObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Files + summary: Upload file. + description: >- + Upload file. + + Upload a file that can be used across various endpoints. + + + The file upload should be a multipart form request with: + + - file: The File object (not file name) to be uploaded. + + - purpose: The intended purpose of the uploaded file. + + - expires_after: Optional form values describing expiration for the file. + parameters: [] + requestBody: + content: + multipart/form-data: + schema: + type: object + properties: + file: + type: string + format: binary + purpose: + $ref: '#/components/schemas/OpenAIFilePurpose' + expires_after: + $ref: '#/components/schemas/ExpiresAfter' + required: + - file + - purpose + required: true + deprecated: false + /v1/files/{file_id}: + get: + responses: + '200': + description: >- + An OpenAIFileObject containing file information. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIFileObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Files + summary: Retrieve file. + description: >- + Retrieve file. + + Returns information about a specific file. + parameters: + - name: file_id + in: path + description: >- + The ID of the file to use for this request. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: >- + An OpenAIFileDeleteResponse indicating successful deletion. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIFileDeleteResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Files + summary: Delete file. + description: Delete file. + parameters: + - name: file_id + in: path + description: >- + The ID of the file to use for this request. + required: true + schema: + type: string + deprecated: false + /v1/files/{file_id}/content: + get: + responses: + '200': + description: >- + The raw file content as a binary response. + content: + application/json: + schema: + $ref: '#/components/schemas/Response' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Files + summary: Retrieve file content. + description: >- + Retrieve file content. + + Returns the contents of the specified file. + parameters: + - name: file_id + in: path + description: >- + The ID of the file to use for this request. + required: true + schema: + type: string + deprecated: false + /v1/health: + get: + responses: + '200': + description: >- + Health information indicating if the service is operational. + content: + application/json: + schema: + $ref: '#/components/schemas/HealthInfo' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inspect + summary: Get health status. + description: >- + Get health status. + + Get the current health status of the service. + parameters: [] + deprecated: false + /v1/inspect/routes: + get: + responses: + '200': + description: >- + Response containing information about all available routes. + content: + application/json: + schema: + $ref: '#/components/schemas/ListRoutesResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inspect + summary: List routes. + description: >- + List routes. + + List all available API routes with their methods and implementing providers. + parameters: [] + deprecated: false + /v1/models: + get: + responses: + '200': + description: A ListModelsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListModelsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: List all models. + description: List all models. + parameters: [] + deprecated: false + post: + responses: + '200': + description: A Model. + content: + application/json: + schema: + $ref: '#/components/schemas/Model' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Register model. + description: >- + Register model. + + Register a model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterModelRequest' + required: true + deprecated: false + /v1/models/{model_id}: + get: + responses: + '200': + description: A Model. + content: + application/json: + schema: + $ref: '#/components/schemas/Model' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Get model. + description: >- + Get model. + + Get a model by its identifier. + parameters: + - name: model_id + in: path + description: The identifier of the model to get. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Unregister model. + description: >- + Unregister model. + + Unregister a model. + parameters: + - name: model_id + in: path + description: >- + The identifier of the model to unregister. + required: true + schema: + type: string + deprecated: false + /v1/moderations: + post: + responses: + '200': + description: A moderation object. + content: + application/json: + schema: + $ref: '#/components/schemas/ModerationObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Safety + summary: Create moderation. + description: >- + Create moderation. + + Classifies if text and/or image inputs are potentially harmful. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RunModerationRequest' + required: true + deprecated: false + /v1/prompts: + get: + responses: + '200': + description: >- + A ListPromptsResponse containing all prompts. + content: + application/json: + schema: + $ref: '#/components/schemas/ListPromptsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: List all prompts. + description: List all prompts. + parameters: [] + deprecated: false + post: + responses: + '200': + description: The created Prompt resource. + content: + application/json: + schema: + $ref: '#/components/schemas/Prompt' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: Create prompt. + description: >- + Create prompt. + + Create a new prompt. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreatePromptRequest' + required: true + deprecated: false + /v1/prompts/{prompt_id}: + get: + responses: + '200': + description: A Prompt resource. + content: + application/json: + schema: + $ref: '#/components/schemas/Prompt' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: Get prompt. + description: >- + Get prompt. + + Get a prompt by its identifier and optional version. + parameters: + - name: prompt_id + in: path + description: The identifier of the prompt to get. + required: true + schema: + type: string + - name: version + in: query + description: >- + The version of the prompt to get (defaults to latest). + required: false + schema: + type: integer + deprecated: false + post: + responses: + '200': + description: >- + The updated Prompt resource with incremented version. + content: + application/json: + schema: + $ref: '#/components/schemas/Prompt' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: Update prompt. + description: >- + Update prompt. + + Update an existing prompt (increments version). + parameters: + - name: prompt_id + in: path + description: The identifier of the prompt to update. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/UpdatePromptRequest' + required: true + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: Delete prompt. + description: >- + Delete prompt. + + Delete a prompt. + parameters: + - name: prompt_id + in: path + description: The identifier of the prompt to delete. + required: true + schema: + type: string + deprecated: false + /v1/prompts/{prompt_id}/set-default-version: + post: + responses: + '200': + description: >- + The prompt with the specified version now set as default. + content: + application/json: + schema: + $ref: '#/components/schemas/Prompt' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: Set prompt version. + description: >- + Set prompt version. + + Set which version of a prompt should be the default in get_prompt (latest). + parameters: + - name: prompt_id + in: path + description: The identifier of the prompt. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/SetDefaultVersionRequest' + required: true + deprecated: false + /v1/prompts/{prompt_id}/versions: + get: + responses: + '200': + description: >- + A ListPromptsResponse containing all versions of the prompt. + content: + application/json: + schema: + $ref: '#/components/schemas/ListPromptsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Prompts + summary: List prompt versions. + description: >- + List prompt versions. + + List all versions of a specific prompt. + parameters: + - name: prompt_id + in: path + description: >- + The identifier of the prompt to list versions for. + required: true + schema: + type: string + deprecated: false + /v1/providers: + get: + responses: + '200': + description: >- + A ListProvidersResponse containing information about all providers. + content: + application/json: + schema: + $ref: '#/components/schemas/ListProvidersResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Providers + summary: List providers. + description: >- + List providers. + + List all available providers. + parameters: [] + deprecated: false + /v1/providers/{provider_id}: + get: + responses: + '200': + description: >- + A ProviderInfo object containing the provider's details. + content: + application/json: + schema: + $ref: '#/components/schemas/ProviderInfo' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Providers + summary: Get provider. + description: >- + Get provider. + + Get detailed information about a specific provider. + parameters: + - name: provider_id + in: path + description: The ID of the provider to inspect. + required: true + schema: + type: string + deprecated: false + /v1/responses: + get: + responses: + '200': + description: A ListOpenAIResponseObject. + content: + application/json: + schema: + $ref: '#/components/schemas/ListOpenAIResponseObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: List all responses. + description: List all responses. + parameters: + - name: after + in: query + description: The ID of the last response to return. + required: false + schema: + type: string + - name: limit + in: query + description: The number of responses to return. + required: false + schema: + type: integer + - name: model + in: query + description: The model to filter responses by. + required: false + schema: + type: string + - name: order + in: query + description: >- + The order to sort responses by when sorted by created_at ('asc' or 'desc'). + required: false + schema: + $ref: '#/components/schemas/Order' + deprecated: false + post: + responses: + '200': + description: An OpenAIResponseObject. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIResponseObject' + text/event-stream: + schema: + $ref: '#/components/schemas/OpenAIResponseObjectStream' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Create a model response. + description: Create a model response. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateOpenaiResponseRequest' + required: true + deprecated: false + x-llama-stack-extra-body-params: + - name: guardrails + schema: + type: array + items: + oneOf: + - type: string + - $ref: '#/components/schemas/ResponseGuardrailSpec' + description: >- + List of guardrails to apply during response generation. Guardrails provide + safety and content moderation. + required: false + /v1/responses/{response_id}: + get: + responses: + '200': + description: An OpenAIResponseObject. + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIResponseObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Get a model response. + description: Get a model response. + parameters: + - name: response_id + in: path + description: >- + The ID of the OpenAI response to retrieve. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: An OpenAIDeleteResponseObject + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAIDeleteResponseObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Delete a response. + description: Delete a response. + parameters: + - name: response_id + in: path + description: The ID of the OpenAI response to delete. + required: true + schema: + type: string + deprecated: false + /v1/responses/{response_id}/input_items: + get: + responses: + '200': + description: An ListOpenAIResponseInputItem. + content: + application/json: + schema: + $ref: '#/components/schemas/ListOpenAIResponseInputItem' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: List input items. + description: List input items. + parameters: + - name: response_id + in: path + description: >- + The ID of the response to retrieve input items for. + required: true + schema: + type: string + - name: after + in: query + description: >- + An item ID to list items after, used for pagination. + required: false + schema: + type: string + - name: before + in: query + description: >- + An item ID to list items before, used for pagination. + required: false + schema: + type: string + - name: include + in: query + description: >- + Additional fields to include in the response. + required: false + schema: + type: array + items: + type: string + - name: limit + in: query + description: >- + A limit on the number of objects to be returned. Limit can range between + 1 and 100, and the default is 20. + required: false + schema: + type: integer + - name: order + in: query + description: >- + The order to return the input items in. Default is desc. + required: false + schema: + $ref: '#/components/schemas/Order' + deprecated: false + /v1/safety/run-shield: + post: + responses: + '200': + description: A RunShieldResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/RunShieldResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Safety + summary: Run shield. + description: >- + Run shield. + + Run a shield. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RunShieldRequest' + required: true + deprecated: false + /v1/scoring-functions: + get: + responses: + '200': + description: A ListScoringFunctionsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListScoringFunctionsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: List all scoring functions. + description: List all scoring functions. + parameters: [] + deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Register a scoring function. + description: Register a scoring function. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterScoringFunctionRequest' + required: true + deprecated: false + /v1/scoring-functions/{scoring_fn_id}: + get: + responses: + '200': + description: A ScoringFn. + content: + application/json: + schema: + $ref: '#/components/schemas/ScoringFn' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Get a scoring function by its ID. + description: Get a scoring function by its ID. + parameters: + - name: scoring_fn_id + in: path + description: The ID of the scoring function to get. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Unregister a scoring function. + description: Unregister a scoring function. + parameters: + - name: scoring_fn_id + in: path + description: >- + The ID of the scoring function to unregister. + required: true + schema: + type: string + deprecated: false + /v1/scoring/score: + post: + responses: + '200': + description: >- + A ScoreResponse object containing rows and aggregated results. + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Scoring + summary: Score a list of rows. + description: Score a list of rows. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreRequest' + required: true + deprecated: false + /v1/scoring/score-batch: + post: + responses: + '200': + description: A ScoreBatchResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreBatchResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Scoring + summary: Score a batch of rows. + description: Score a batch of rows. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreBatchRequest' + required: true + deprecated: false + /v1/shields: + get: + responses: + '200': + description: A ListShieldsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListShieldsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: List all shields. + description: List all shields. + parameters: [] + deprecated: false + post: + responses: + '200': + description: A Shield. + content: + application/json: + schema: + $ref: '#/components/schemas/Shield' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Register a shield. + description: Register a shield. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterShieldRequest' + required: true + deprecated: false + /v1/shields/{identifier}: + get: + responses: + '200': + description: A Shield. + content: + application/json: + schema: + $ref: '#/components/schemas/Shield' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Get a shield by its identifier. + description: Get a shield by its identifier. + parameters: + - name: identifier + in: path + description: The identifier of the shield to get. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Unregister a shield. + description: Unregister a shield. + parameters: + - name: identifier + in: path + description: >- + The identifier of the shield to unregister. + required: true + schema: + type: string + deprecated: false + /v1/synthetic-data-generation/generate: + post: + responses: + '200': + description: >- + Response containing filtered synthetic data samples and optional statistics + content: + application/json: + schema: + $ref: '#/components/schemas/SyntheticDataGenerationResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - SyntheticDataGeneration (Coming Soon) + summary: >- + Generate synthetic data based on input dialogs and apply filtering. + description: >- + Generate synthetic data based on input dialogs and apply filtering. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/SyntheticDataGenerateRequest' + required: true + deprecated: false + /v1/tool-runtime/invoke: + post: + responses: + '200': + description: A ToolInvocationResult. + content: + application/json: + schema: + $ref: '#/components/schemas/ToolInvocationResult' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolRuntime + summary: Run a tool with the given arguments. + description: Run a tool with the given arguments. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/InvokeToolRequest' + required: true + deprecated: false + /v1/tool-runtime/list-tools: + get: + responses: + '200': + description: A ListToolDefsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListToolDefsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolRuntime + summary: List all tools in the runtime. + description: List all tools in the runtime. + parameters: + - name: tool_group_id + in: query + description: >- + The ID of the tool group to list tools for. + required: false + schema: + type: string + - name: mcp_endpoint + in: query + description: >- + The MCP endpoint to use for the tool group. + required: false + schema: + $ref: '#/components/schemas/URL' + deprecated: false + /v1/tool-runtime/rag-tool/insert: + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolRuntime + summary: >- + Index documents so they can be used by the RAG system. + description: >- + Index documents so they can be used by the RAG system. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/InsertRequest' + required: true + deprecated: false + /v1/tool-runtime/rag-tool/query: + post: + responses: + '200': + description: >- + RAGQueryResult containing the retrieved content and metadata + content: + application/json: + schema: + $ref: '#/components/schemas/RAGQueryResult' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolRuntime + summary: >- + Query the RAG system for context; typically invoked by the agent. + description: >- + Query the RAG system for context; typically invoked by the agent. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/QueryRequest' + required: true + deprecated: false + /v1/toolgroups: + get: + responses: + '200': + description: A ListToolGroupsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListToolGroupsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: List tool groups with optional provider. + description: List tool groups with optional provider. + parameters: [] + deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Register a tool group. + description: Register a tool group. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterToolGroupRequest' + required: true + deprecated: false + /v1/toolgroups/{toolgroup_id}: + get: + responses: + '200': + description: A ToolGroup. + content: + application/json: + schema: + $ref: '#/components/schemas/ToolGroup' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Get a tool group by its ID. + description: Get a tool group by its ID. + parameters: + - name: toolgroup_id + in: path + description: The ID of the tool group to get. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Unregister a tool group. + description: Unregister a tool group. + parameters: + - name: toolgroup_id + in: path + description: The ID of the tool group to unregister. + required: true + schema: + type: string + deprecated: false + /v1/tools: + get: + responses: + '200': + description: A ListToolDefsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListToolDefsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: List tools with optional tool group. + description: List tools with optional tool group. + parameters: + - name: toolgroup_id + in: query + description: >- + The ID of the tool group to list tools for. + required: false + schema: + type: string + deprecated: false + /v1/tools/{tool_name}: + get: + responses: + '200': + description: A ToolDef. + content: + application/json: + schema: + $ref: '#/components/schemas/ToolDef' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Get a tool by its name. + description: Get a tool by its name. + parameters: + - name: tool_name + in: path + description: The name of the tool to get. + required: true + schema: + type: string + deprecated: false + /v1/vector-io/insert: + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Insert chunks into a vector database. + description: Insert chunks into a vector database. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/InsertChunksRequest' + required: true + deprecated: false + /v1/vector-io/query: + post: + responses: + '200': + description: A QueryChunksResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/QueryChunksResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Query chunks from a vector database. + description: Query chunks from a vector database. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/QueryChunksRequest' + required: true + deprecated: false + /v1/vector_stores: + get: + responses: + '200': + description: >- + A VectorStoreListResponse containing the list of vector stores. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreListResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Returns a list of vector stores. + description: Returns a list of vector stores. + parameters: + - name: limit + in: query + description: >- + A limit on the number of objects to be returned. Limit can range between + 1 and 100, and the default is 20. + required: false + schema: + type: integer + - name: order + in: query + description: >- + Sort order by the `created_at` timestamp of the objects. `asc` for ascending + order and `desc` for descending order. + required: false + schema: + type: string + - name: after + in: query + description: >- + A cursor for use in pagination. `after` is an object ID that defines your + place in the list. + required: false + schema: + type: string + - name: before + in: query + description: >- + A cursor for use in pagination. `before` is an object ID that defines + your place in the list. + required: false + schema: + type: string + deprecated: false + post: + responses: + '200': + description: >- + A VectorStoreObject representing the created vector store. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Creates a vector store. + description: >- + Creates a vector store. + + Generate an OpenAI-compatible vector store with the given parameters. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody' + required: true + deprecated: false + /v1/vector_stores/{vector_store_id}: + get: + responses: + '200': + description: >- + A VectorStoreObject representing the vector store. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Retrieves a vector store. + description: Retrieves a vector store. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store to retrieve. + required: true + schema: + type: string + deprecated: false + post: + responses: + '200': + description: >- + A VectorStoreObject representing the updated vector store. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Updates a vector store. + description: Updates a vector store. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store to update. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenaiUpdateVectorStoreRequest' + required: true + deprecated: false + delete: + responses: + '200': + description: >- + A VectorStoreDeleteResponse indicating the deletion status. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreDeleteResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Delete a vector store. + description: Delete a vector store. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store to delete. + required: true + schema: + type: string + deprecated: false + /v1/vector_stores/{vector_store_id}/file_batches: + post: + responses: + '200': + description: >- + A VectorStoreFileBatchObject representing the created file batch. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileBatchObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Create a vector store file batch. + description: >- + Create a vector store file batch. + + Generate an OpenAI-compatible vector store file batch for the given vector + store. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store to create the file batch for. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody' + required: true + deprecated: false + /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}: + get: + responses: + '200': + description: >- + A VectorStoreFileBatchObject representing the file batch. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileBatchObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Retrieve a vector store file batch. + description: Retrieve a vector store file batch. + parameters: + - name: batch_id + in: path + description: The ID of the file batch to retrieve. + required: true + schema: + type: string + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file batch. + required: true + schema: + type: string + deprecated: false + /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel: + post: + responses: + '200': + description: >- + A VectorStoreFileBatchObject representing the cancelled file batch. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileBatchObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Cancels a vector store file batch. + description: Cancels a vector store file batch. + parameters: + - name: batch_id + in: path + description: The ID of the file batch to cancel. + required: true + schema: + type: string + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file batch. + required: true + schema: + type: string + deprecated: false + /v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files: + get: + responses: + '200': + description: >- + A VectorStoreFilesListInBatchResponse containing the list of files in + the batch. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFilesListInBatchResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: >- + Returns a list of vector store files in a batch. + description: >- + Returns a list of vector store files in a batch. + parameters: + - name: batch_id + in: path + description: >- + The ID of the file batch to list files from. + required: true + schema: + type: string + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file batch. + required: true + schema: + type: string + - name: after + in: query + description: >- + A cursor for use in pagination. `after` is an object ID that defines your + place in the list. + required: false + schema: + type: string + - name: before + in: query + description: >- + A cursor for use in pagination. `before` is an object ID that defines + your place in the list. + required: false + schema: + type: string + - name: filter + in: query + description: >- + Filter by file status. One of in_progress, completed, failed, cancelled. + required: false + schema: + type: string + - name: limit + in: query + description: >- + A limit on the number of objects to be returned. Limit can range between + 1 and 100, and the default is 20. + required: false + schema: + type: integer + - name: order + in: query + description: >- + Sort order by the `created_at` timestamp of the objects. `asc` for ascending + order and `desc` for descending order. + required: false + schema: + type: string + deprecated: false + /v1/vector_stores/{vector_store_id}/files: + get: + responses: + '200': + description: >- + A VectorStoreListFilesResponse containing the list of files. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreListFilesResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: List files in a vector store. + description: List files in a vector store. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store to list files from. + required: true + schema: + type: string + - name: limit + in: query + description: >- + (Optional) A limit on the number of objects to be returned. Limit can + range between 1 and 100, and the default is 20. + required: false + schema: + type: integer + - name: order + in: query + description: >- + (Optional) Sort order by the `created_at` timestamp of the objects. `asc` + for ascending order and `desc` for descending order. + required: false + schema: + type: string + - name: after + in: query + description: >- + (Optional) A cursor for use in pagination. `after` is an object ID that + defines your place in the list. + required: false + schema: + type: string + - name: before + in: query + description: >- + (Optional) A cursor for use in pagination. `before` is an object ID that + defines your place in the list. + required: false + schema: + type: string + - name: filter + in: query + description: >- + (Optional) Filter by file status to only return files with the specified + status. + required: false + schema: + $ref: '#/components/schemas/VectorStoreFileStatus' + deprecated: false + post: + responses: + '200': + description: >- + A VectorStoreFileObject representing the attached file. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Attach a file to a vector store. + description: Attach a file to a vector store. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store to attach the file to. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenaiAttachFileToVectorStoreRequest' + required: true + deprecated: false + /v1/vector_stores/{vector_store_id}/files/{file_id}: + get: + responses: + '200': + description: >- + A VectorStoreFileObject representing the file. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Retrieves a vector store file. + description: Retrieves a vector store file. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file to retrieve. + required: true + schema: + type: string + - name: file_id + in: path + description: The ID of the file to retrieve. + required: true + schema: + type: string + deprecated: false + post: + responses: + '200': + description: >- + A VectorStoreFileObject representing the updated file. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileObject' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Updates a vector store file. + description: Updates a vector store file. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file to update. + required: true + schema: + type: string + - name: file_id + in: path + description: The ID of the file to update. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenaiUpdateVectorStoreFileRequest' + required: true + deprecated: false + delete: + responses: + '200': + description: >- + A VectorStoreFileDeleteResponse indicating the deletion status. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileDeleteResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Delete a vector store file. + description: Delete a vector store file. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file to delete. + required: true + schema: + type: string + - name: file_id + in: path + description: The ID of the file to delete. + required: true + schema: + type: string + deprecated: false + /v1/vector_stores/{vector_store_id}/files/{file_id}/content: + get: + responses: + '200': + description: >- + A list of InterleavedContent representing the file contents. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreFileContentsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: >- + Retrieves the contents of a vector store file. + description: >- + Retrieves the contents of a vector store file. + parameters: + - name: vector_store_id + in: path + description: >- + The ID of the vector store containing the file to retrieve. + required: true + schema: + type: string + - name: file_id + in: path + description: The ID of the file to retrieve. + required: true + schema: + type: string + deprecated: false + /v1/vector_stores/{vector_store_id}/search: + post: + responses: + '200': + description: >- + A VectorStoreSearchResponse containing the search results. + content: + application/json: + schema: + $ref: '#/components/schemas/VectorStoreSearchResponsePage' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - VectorIO + summary: Search for chunks in a vector store. + description: >- + Search for chunks in a vector store. + + Searches a vector store for relevant chunks based on a query and optional + file attribute filters. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store to search. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/OpenaiSearchVectorStoreRequest' + required: true + deprecated: false + /v1/version: + get: + responses: + '200': + description: >- + Version information containing the service version number. + content: + application/json: + schema: + $ref: '#/components/schemas/VersionInfo' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inspect + summary: Get version. + description: >- + Get version. + + Get the version of the service. + parameters: [] + deprecated: false + /v1beta/datasetio/append-rows/{dataset_id}: + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - DatasetIO + summary: Append rows to a dataset. + description: Append rows to a dataset. + parameters: + - name: dataset_id + in: path + description: >- + The ID of the dataset to append the rows to. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/AppendRowsRequest' + required: true + deprecated: false + /v1beta/datasetio/iterrows/{dataset_id}: + get: + responses: + '200': + description: A PaginatedResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/PaginatedResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - DatasetIO + summary: >- + Get a paginated list of rows from a dataset. + description: >- + Get a paginated list of rows from a dataset. + + Uses offset-based pagination where: + + - start_index: The starting index (0-based). If None, starts from beginning. + + - limit: Number of items to return. If None or -1, returns all items. + + + The response includes: + + - data: List of items for the current page. + + - has_more: Whether there are more items available after this set. + parameters: + - name: dataset_id + in: path + description: >- + The ID of the dataset to get the rows from. + required: true + schema: + type: string + - name: start_index + in: query + description: >- + Index into dataset for the first row to get. Get all rows if None. + required: false + schema: + type: integer + - name: limit + in: query + description: The number of rows to get. + required: false + schema: + type: integer + deprecated: false + /v1beta/datasets: + get: + responses: + '200': + description: A ListDatasetsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListDatasetsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Datasets + summary: List all datasets. + description: List all datasets. + parameters: [] + deprecated: false + post: + responses: + '200': + description: A Dataset. + content: + application/json: + schema: + $ref: '#/components/schemas/Dataset' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Datasets + summary: Register a new dataset. + description: Register a new dataset. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterDatasetRequest' + required: true + deprecated: false + /v1beta/datasets/{dataset_id}: + get: + responses: + '200': + description: A Dataset. + content: + application/json: + schema: + $ref: '#/components/schemas/Dataset' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Datasets + summary: Get a dataset by its ID. + description: Get a dataset by its ID. + parameters: + - name: dataset_id + in: path + description: The ID of the dataset to get. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Datasets + summary: Unregister a dataset by its ID. + description: Unregister a dataset by its ID. + parameters: + - name: dataset_id + in: path + description: The ID of the dataset to unregister. + required: true + schema: + type: string + deprecated: false + /v1alpha/agents: + get: + responses: + '200': + description: A PaginatedResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/PaginatedResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: List all agents. + description: List all agents. + parameters: + - name: start_index + in: query + description: The index to start the pagination from. + required: false + schema: + type: integer + - name: limit + in: query + description: The number of agents to return. + required: false + schema: + type: integer + deprecated: false + post: + responses: + '200': + description: >- + An AgentCreateResponse with the agent ID. + content: + application/json: + schema: + $ref: '#/components/schemas/AgentCreateResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: >- + Create an agent with the given configuration. + description: >- + Create an agent with the given configuration. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateAgentRequest' + required: true + deprecated: false + /v1alpha/agents/{agent_id}: + get: + responses: + '200': + description: An Agent of the agent. + content: + application/json: + schema: + $ref: '#/components/schemas/Agent' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Describe an agent by its ID. + description: Describe an agent by its ID. + parameters: + - name: agent_id + in: path + description: ID of the agent. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: >- + Delete an agent by its ID and its associated sessions and turns. + description: >- + Delete an agent by its ID and its associated sessions and turns. + parameters: + - name: agent_id + in: path + description: The ID of the agent to delete. + required: true + schema: + type: string + deprecated: false + /v1alpha/agents/{agent_id}/session: + post: + responses: + '200': + description: An AgentSessionCreateResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/AgentSessionCreateResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Create a new session for an agent. + description: Create a new session for an agent. + parameters: + - name: agent_id + in: path + description: >- + The ID of the agent to create the session for. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateAgentSessionRequest' + required: true + deprecated: false + /v1alpha/agents/{agent_id}/session/{session_id}: + get: + responses: + '200': + description: A Session. + content: + application/json: + schema: + $ref: '#/components/schemas/Session' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Retrieve an agent session by its ID. + description: Retrieve an agent session by its ID. + parameters: + - name: session_id + in: path + description: The ID of the session to get. + required: true + schema: + type: string + - name: agent_id + in: path + description: >- + The ID of the agent to get the session for. + required: true + schema: + type: string + - name: turn_ids + in: query + description: >- + (Optional) List of turn IDs to filter the session by. + required: false + schema: + type: array + items: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: >- + Delete an agent session by its ID and its associated turns. + description: >- + Delete an agent session by its ID and its associated turns. + parameters: + - name: session_id + in: path + description: The ID of the session to delete. + required: true + schema: + type: string + - name: agent_id + in: path + description: >- + The ID of the agent to delete the session for. + required: true + schema: + type: string + deprecated: false + /v1alpha/agents/{agent_id}/session/{session_id}/turn: + post: + responses: + '200': + description: >- + If stream=False, returns a Turn object. If stream=True, returns an SSE + event stream of AgentTurnResponseStreamChunk. + content: + application/json: + schema: + $ref: '#/components/schemas/Turn' + text/event-stream: + schema: + $ref: '#/components/schemas/AgentTurnResponseStreamChunk' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Create a new turn for an agent. + description: Create a new turn for an agent. + parameters: + - name: agent_id + in: path + description: >- + The ID of the agent to create the turn for. + required: true + schema: + type: string + - name: session_id + in: path + description: >- + The ID of the session to create the turn for. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateAgentTurnRequest' + required: true + deprecated: false + /v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}: + get: + responses: + '200': + description: A Turn. + content: + application/json: + schema: + $ref: '#/components/schemas/Turn' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Retrieve an agent turn by its ID. + description: Retrieve an agent turn by its ID. + parameters: + - name: agent_id + in: path + description: The ID of the agent to get the turn for. + required: true + schema: + type: string + - name: session_id + in: path + description: >- + The ID of the session to get the turn for. + required: true + schema: + type: string + - name: turn_id + in: path + description: The ID of the turn to get. + required: true + schema: + type: string + deprecated: false + /v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume: + post: + responses: + '200': + description: >- + A Turn object if stream is False, otherwise an AsyncIterator of AgentTurnResponseStreamChunk + objects. + content: + application/json: + schema: + $ref: '#/components/schemas/Turn' + text/event-stream: + schema: + $ref: '#/components/schemas/AgentTurnResponseStreamChunk' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: >- + Resume an agent turn with executed tool call responses. + description: >- + Resume an agent turn with executed tool call responses. + + When a Turn has the status `awaiting_input` due to pending input from client + side tool calls, this endpoint can be used to submit the outputs from the + tool calls once they are ready. + parameters: + - name: agent_id + in: path + description: The ID of the agent to resume. + required: true + schema: + type: string + - name: session_id + in: path + description: The ID of the session to resume. + required: true + schema: + type: string + - name: turn_id + in: path + description: The ID of the turn to resume. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/ResumeAgentTurnRequest' + required: true + deprecated: false + /v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}: + get: + responses: + '200': + description: An AgentStepResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/AgentStepResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: Retrieve an agent step by its ID. + description: Retrieve an agent step by its ID. + parameters: + - name: agent_id + in: path + description: The ID of the agent to get the step for. + required: true + schema: + type: string + - name: session_id + in: path + description: >- + The ID of the session to get the step for. + required: true + schema: + type: string + - name: turn_id + in: path + description: The ID of the turn to get the step for. + required: true + schema: + type: string + - name: step_id + in: path + description: The ID of the step to get. + required: true + schema: + type: string + deprecated: false + /v1alpha/agents/{agent_id}/sessions: + get: + responses: + '200': + description: A PaginatedResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/PaginatedResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Agents + summary: List all session(s) of a given agent. + description: List all session(s) of a given agent. + parameters: + - name: agent_id + in: path + description: >- + The ID of the agent to list sessions for. + required: true + schema: + type: string + - name: start_index + in: query + description: The index to start the pagination from. + required: false + schema: + type: integer + - name: limit + in: query + description: The number of sessions to return. + required: false + schema: + type: integer + deprecated: false + /v1alpha/eval/benchmarks: + get: + responses: + '200': + description: A ListBenchmarksResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListBenchmarksResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Benchmarks + summary: List all benchmarks. + description: List all benchmarks. + parameters: [] + deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Benchmarks + summary: Register a benchmark. + description: Register a benchmark. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterBenchmarkRequest' + required: true + deprecated: false + /v1alpha/eval/benchmarks/{benchmark_id}: + get: + responses: + '200': + description: A Benchmark. + content: + application/json: + schema: + $ref: '#/components/schemas/Benchmark' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Benchmarks + summary: Get a benchmark by its ID. + description: Get a benchmark by its ID. + parameters: + - name: benchmark_id + in: path + description: The ID of the benchmark to get. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Benchmarks + summary: Unregister a benchmark. + description: Unregister a benchmark. + parameters: + - name: benchmark_id + in: path + description: The ID of the benchmark to unregister. + required: true + schema: + type: string + deprecated: false + /v1alpha/eval/benchmarks/{benchmark_id}/evaluations: + post: + responses: + '200': + description: >- + EvaluateResponse object containing generations and scores. + content: + application/json: + schema: + $ref: '#/components/schemas/EvaluateResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Eval + summary: Evaluate a list of rows on a benchmark. + description: Evaluate a list of rows on a benchmark. + parameters: + - name: benchmark_id + in: path + description: >- + The ID of the benchmark to run the evaluation on. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/EvaluateRowsRequest' + required: true + deprecated: false + /v1alpha/eval/benchmarks/{benchmark_id}/jobs: + post: + responses: + '200': + description: >- + The job that was created to run the evaluation. + content: + application/json: + schema: + $ref: '#/components/schemas/Job' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Eval + summary: Run an evaluation on a benchmark. + description: Run an evaluation on a benchmark. + parameters: + - name: benchmark_id + in: path + description: >- + The ID of the benchmark to run the evaluation on. + required: true + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RunEvalRequest' + required: true + deprecated: false + /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}: + get: + responses: + '200': + description: The status of the evaluation job. + content: + application/json: + schema: + $ref: '#/components/schemas/Job' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Eval + summary: Get the status of a job. + description: Get the status of a job. + parameters: + - name: benchmark_id + in: path + description: >- + The ID of the benchmark to run the evaluation on. + required: true + schema: + type: string + - name: job_id + in: path + description: The ID of the job to get the status of. + required: true + schema: + type: string + deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Eval + summary: Cancel a job. + description: Cancel a job. + parameters: + - name: benchmark_id + in: path + description: >- + The ID of the benchmark to run the evaluation on. + required: true + schema: + type: string + - name: job_id + in: path + description: The ID of the job to cancel. + required: true + schema: + type: string + deprecated: false + /v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result: + get: + responses: + '200': + description: The result of the job. + content: + application/json: + schema: + $ref: '#/components/schemas/EvaluateResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Eval + summary: Get the result of a job. + description: Get the result of a job. + parameters: + - name: benchmark_id + in: path + description: >- + The ID of the benchmark to run the evaluation on. + required: true + schema: + type: string + - name: job_id + in: path + description: The ID of the job to get the result of. + required: true + schema: + type: string + deprecated: false + /v1alpha/inference/rerank: + post: + responses: + '200': + description: >- + RerankResponse with indices sorted by relevance score (descending). + content: + application/json: + schema: + $ref: '#/components/schemas/RerankResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Inference + summary: >- + Rerank a list of documents based on their relevance to a query. + description: >- + Rerank a list of documents based on their relevance to a query. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RerankRequest' + required: true + deprecated: false + /v1alpha/post-training/job/artifacts: + get: + responses: + '200': + description: A PostTrainingJobArtifactsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/PostTrainingJobArtifactsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - PostTraining (Coming Soon) + summary: Get the artifacts of a training job. + description: Get the artifacts of a training job. + parameters: + - name: job_uuid + in: query + description: >- + The UUID of the job to get the artifacts of. + required: true + schema: + type: string + deprecated: false + /v1alpha/post-training/job/cancel: + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - PostTraining (Coming Soon) + summary: Cancel a training job. + description: Cancel a training job. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CancelTrainingJobRequest' + required: true + deprecated: false + /v1alpha/post-training/job/status: + get: + responses: + '200': + description: A PostTrainingJobStatusResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/PostTrainingJobStatusResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - PostTraining (Coming Soon) + summary: Get the status of a training job. + description: Get the status of a training job. + parameters: + - name: job_uuid + in: query + description: >- + The UUID of the job to get the status of. + required: true + schema: + type: string + deprecated: false + /v1alpha/post-training/jobs: + get: + responses: + '200': + description: A ListPostTrainingJobsResponse. + content: + application/json: + schema: + $ref: '#/components/schemas/ListPostTrainingJobsResponse' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - PostTraining (Coming Soon) + summary: Get all training jobs. + description: Get all training jobs. + parameters: [] + deprecated: false + /v1alpha/post-training/preference-optimize: + post: + responses: + '200': + description: A PostTrainingJob. + content: + application/json: + schema: + $ref: '#/components/schemas/PostTrainingJob' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - PostTraining (Coming Soon) + summary: Run preference optimization of a model. + description: Run preference optimization of a model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/PreferenceOptimizeRequest' + required: true + deprecated: false + /v1alpha/post-training/supervised-fine-tune: + post: + responses: + '200': + description: A PostTrainingJob. + content: + application/json: + schema: + $ref: '#/components/schemas/PostTrainingJob' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - PostTraining (Coming Soon) + summary: Run supervised fine-tuning of a model. + description: Run supervised fine-tuning of a model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/SupervisedFineTuneRequest' + required: true + deprecated: false +jsonSchemaDialect: >- + https://json-schema.org/draft/2020-12/schema +components: + schemas: + Error: + type: object + properties: + status: + type: integer + description: HTTP status code + title: + type: string + description: >- + Error title, a short summary of the error which is invariant for an error + type + detail: + type: string + description: >- + Error detail, a longer human-readable description of the error + instance: + type: string + description: >- + (Optional) A URL which can be used to retrieve more information about + the specific occurrence of the error + additionalProperties: false + required: + - status + - title + - detail + title: Error + description: >- + Error response from the API. Roughly follows RFC 7807. + Order: + type: string + enum: + - asc + - desc + title: Order + description: Sort order for paginated responses. + ListOpenAIChatCompletionResponse: + type: object + properties: + data: + type: array + items: + type: object + properties: + id: + type: string + description: The ID of the chat completion + choices: + type: array + items: + $ref: '#/components/schemas/OpenAIChoice' + description: List of choices + object: + type: string + const: chat.completion + default: chat.completion + description: >- + The object type, which will be "chat.completion" + created: + type: integer + description: >- + The Unix timestamp in seconds when the chat completion was created + model: + type: string + description: >- + The model that was used to generate the chat completion + usage: + $ref: '#/components/schemas/OpenAIChatCompletionUsage' + description: >- + Token usage information for the completion + input_messages: + type: array + items: + $ref: '#/components/schemas/OpenAIMessageParam' + additionalProperties: false + required: + - id + - choices + - object + - created + - model + - input_messages + title: OpenAICompletionWithInputMessages + description: >- + List of chat completion objects with their input messages + has_more: + type: boolean + description: >- + Whether there are more completions available beyond this list + first_id: + type: string + description: ID of the first completion in this list + last_id: + type: string + description: ID of the last completion in this list + object: + type: string + const: list + default: list + description: >- + Must be "list" to identify this as a list response + additionalProperties: false + required: + - data + - has_more + - first_id + - last_id + - object + title: ListOpenAIChatCompletionResponse + description: >- + Response from listing OpenAI-compatible chat completions. + OpenAIAssistantMessageParam: + type: object + properties: + role: + type: string + const: assistant + default: assistant + description: >- + Must be "assistant" to identify this as the model's response + content: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + description: The content of the model's response + name: + type: string + description: >- + (Optional) The name of the assistant message participant. + tool_calls: + type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionToolCall' + description: >- + List of tool calls. Each tool call is an OpenAIChatCompletionToolCall + object. + additionalProperties: false + required: + - role + title: OpenAIAssistantMessageParam + description: >- + A message containing the model's (assistant) response in an OpenAI-compatible + chat completion request. + "OpenAIChatCompletionContentPartImageParam": + type: object + properties: + type: + type: string + const: image_url + default: image_url + description: >- + Must be "image_url" to identify this as image content + image_url: + $ref: '#/components/schemas/OpenAIImageURL' + description: >- + Image URL specification and processing details + additionalProperties: false + required: + - type + - image_url + title: >- + OpenAIChatCompletionContentPartImageParam + description: >- + Image content part for OpenAI-compatible chat completion messages. + OpenAIChatCompletionContentPartParam: + oneOf: + - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' + - $ref: '#/components/schemas/OpenAIFile' + discriminator: + propertyName: type + mapping: + text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' + file: '#/components/schemas/OpenAIFile' + OpenAIChatCompletionContentPartTextParam: + type: object + properties: + type: + type: string + const: text + default: text + description: >- + Must be "text" to identify this as text content + text: + type: string + description: The text content of the message + additionalProperties: false + required: + - type + - text + title: OpenAIChatCompletionContentPartTextParam + description: >- + Text content part for OpenAI-compatible chat completion messages. + OpenAIChatCompletionToolCall: + type: object + properties: + index: + type: integer + description: >- + (Optional) Index of the tool call in the list + id: + type: string + description: >- + (Optional) Unique identifier for the tool call + type: + type: string + const: function + default: function + description: >- + Must be "function" to identify this as a function call + function: + $ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction' + description: (Optional) Function call details + additionalProperties: false + required: + - type + title: OpenAIChatCompletionToolCall + description: >- + Tool call specification for OpenAI-compatible chat completion responses. + OpenAIChatCompletionToolCallFunction: + type: object + properties: + name: + type: string + description: (Optional) Name of the function to call + arguments: + type: string + description: >- + (Optional) Arguments to pass to the function as a JSON string + additionalProperties: false + title: OpenAIChatCompletionToolCallFunction + description: >- + Function call details for OpenAI-compatible tool calls. + OpenAIChatCompletionUsage: + type: object + properties: + prompt_tokens: + type: integer + description: Number of tokens in the prompt + completion_tokens: + type: integer + description: Number of tokens in the completion + total_tokens: + type: integer + description: Total tokens used (prompt + completion) + prompt_tokens_details: + type: object + properties: + cached_tokens: + type: integer + description: Number of tokens retrieved from cache + additionalProperties: false + title: >- + OpenAIChatCompletionUsagePromptTokensDetails + description: >- + Token details for prompt tokens in OpenAI chat completion usage. + completion_tokens_details: + type: object + properties: + reasoning_tokens: + type: integer + description: >- + Number of tokens used for reasoning (o1/o3 models) + additionalProperties: false + title: >- + OpenAIChatCompletionUsageCompletionTokensDetails + description: >- + Token details for output tokens in OpenAI chat completion usage. + additionalProperties: false + required: + - prompt_tokens + - completion_tokens + - total_tokens + title: OpenAIChatCompletionUsage + description: >- + Usage information for OpenAI chat completion. + OpenAIChoice: + type: object + properties: + message: + oneOf: + - $ref: '#/components/schemas/OpenAIUserMessageParam' + - $ref: '#/components/schemas/OpenAISystemMessageParam' + - $ref: '#/components/schemas/OpenAIAssistantMessageParam' + - $ref: '#/components/schemas/OpenAIToolMessageParam' + - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' + discriminator: + propertyName: role + mapping: + user: '#/components/schemas/OpenAIUserMessageParam' + system: '#/components/schemas/OpenAISystemMessageParam' + assistant: '#/components/schemas/OpenAIAssistantMessageParam' + tool: '#/components/schemas/OpenAIToolMessageParam' + developer: '#/components/schemas/OpenAIDeveloperMessageParam' + description: The message from the model + finish_reason: + type: string + description: The reason the model stopped generating + index: + type: integer + description: The index of the choice + logprobs: + $ref: '#/components/schemas/OpenAIChoiceLogprobs' + description: >- + (Optional) The log probabilities for the tokens in the message + additionalProperties: false + required: + - message + - finish_reason + - index + title: OpenAIChoice + description: >- + A choice from an OpenAI-compatible chat completion response. + OpenAIChoiceLogprobs: + type: object + properties: + content: + type: array + items: + $ref: '#/components/schemas/OpenAITokenLogProb' + description: >- + (Optional) The log probabilities for the tokens in the message + refusal: + type: array + items: + $ref: '#/components/schemas/OpenAITokenLogProb' + description: >- + (Optional) The log probabilities for the tokens in the message + additionalProperties: false + title: OpenAIChoiceLogprobs + description: >- + The log probabilities for the tokens in the message from an OpenAI-compatible + chat completion response. + OpenAIDeveloperMessageParam: + type: object + properties: + role: + type: string + const: developer + default: developer + description: >- + Must be "developer" to identify this as a developer message + content: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + description: The content of the developer message + name: + type: string + description: >- + (Optional) The name of the developer message participant. + additionalProperties: false + required: + - role + - content + title: OpenAIDeveloperMessageParam + description: >- + A message from the developer in an OpenAI-compatible chat completion request. + OpenAIFile: + type: object + properties: + type: + type: string + const: file + default: file + file: + $ref: '#/components/schemas/OpenAIFileFile' + additionalProperties: false + required: + - type + - file + title: OpenAIFile + OpenAIFileFile: + type: object + properties: + file_data: + type: string + file_id: + type: string + filename: + type: string + additionalProperties: false + title: OpenAIFileFile + OpenAIImageURL: + type: object + properties: + url: + type: string + description: >- + URL of the image to include in the message + detail: + type: string + description: >- + (Optional) Level of detail for image processing. Can be "low", "high", + or "auto" + additionalProperties: false + required: + - url + title: OpenAIImageURL + description: >- + Image URL specification for OpenAI-compatible chat completion messages. + OpenAIMessageParam: + oneOf: + - $ref: '#/components/schemas/OpenAIUserMessageParam' + - $ref: '#/components/schemas/OpenAISystemMessageParam' + - $ref: '#/components/schemas/OpenAIAssistantMessageParam' + - $ref: '#/components/schemas/OpenAIToolMessageParam' + - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' + discriminator: + propertyName: role + mapping: + user: '#/components/schemas/OpenAIUserMessageParam' + system: '#/components/schemas/OpenAISystemMessageParam' + assistant: '#/components/schemas/OpenAIAssistantMessageParam' + tool: '#/components/schemas/OpenAIToolMessageParam' + developer: '#/components/schemas/OpenAIDeveloperMessageParam' + OpenAISystemMessageParam: + type: object + properties: + role: + type: string + const: system + default: system + description: >- + Must be "system" to identify this as a system message + content: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + description: >- + The content of the "system prompt". If multiple system messages are provided, + they are concatenated. The underlying Llama Stack code may also add other + system messages (for example, for formatting tool definitions). + name: + type: string + description: >- + (Optional) The name of the system message participant. + additionalProperties: false + required: + - role + - content + title: OpenAISystemMessageParam + description: >- + A system message providing instructions or context to the model. + OpenAITokenLogProb: + type: object + properties: + token: + type: string + bytes: + type: array + items: + type: integer + logprob: + type: number + top_logprobs: + type: array + items: + $ref: '#/components/schemas/OpenAITopLogProb' + additionalProperties: false + required: + - token + - logprob + - top_logprobs + title: OpenAITokenLogProb + description: >- + The log probability for a token from an OpenAI-compatible chat completion + response. + OpenAIToolMessageParam: + type: object + properties: + role: + type: string + const: tool + default: tool + description: >- + Must be "tool" to identify this as a tool response + tool_call_id: + type: string + description: >- + Unique identifier for the tool call this response is for + content: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + description: The response content from the tool + additionalProperties: false + required: + - role + - tool_call_id + - content + title: OpenAIToolMessageParam + description: >- + A message representing the result of a tool invocation in an OpenAI-compatible + chat completion request. + OpenAITopLogProb: + type: object + properties: + token: + type: string + bytes: + type: array + items: + type: integer + logprob: + type: number + additionalProperties: false + required: + - token + - logprob + title: OpenAITopLogProb + description: >- + The top log probability for a token from an OpenAI-compatible chat completion + response. + OpenAIUserMessageParam: + type: object + properties: + role: + type: string + const: user + default: user + description: >- + Must be "user" to identify this as a user message + content: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam' + description: >- + The content of the message, which can include text and other media + name: + type: string + description: >- + (Optional) The name of the user message participant. + additionalProperties: false + required: + - role + - content + title: OpenAIUserMessageParam + description: >- + A message from the user in an OpenAI-compatible chat completion request. + OpenAIJSONSchema: + type: object + properties: + name: + type: string + description: Name of the schema + description: + type: string + description: (Optional) Description of the schema + strict: + type: boolean + description: >- + (Optional) Whether to enforce strict adherence to the schema + schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) The JSON schema definition + additionalProperties: false + required: + - name + title: OpenAIJSONSchema + description: >- + JSON schema specification for OpenAI-compatible structured response format. + OpenAIResponseFormatJSONObject: + type: object + properties: + type: + type: string + const: json_object + default: json_object + description: >- + Must be "json_object" to indicate generic JSON object response format + additionalProperties: false + required: + - type + title: OpenAIResponseFormatJSONObject + description: >- + JSON object response format for OpenAI-compatible chat completion requests. + OpenAIResponseFormatJSONSchema: + type: object + properties: + type: + type: string + const: json_schema + default: json_schema + description: >- + Must be "json_schema" to indicate structured JSON response format + json_schema: + $ref: '#/components/schemas/OpenAIJSONSchema' + description: >- + The JSON schema specification for the response + additionalProperties: false + required: + - type + - json_schema + title: OpenAIResponseFormatJSONSchema + description: >- + JSON schema response format for OpenAI-compatible chat completion requests. + OpenAIResponseFormatParam: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseFormatText' + - $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema' + - $ref: '#/components/schemas/OpenAIResponseFormatJSONObject' + discriminator: + propertyName: type + mapping: + text: '#/components/schemas/OpenAIResponseFormatText' + json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema' + json_object: '#/components/schemas/OpenAIResponseFormatJSONObject' + OpenAIResponseFormatText: + type: object + properties: + type: + type: string + const: text + default: text + description: >- + Must be "text" to indicate plain text response format + additionalProperties: false + required: + - type + title: OpenAIResponseFormatText + description: >- + Text response format for OpenAI-compatible chat completion requests. + OpenAIChatCompletionRequestWithExtraBody: + type: object + properties: + model: + type: string + description: >- + The identifier of the model to use. The model must be registered with + Llama Stack and available via the /models endpoint. + messages: + type: array + items: + $ref: '#/components/schemas/OpenAIMessageParam' + description: List of messages in the conversation. + frequency_penalty: + type: number + description: >- + (Optional) The penalty for repeated tokens. + function_call: + oneOf: + - type: string + - type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) The function call to use. + functions: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) List of functions to use. + logit_bias: + type: object + additionalProperties: + type: number + description: (Optional) The logit bias to use. + logprobs: + type: boolean + description: (Optional) The log probabilities to use. + max_completion_tokens: + type: integer + description: >- + (Optional) The maximum number of tokens to generate. + max_tokens: + type: integer + description: >- + (Optional) The maximum number of tokens to generate. + n: + type: integer + description: >- + (Optional) The number of completions to generate. + parallel_tool_calls: + type: boolean + description: >- + (Optional) Whether to parallelize tool calls. + presence_penalty: + type: number + description: >- + (Optional) The penalty for repeated tokens. + response_format: + $ref: '#/components/schemas/OpenAIResponseFormatParam' + description: (Optional) The response format to use. + seed: + type: integer + description: (Optional) The seed to use. + stop: + oneOf: + - type: string + - type: array + items: + type: string + description: (Optional) The stop tokens to use. + stream: + type: boolean + description: >- + (Optional) Whether to stream the response. + stream_options: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) The stream options to use. + temperature: + type: number + description: (Optional) The temperature to use. + tool_choice: + oneOf: + - type: string + - type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) The tool choice to use. + tools: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) The tools to use. + top_logprobs: + type: integer + description: >- + (Optional) The top log probabilities to use. + top_p: + type: number + description: (Optional) The top p to use. + user: + type: string + description: (Optional) The user to use. + additionalProperties: false + required: + - model + - messages + title: OpenAIChatCompletionRequestWithExtraBody + description: >- + Request parameters for OpenAI-compatible chat completion endpoint. + OpenAIChatCompletion: + type: object + properties: + id: + type: string + description: The ID of the chat completion + choices: + type: array + items: + $ref: '#/components/schemas/OpenAIChoice' + description: List of choices + object: + type: string + const: chat.completion + default: chat.completion + description: >- + The object type, which will be "chat.completion" + created: + type: integer + description: >- + The Unix timestamp in seconds when the chat completion was created + model: + type: string + description: >- + The model that was used to generate the chat completion + usage: + $ref: '#/components/schemas/OpenAIChatCompletionUsage' + description: >- + Token usage information for the completion + additionalProperties: false + required: + - id + - choices + - object + - created + - model + title: OpenAIChatCompletion + description: >- + Response from an OpenAI-compatible chat completion request. + OpenAIChatCompletionChunk: + type: object + properties: + id: + type: string + description: The ID of the chat completion + choices: + type: array + items: + $ref: '#/components/schemas/OpenAIChunkChoice' + description: List of choices + object: + type: string + const: chat.completion.chunk + default: chat.completion.chunk + description: >- + The object type, which will be "chat.completion.chunk" + created: + type: integer + description: >- + The Unix timestamp in seconds when the chat completion was created + model: + type: string + description: >- + The model that was used to generate the chat completion + usage: + $ref: '#/components/schemas/OpenAIChatCompletionUsage' + description: >- + Token usage information (typically included in final chunk with stream_options) + additionalProperties: false + required: + - id + - choices + - object + - created + - model + title: OpenAIChatCompletionChunk + description: >- + Chunk from a streaming response to an OpenAI-compatible chat completion request. + OpenAIChoiceDelta: + type: object + properties: + content: + type: string + description: (Optional) The content of the delta + refusal: + type: string + description: (Optional) The refusal of the delta + role: + type: string + description: (Optional) The role of the delta + tool_calls: + type: array + items: + $ref: '#/components/schemas/OpenAIChatCompletionToolCall' + description: (Optional) The tool calls of the delta + reasoning_content: + type: string + description: >- + (Optional) The reasoning content from the model (non-standard, for o1/o3 + models) + additionalProperties: false + title: OpenAIChoiceDelta + description: >- + A delta from an OpenAI-compatible chat completion streaming response. + OpenAIChunkChoice: + type: object + properties: + delta: + $ref: '#/components/schemas/OpenAIChoiceDelta' + description: The delta from the chunk + finish_reason: + type: string + description: The reason the model stopped generating + index: + type: integer + description: The index of the choice + logprobs: + $ref: '#/components/schemas/OpenAIChoiceLogprobs' + description: >- + (Optional) The log probabilities for the tokens in the message + additionalProperties: false + required: + - delta + - finish_reason + - index + title: OpenAIChunkChoice + description: >- + A chunk choice from an OpenAI-compatible chat completion streaming response. + OpenAICompletionWithInputMessages: + type: object + properties: + id: + type: string + description: The ID of the chat completion + choices: + type: array + items: + $ref: '#/components/schemas/OpenAIChoice' + description: List of choices + object: + type: string + const: chat.completion + default: chat.completion + description: >- + The object type, which will be "chat.completion" + created: + type: integer + description: >- + The Unix timestamp in seconds when the chat completion was created + model: + type: string + description: >- + The model that was used to generate the chat completion + usage: + $ref: '#/components/schemas/OpenAIChatCompletionUsage' + description: >- + Token usage information for the completion + input_messages: + type: array + items: + $ref: '#/components/schemas/OpenAIMessageParam' + additionalProperties: false + required: + - id + - choices + - object + - created + - model + - input_messages + title: OpenAICompletionWithInputMessages + OpenAICompletionRequestWithExtraBody: + type: object + properties: + model: + type: string + description: >- + The identifier of the model to use. The model must be registered with + Llama Stack and available via the /models endpoint. + prompt: + oneOf: + - type: string + - type: array + items: + type: string + - type: array + items: + type: integer + - type: array + items: + type: array + items: + type: integer + description: The prompt to generate a completion for. + best_of: + type: integer + description: >- + (Optional) The number of completions to generate. + echo: + type: boolean + description: (Optional) Whether to echo the prompt. + frequency_penalty: + type: number + description: >- + (Optional) The penalty for repeated tokens. + logit_bias: + type: object + additionalProperties: + type: number + description: (Optional) The logit bias to use. + logprobs: + type: boolean + description: (Optional) The log probabilities to use. + max_tokens: + type: integer + description: >- + (Optional) The maximum number of tokens to generate. + n: + type: integer + description: >- + (Optional) The number of completions to generate. + presence_penalty: + type: number + description: >- + (Optional) The penalty for repeated tokens. + seed: + type: integer + description: (Optional) The seed to use. + stop: + oneOf: + - type: string + - type: array + items: + type: string + description: (Optional) The stop tokens to use. + stream: + type: boolean + description: >- + (Optional) Whether to stream the response. + stream_options: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) The stream options to use. + temperature: + type: number + description: (Optional) The temperature to use. + top_p: + type: number + description: (Optional) The top p to use. + user: + type: string + description: (Optional) The user to use. + suffix: + type: string + description: >- + (Optional) The suffix that should be appended to the completion. + additionalProperties: false + required: + - model + - prompt + title: OpenAICompletionRequestWithExtraBody + description: >- + Request parameters for OpenAI-compatible completion endpoint. + OpenAICompletion: + type: object + properties: + id: + type: string + choices: + type: array + items: + $ref: '#/components/schemas/OpenAICompletionChoice' + created: + type: integer + model: + type: string + object: + type: string + const: text_completion + default: text_completion + additionalProperties: false + required: + - id + - choices + - created + - model + - object + title: OpenAICompletion + description: >- + Response from an OpenAI-compatible completion request. + OpenAICompletionChoice: + type: object + properties: + finish_reason: + type: string + text: + type: string + index: + type: integer + logprobs: + $ref: '#/components/schemas/OpenAIChoiceLogprobs' + additionalProperties: false + required: + - finish_reason + - text + - index + title: OpenAICompletionChoice + description: >- + A choice from an OpenAI-compatible completion response. + ConversationItem: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseMessage' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + - $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + discriminator: + propertyName: type + mapping: + message: '#/components/schemas/OpenAIResponseMessage' + web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + function_call_output: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput' + mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + mcp_approval_response: '#/components/schemas/OpenAIResponseMCPApprovalResponse' + mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + OpenAIResponseAnnotationCitation: + type: object + properties: + type: + type: string + const: url_citation + default: url_citation + description: >- + Annotation type identifier, always "url_citation" + end_index: + type: integer + description: >- + End position of the citation span in the content + start_index: + type: integer + description: >- + Start position of the citation span in the content + title: + type: string + description: Title of the referenced web resource + url: + type: string + description: URL of the referenced web resource + additionalProperties: false + required: + - type + - end_index + - start_index + - title + - url + title: OpenAIResponseAnnotationCitation + description: >- + URL citation annotation for referencing external web resources. + "OpenAIResponseAnnotationContainerFileCitation": + type: object + properties: + type: + type: string + const: container_file_citation + default: container_file_citation + container_id: + type: string + end_index: + type: integer + file_id: + type: string + filename: + type: string + start_index: + type: integer + additionalProperties: false + required: + - type + - container_id + - end_index + - file_id + - filename + - start_index + title: >- + OpenAIResponseAnnotationContainerFileCitation + OpenAIResponseAnnotationFileCitation: + type: object + properties: + type: + type: string + const: file_citation + default: file_citation + description: >- + Annotation type identifier, always "file_citation" + file_id: + type: string + description: Unique identifier of the referenced file + filename: + type: string + description: Name of the referenced file + index: + type: integer + description: >- + Position index of the citation within the content + additionalProperties: false + required: + - type + - file_id + - filename + - index + title: OpenAIResponseAnnotationFileCitation + description: >- + File citation annotation for referencing specific files in response content. + OpenAIResponseAnnotationFilePath: + type: object + properties: + type: + type: string + const: file_path + default: file_path + file_id: + type: string + index: + type: integer + additionalProperties: false + required: + - type + - file_id + - index + title: OpenAIResponseAnnotationFilePath + OpenAIResponseAnnotations: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseAnnotationFileCitation' + - $ref: '#/components/schemas/OpenAIResponseAnnotationCitation' + - $ref: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' + - $ref: '#/components/schemas/OpenAIResponseAnnotationFilePath' + discriminator: + propertyName: type + mapping: + file_citation: '#/components/schemas/OpenAIResponseAnnotationFileCitation' + url_citation: '#/components/schemas/OpenAIResponseAnnotationCitation' + container_file_citation: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' + file_path: '#/components/schemas/OpenAIResponseAnnotationFilePath' + OpenAIResponseContentPartRefusal: + type: object + properties: + type: + type: string + const: refusal + default: refusal + description: >- + Content part type identifier, always "refusal" + refusal: + type: string + description: Refusal text supplied by the model + additionalProperties: false + required: + - type + - refusal + title: OpenAIResponseContentPartRefusal + description: >- + Refusal content within a streamed response part. + "OpenAIResponseInputFunctionToolCallOutput": + type: object + properties: + call_id: + type: string + output: + type: string + type: + type: string + const: function_call_output + default: function_call_output + id: + type: string + status: + type: string + additionalProperties: false + required: + - call_id + - output + - type + title: >- + OpenAIResponseInputFunctionToolCallOutput + description: >- + This represents the output of a function call that gets passed back to the + model. + OpenAIResponseInputMessageContent: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseInputMessageContentText' + - $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage' + discriminator: + propertyName: type + mapping: + input_text: '#/components/schemas/OpenAIResponseInputMessageContentText' + input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage' + OpenAIResponseInputMessageContentImage: + type: object + properties: + detail: + oneOf: + - type: string + const: low + - type: string + const: high + - type: string + const: auto + default: auto + description: >- + Level of detail for image processing, can be "low", "high", or "auto" + type: + type: string + const: input_image + default: input_image + description: >- + Content type identifier, always "input_image" + image_url: + type: string + description: (Optional) URL of the image content + additionalProperties: false + required: + - detail + - type + title: OpenAIResponseInputMessageContentImage + description: >- + Image content for input messages in OpenAI response format. + OpenAIResponseInputMessageContentText: + type: object + properties: + text: + type: string + description: The text content of the input message + type: + type: string + const: input_text + default: input_text + description: >- + Content type identifier, always "input_text" + additionalProperties: false + required: + - text + - type + title: OpenAIResponseInputMessageContentText + description: >- + Text content for input messages in OpenAI response format. + OpenAIResponseMCPApprovalRequest: + type: object + properties: + arguments: + type: string + id: + type: string + name: + type: string + server_label: + type: string + type: + type: string + const: mcp_approval_request + default: mcp_approval_request + additionalProperties: false + required: + - arguments + - id + - name + - server_label + - type + title: OpenAIResponseMCPApprovalRequest + description: >- + A request for human approval of a tool invocation. + OpenAIResponseMCPApprovalResponse: + type: object + properties: + approval_request_id: + type: string + approve: + type: boolean + type: + type: string + const: mcp_approval_response + default: mcp_approval_response + id: + type: string + reason: + type: string + additionalProperties: false + required: + - approval_request_id + - approve + - type + title: OpenAIResponseMCPApprovalResponse + description: A response to an MCP approval request. + OpenAIResponseMessage: + type: object + properties: + content: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIResponseInputMessageContent' + - type: array + items: + $ref: '#/components/schemas/OpenAIResponseOutputMessageContent' + role: + oneOf: + - type: string + const: system + - type: string + const: developer + - type: string + const: user + - type: string + const: assistant + type: + type: string + const: message + default: message + id: + type: string + status: + type: string + additionalProperties: false + required: + - content + - role + - type + title: OpenAIResponseMessage + description: >- + Corresponds to the various Message types in the Responses API. They are all + under one type because the Responses API gives them all the same "type" value, + and there is no way to tell them apart in certain scenarios. + OpenAIResponseOutputMessageContent: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText' + - $ref: '#/components/schemas/OpenAIResponseContentPartRefusal' + discriminator: + propertyName: type + mapping: + output_text: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText' + refusal: '#/components/schemas/OpenAIResponseContentPartRefusal' + "OpenAIResponseOutputMessageContentOutputText": + type: object + properties: + text: + type: string + type: + type: string + const: output_text + default: output_text + annotations: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseAnnotations' + additionalProperties: false + required: + - text + - type + - annotations + title: >- + OpenAIResponseOutputMessageContentOutputText + "OpenAIResponseOutputMessageFileSearchToolCall": + type: object + properties: + id: + type: string + description: Unique identifier for this tool call + queries: + type: array + items: + type: string + description: List of search queries executed + status: + type: string + description: >- + Current status of the file search operation + type: + type: string + const: file_search_call + default: file_search_call + description: >- + Tool call type identifier, always "file_search_call" + results: + type: array + items: + type: object + properties: + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Key-value attributes associated with the file + file_id: + type: string + description: >- + Unique identifier of the file containing the result + filename: + type: string + description: Name of the file containing the result + score: + type: number + description: >- + Relevance score for this search result (between 0 and 1) + text: + type: string + description: Text content of the search result + additionalProperties: false + required: + - attributes + - file_id + - filename + - score + - text + title: >- + OpenAIResponseOutputMessageFileSearchToolCallResults + description: >- + Search results returned by the file search operation. + description: >- + (Optional) Search results returned by the file search operation + additionalProperties: false + required: + - id + - queries + - status + - type + title: >- + OpenAIResponseOutputMessageFileSearchToolCall + description: >- + File search tool call output message for OpenAI responses. + "OpenAIResponseOutputMessageFunctionToolCall": + type: object + properties: + call_id: + type: string + description: Unique identifier for the function call + name: + type: string + description: Name of the function being called + arguments: + type: string + description: >- + JSON string containing the function arguments + type: + type: string + const: function_call + default: function_call + description: >- + Tool call type identifier, always "function_call" + id: + type: string + description: >- + (Optional) Additional identifier for the tool call + status: + type: string + description: >- + (Optional) Current status of the function call execution + additionalProperties: false + required: + - call_id + - name + - arguments + - type + title: >- + OpenAIResponseOutputMessageFunctionToolCall + description: >- + Function tool call output message for OpenAI responses. + OpenAIResponseOutputMessageMCPCall: + type: object + properties: + id: + type: string + description: Unique identifier for this MCP call + type: + type: string + const: mcp_call + default: mcp_call + description: >- + Tool call type identifier, always "mcp_call" + arguments: + type: string + description: >- + JSON string containing the MCP call arguments + name: + type: string + description: Name of the MCP method being called + server_label: + type: string + description: >- + Label identifying the MCP server handling the call + error: + type: string + description: >- + (Optional) Error message if the MCP call failed + output: + type: string + description: >- + (Optional) Output result from the successful MCP call + additionalProperties: false + required: + - id + - type + - arguments + - name + - server_label + title: OpenAIResponseOutputMessageMCPCall + description: >- + Model Context Protocol (MCP) call output message for OpenAI responses. + OpenAIResponseOutputMessageMCPListTools: + type: object + properties: + id: + type: string + description: >- + Unique identifier for this MCP list tools operation + type: + type: string + const: mcp_list_tools + default: mcp_list_tools + description: >- + Tool call type identifier, always "mcp_list_tools" + server_label: + type: string + description: >- + Label identifying the MCP server providing the tools + tools: + type: array + items: + type: object + properties: + input_schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + JSON schema defining the tool's input parameters + name: + type: string + description: Name of the tool + description: + type: string + description: >- + (Optional) Description of what the tool does + additionalProperties: false + required: + - input_schema + - name + title: MCPListToolsTool + description: >- + Tool definition returned by MCP list tools operation. + description: >- + List of available tools provided by the MCP server + additionalProperties: false + required: + - id + - type + - server_label + - tools + title: OpenAIResponseOutputMessageMCPListTools + description: >- + MCP list tools output message containing available tools from an MCP server. + "OpenAIResponseOutputMessageWebSearchToolCall": + type: object + properties: + id: + type: string + description: Unique identifier for this tool call + status: + type: string + description: >- + Current status of the web search operation + type: + type: string + const: web_search_call + default: web_search_call + description: >- + Tool call type identifier, always "web_search_call" + additionalProperties: false + required: + - id + - status + - type + title: >- + OpenAIResponseOutputMessageWebSearchToolCall + description: >- + Web search tool call output message for OpenAI responses. + CreateConversationRequest: + type: object + properties: + items: + type: array + items: + $ref: '#/components/schemas/ConversationItem' + description: >- + Initial items to include in the conversation context. + metadata: + type: object + additionalProperties: + type: string + description: >- + Set of key-value pairs that can be attached to an object. + additionalProperties: false + title: CreateConversationRequest + Conversation: + type: object + properties: + id: + type: string + object: + type: string + const: conversation + default: conversation + created_at: + type: integer + metadata: + type: object + additionalProperties: + type: string + items: + type: array + items: + type: object + title: dict + description: >- + dict() -> new empty dictionary dict(mapping) -> new dictionary initialized + from a mapping object's (key, value) pairs dict(iterable) -> new + dictionary initialized as if via: d = {} for k, v in iterable: d[k] + = v dict(**kwargs) -> new dictionary initialized with the name=value + pairs in the keyword argument list. For example: dict(one=1, two=2) + additionalProperties: false + required: + - id + - object + - created_at + title: Conversation + description: OpenAI-compatible conversation object. + UpdateConversationRequest: + type: object + properties: + metadata: + type: object + additionalProperties: + type: string + description: >- + Set of key-value pairs that can be attached to an object. + additionalProperties: false + required: + - metadata + title: UpdateConversationRequest + ConversationDeletedResource: + type: object + properties: + id: + type: string + object: + type: string + default: conversation.deleted + deleted: + type: boolean + default: true + additionalProperties: false + required: + - id + - object + - deleted + title: ConversationDeletedResource + description: Response for deleted conversation. + ConversationItemList: + type: object + properties: + object: + type: string + default: list + data: + type: array + items: + $ref: '#/components/schemas/ConversationItem' + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + default: false + additionalProperties: false + required: + - object + - data + - has_more + title: ConversationItemList + description: >- + List of conversation items with pagination. + AddItemsRequest: + type: object + properties: + items: + type: array + items: + $ref: '#/components/schemas/ConversationItem' + description: >- + Items to include in the conversation context. + additionalProperties: false + required: + - items + title: AddItemsRequest + ConversationItemDeletedResource: + type: object + properties: + id: + type: string + object: + type: string + default: conversation.item.deleted + deleted: + type: boolean + default: true + additionalProperties: false + required: + - id + - object + - deleted + title: ConversationItemDeletedResource + description: Response for deleted conversation item. + OpenAIEmbeddingsRequestWithExtraBody: + type: object + properties: + model: + type: string + description: >- + The identifier of the model to use. The model must be an embedding model + registered with Llama Stack and available via the /models endpoint. + input: + oneOf: + - type: string + - type: array + items: + type: string + description: >- + Input text to embed, encoded as a string or array of strings. To embed + multiple inputs in a single request, pass an array of strings. + encoding_format: + type: string + default: float + description: >- + (Optional) The format to return the embeddings in. Can be either "float" + or "base64". Defaults to "float". + dimensions: + type: integer + description: >- + (Optional) The number of dimensions the resulting output embeddings should + have. Only supported in text-embedding-3 and later models. + user: + type: string + description: >- + (Optional) A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. + additionalProperties: false + required: + - model + - input + title: OpenAIEmbeddingsRequestWithExtraBody + description: >- + Request parameters for OpenAI-compatible embeddings endpoint. + OpenAIEmbeddingData: + type: object + properties: + object: + type: string + const: embedding + default: embedding + description: >- + The object type, which will be "embedding" + embedding: + oneOf: + - type: array + items: + type: number + - type: string + description: >- + The embedding vector as a list of floats (when encoding_format="float") + or as a base64-encoded string (when encoding_format="base64") + index: + type: integer + description: >- + The index of the embedding in the input list + additionalProperties: false + required: + - object + - embedding + - index + title: OpenAIEmbeddingData + description: >- + A single embedding data object from an OpenAI-compatible embeddings response. + OpenAIEmbeddingUsage: + type: object + properties: + prompt_tokens: + type: integer + description: The number of tokens in the input + total_tokens: + type: integer + description: The total number of tokens used + additionalProperties: false + required: + - prompt_tokens + - total_tokens + title: OpenAIEmbeddingUsage + description: >- + Usage information for an OpenAI-compatible embeddings response. + OpenAIEmbeddingsResponse: + type: object + properties: + object: + type: string + const: list + default: list + description: The object type, which will be "list" + data: + type: array + items: + $ref: '#/components/schemas/OpenAIEmbeddingData' + description: List of embedding data objects + model: + type: string + description: >- + The model that was used to generate the embeddings + usage: + $ref: '#/components/schemas/OpenAIEmbeddingUsage' + description: Usage information + additionalProperties: false + required: + - object + - data + - model + - usage + title: OpenAIEmbeddingsResponse + description: >- + Response from an OpenAI-compatible embeddings request. + OpenAIFilePurpose: + type: string + enum: + - assistants + - batch + title: OpenAIFilePurpose + description: >- + Valid purpose values for OpenAI Files API. + ListOpenAIFileResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/OpenAIFileObject' + description: List of file objects + has_more: + type: boolean + description: >- + Whether there are more files available beyond this page + first_id: + type: string + description: >- + ID of the first file in the list for pagination + last_id: + type: string + description: >- + ID of the last file in the list for pagination + object: + type: string + const: list + default: list + description: The object type, which is always "list" + additionalProperties: false + required: + - data + - has_more + - first_id + - last_id + - object + title: ListOpenAIFileResponse + description: >- + Response for listing files in OpenAI Files API. + OpenAIFileObject: + type: object + properties: + object: + type: string + const: file + default: file + description: The object type, which is always "file" + id: + type: string + description: >- + The file identifier, which can be referenced in the API endpoints + bytes: + type: integer + description: The size of the file, in bytes + created_at: + type: integer + description: >- + The Unix timestamp (in seconds) for when the file was created + expires_at: + type: integer + description: >- + The Unix timestamp (in seconds) for when the file expires + filename: + type: string + description: The name of the file + purpose: + type: string + enum: + - assistants + - batch + description: The intended purpose of the file + additionalProperties: false + required: + - object + - id + - bytes + - created_at + - expires_at + - filename + - purpose + title: OpenAIFileObject + description: >- + OpenAI File object as defined in the OpenAI Files API. + ExpiresAfter: + type: object + properties: + anchor: + type: string + const: created_at + seconds: + type: integer + additionalProperties: false + required: + - anchor + - seconds + title: ExpiresAfter + description: >- + Control expiration of uploaded files. + + Params: + - anchor, must be "created_at" + - seconds, must be int between 3600 and 2592000 (1 hour to 30 days) + OpenAIFileDeleteResponse: + type: object + properties: + id: + type: string + description: The file identifier that was deleted + object: + type: string + const: file + default: file + description: The object type, which is always "file" + deleted: + type: boolean + description: >- + Whether the file was successfully deleted + additionalProperties: false + required: + - id + - object + - deleted + title: OpenAIFileDeleteResponse + description: >- + Response for deleting a file in OpenAI Files API. + Response: + type: object + title: Response + HealthInfo: + type: object + properties: + status: + type: string + enum: + - OK + - Error + - Not Implemented + description: Current health status of the service + additionalProperties: false + required: + - status + title: HealthInfo + description: >- + Health status information for the service. + RouteInfo: + type: object + properties: + route: + type: string + description: The API endpoint path + method: + type: string + description: HTTP method for the route + provider_types: + type: array + items: + type: string + description: >- + List of provider types that implement this route + additionalProperties: false + required: + - route + - method + - provider_types + title: RouteInfo + description: >- + Information about an API route including its path, method, and implementing + providers. + ListRoutesResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/RouteInfo' + description: >- + List of available route information objects + additionalProperties: false + required: + - data + title: ListRoutesResponse + description: >- + Response containing a list of all available API routes. + Model: + type: object + properties: + identifier: + type: string + description: >- + Unique identifier for this resource in llama stack + provider_resource_id: + type: string + description: >- + Unique identifier for this resource in the provider + provider_id: + type: string + description: >- + ID of the provider that owns this resource + type: + type: string + enum: + - model + - shield + - vector_db + - dataset + - scoring_function + - benchmark + - tool + - tool_group + - prompt + const: model + default: model + description: >- + The resource type, always 'model' for model resources + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Any additional metadata for this model + model_type: + $ref: '#/components/schemas/ModelType' + default: llm + description: >- + The type of model (LLM or embedding model) + additionalProperties: false + required: + - identifier + - provider_id + - type + - metadata + - model_type + title: Model + description: >- + A model resource representing an AI model registered in Llama Stack. + ModelType: + type: string + enum: + - llm + - embedding + title: ModelType + description: >- + Enumeration of supported model types in Llama Stack. + ListModelsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Model' + additionalProperties: false + required: + - data + title: ListModelsResponse + RegisterModelRequest: + type: object + properties: + model_id: + type: string + description: The identifier of the model to register. + provider_model_id: + type: string + description: >- + The identifier of the model in the provider. + provider_id: + type: string + description: The identifier of the provider. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Any additional metadata for this model. + model_type: + $ref: '#/components/schemas/ModelType' + description: The type of model to register. + additionalProperties: false + required: + - model_id + title: RegisterModelRequest + RunModerationRequest: + type: object + properties: + input: + oneOf: + - type: string + - type: array + items: + type: string + description: >- + Input (or inputs) to classify. Can be a single string, an array of strings, + or an array of multi-modal input objects similar to other models. + model: + type: string + description: >- + The content moderation model you would like to use. + additionalProperties: false + required: + - input + - model + title: RunModerationRequest + ModerationObject: + type: object + properties: + id: + type: string + description: >- + The unique identifier for the moderation request. + model: + type: string + description: >- + The model used to generate the moderation results. + results: + type: array + items: + $ref: '#/components/schemas/ModerationObjectResults' + description: A list of moderation objects + additionalProperties: false + required: + - id + - model + - results + title: ModerationObject + description: A moderation object. + ModerationObjectResults: + type: object + properties: + flagged: + type: boolean + description: >- + Whether any of the below categories are flagged. + categories: + type: object + additionalProperties: + type: boolean + description: >- + A list of the categories, and whether they are flagged or not. + category_applied_input_types: + type: object + additionalProperties: + type: array + items: + type: string + description: >- + A list of the categories along with the input type(s) that the score applies + to. + category_scores: + type: object + additionalProperties: + type: number + description: >- + A list of the categories along with their scores as predicted by model. + user_message: + type: string + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - flagged + - metadata + title: ModerationObjectResults + description: A moderation object. + Prompt: + type: object + properties: + prompt: + type: string + description: >- + The system prompt text with variable placeholders. Variables are only + supported when using the Responses API. + version: + type: integer + description: >- + Version (integer starting at 1, incremented on save) + prompt_id: + type: string + description: >- + Unique identifier formatted as 'pmpt_<48-digit-hash>' + variables: + type: array + items: + type: string + description: >- + List of prompt variable names that can be used in the prompt template + is_default: + type: boolean + default: false + description: >- + Boolean indicating whether this version is the default version for this + prompt + additionalProperties: false + required: + - version + - prompt_id + - variables + - is_default + title: Prompt + description: >- + A prompt resource representing a stored OpenAI Compatible prompt template + in Llama Stack. + ListPromptsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Prompt' + additionalProperties: false + required: + - data + title: ListPromptsResponse + description: Response model to list prompts. + CreatePromptRequest: + type: object + properties: + prompt: + type: string + description: >- + The prompt text content with variable placeholders. + variables: + type: array + items: + type: string + description: >- + List of variable names that can be used in the prompt template. + additionalProperties: false + required: + - prompt + title: CreatePromptRequest + UpdatePromptRequest: + type: object + properties: + prompt: + type: string + description: The updated prompt text content. + version: + type: integer + description: >- + The current version of the prompt being updated. + variables: + type: array + items: + type: string + description: >- + Updated list of variable names that can be used in the prompt template. + set_as_default: + type: boolean + description: >- + Set the new version as the default (default=True). + additionalProperties: false + required: + - prompt + - version + - set_as_default + title: UpdatePromptRequest + SetDefaultVersionRequest: + type: object + properties: + version: + type: integer + description: The version to set as default. + additionalProperties: false + required: + - version + title: SetDefaultVersionRequest + ProviderInfo: + type: object + properties: + api: + type: string + description: The API name this provider implements + provider_id: + type: string + description: Unique identifier for the provider + provider_type: + type: string + description: The type of provider implementation + config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Configuration parameters for the provider + health: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Current health status of the provider + additionalProperties: false + required: + - api + - provider_id + - provider_type + - config + - health + title: ProviderInfo + description: >- + Information about a registered provider including its configuration and health + status. + ListProvidersResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ProviderInfo' + description: List of provider information objects + additionalProperties: false + required: + - data + title: ListProvidersResponse + description: >- + Response containing a list of all available providers. + ListOpenAIResponseObject: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseObjectWithInput' + description: >- + List of response objects with their input context + has_more: + type: boolean + description: >- + Whether there are more results available beyond this page + first_id: + type: string + description: >- + Identifier of the first item in this page + last_id: + type: string + description: Identifier of the last item in this page + object: + type: string + const: list + default: list + description: Object type identifier, always "list" + additionalProperties: false + required: + - data + - has_more + - first_id + - last_id + - object + title: ListOpenAIResponseObject + description: >- + Paginated list of OpenAI response objects with navigation metadata. + OpenAIResponseError: + type: object + properties: + code: + type: string + description: >- + Error code identifying the type of failure + message: + type: string + description: >- + Human-readable error message describing the failure + additionalProperties: false + required: + - code + - message + title: OpenAIResponseError + description: >- + Error details for failed OpenAI response requests. + OpenAIResponseInput: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + - $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + - $ref: '#/components/schemas/OpenAIResponseMessage' + OpenAIResponseInputToolFileSearch: + type: object + properties: + type: + type: string + const: file_search + default: file_search + description: >- + Tool type identifier, always "file_search" + vector_store_ids: + type: array + items: + type: string + description: >- + List of vector store identifiers to search within + filters: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Additional filters to apply to the search + max_num_results: + type: integer + default: 10 + description: >- + (Optional) Maximum number of search results to return (1-50) + ranking_options: + type: object + properties: + ranker: + type: string + description: >- + (Optional) Name of the ranking algorithm to use + score_threshold: + type: number + default: 0.0 + description: >- + (Optional) Minimum relevance score threshold for results + additionalProperties: false + description: >- + (Optional) Options for ranking and scoring search results + additionalProperties: false + required: + - type + - vector_store_ids + title: OpenAIResponseInputToolFileSearch + description: >- + File search tool configuration for OpenAI response inputs. + OpenAIResponseInputToolFunction: + type: object + properties: + type: + type: string + const: function + default: function + description: Tool type identifier, always "function" + name: + type: string + description: Name of the function that can be called + description: + type: string + description: >- + (Optional) Description of what the function does + parameters: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) JSON schema defining the function's parameters + strict: + type: boolean + description: >- + (Optional) Whether to enforce strict parameter validation + additionalProperties: false + required: + - type + - name + title: OpenAIResponseInputToolFunction + description: >- + Function tool configuration for OpenAI response inputs. + OpenAIResponseInputToolWebSearch: + type: object + properties: + type: + oneOf: + - type: string + const: web_search + - type: string + const: web_search_preview + - type: string + const: web_search_preview_2025_03_11 + default: web_search + description: Web search tool type variant to use + search_context_size: + type: string + default: medium + description: >- + (Optional) Size of search context, must be "low", "medium", or "high" + additionalProperties: false + required: + - type + title: OpenAIResponseInputToolWebSearch + description: >- + Web search tool configuration for OpenAI response inputs. + OpenAIResponseObjectWithInput: + type: object + properties: + created_at: + type: integer + description: >- + Unix timestamp when the response was created + error: + $ref: '#/components/schemas/OpenAIResponseError' + description: >- + (Optional) Error details if the response generation failed + id: + type: string + description: Unique identifier for this response + model: + type: string + description: Model identifier used for generation + object: + type: string + const: response + default: response + description: >- + Object type identifier, always "response" + output: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseOutput' + description: >- + List of generated output items (messages, tool calls, etc.) + parallel_tool_calls: + type: boolean + default: false + description: >- + Whether tool calls can be executed in parallel + previous_response_id: + type: string + description: >- + (Optional) ID of the previous response in a conversation + status: + type: string + description: >- + Current status of the response generation + temperature: + type: number + description: >- + (Optional) Sampling temperature used for generation + text: + $ref: '#/components/schemas/OpenAIResponseText' + description: >- + Text formatting configuration for the response + top_p: + type: number + description: >- + (Optional) Nucleus sampling parameter used for generation + tools: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseTool' + description: >- + (Optional) An array of tools the model may call while generating a response. + truncation: + type: string + description: >- + (Optional) Truncation strategy applied to the response + usage: + $ref: '#/components/schemas/OpenAIResponseUsage' + description: >- + (Optional) Token usage information for the response + instructions: + type: string + description: >- + (Optional) System message inserted into the model's context + input: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseInput' + description: >- + List of input items that led to this response + additionalProperties: false + required: + - created_at + - id + - model + - object + - output + - parallel_tool_calls + - status + - text + - input + title: OpenAIResponseObjectWithInput + description: >- + OpenAI response object extended with input context information. + OpenAIResponseOutput: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseMessage' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + discriminator: + propertyName: type + mapping: + message: '#/components/schemas/OpenAIResponseMessage' + web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + OpenAIResponseText: + type: object + properties: + format: + type: object + properties: + type: + oneOf: + - type: string + const: text + - type: string + const: json_schema + - type: string + const: json_object + description: >- + Must be "text", "json_schema", or "json_object" to identify the format + type + name: + type: string + description: >- + The name of the response format. Only used for json_schema. + schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The JSON schema the response should conform to. In a Python SDK, this + is often a `pydantic` model. Only used for json_schema. + description: + type: string + description: >- + (Optional) A description of the response format. Only used for json_schema. + strict: + type: boolean + description: >- + (Optional) Whether to strictly enforce the JSON schema. If true, the + response must match the schema exactly. Only used for json_schema. + additionalProperties: false + required: + - type + description: >- + (Optional) Text format configuration specifying output format requirements + additionalProperties: false + title: OpenAIResponseText + description: >- + Text response configuration for OpenAI responses. + OpenAIResponseTool: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch' + - $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch' + - $ref: '#/components/schemas/OpenAIResponseInputToolFunction' + - $ref: '#/components/schemas/OpenAIResponseToolMCP' + discriminator: + propertyName: type + mapping: + web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch' + file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch' + function: '#/components/schemas/OpenAIResponseInputToolFunction' + mcp: '#/components/schemas/OpenAIResponseToolMCP' + OpenAIResponseToolMCP: + type: object + properties: + type: + type: string + const: mcp + default: mcp + description: Tool type identifier, always "mcp" + server_label: + type: string + description: Label to identify this MCP server + allowed_tools: + oneOf: + - type: array + items: + type: string + - type: object + properties: + tool_names: + type: array + items: + type: string + description: >- + (Optional) List of specific tool names that are allowed + additionalProperties: false + title: AllowedToolsFilter + description: >- + Filter configuration for restricting which MCP tools can be used. + description: >- + (Optional) Restriction on which tools can be used from this server + additionalProperties: false + required: + - type + - server_label + title: OpenAIResponseToolMCP + description: >- + Model Context Protocol (MCP) tool configuration for OpenAI response object. + OpenAIResponseUsage: + type: object + properties: + input_tokens: + type: integer + description: Number of tokens in the input + output_tokens: + type: integer + description: Number of tokens in the output + total_tokens: + type: integer + description: Total tokens used (input + output) + input_tokens_details: + type: object + properties: + cached_tokens: + type: integer + description: Number of tokens retrieved from cache + additionalProperties: false + description: Detailed breakdown of input token usage + output_tokens_details: + type: object + properties: + reasoning_tokens: + type: integer + description: >- + Number of tokens used for reasoning (o1/o3 models) + additionalProperties: false + description: Detailed breakdown of output token usage + additionalProperties: false + required: + - input_tokens + - output_tokens + - total_tokens + title: OpenAIResponseUsage + description: Usage information for OpenAI response. + ResponseGuardrailSpec: + type: object + properties: + type: + type: string + description: The type/identifier of the guardrail. + additionalProperties: false + required: + - type + title: ResponseGuardrailSpec + description: >- + Specification for a guardrail to apply during response generation. + OpenAIResponseInputTool: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch' + - $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch' + - $ref: '#/components/schemas/OpenAIResponseInputToolFunction' + - $ref: '#/components/schemas/OpenAIResponseInputToolMCP' + discriminator: + propertyName: type + mapping: + web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch' + file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch' + function: '#/components/schemas/OpenAIResponseInputToolFunction' + mcp: '#/components/schemas/OpenAIResponseInputToolMCP' + OpenAIResponseInputToolMCP: + type: object + properties: + type: + type: string + const: mcp + default: mcp + description: Tool type identifier, always "mcp" + server_label: + type: string + description: Label to identify this MCP server + server_url: + type: string + description: URL endpoint of the MCP server + headers: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) HTTP headers to include when connecting to the server + require_approval: + oneOf: + - type: string + const: always + - type: string + const: never + - type: object + properties: + always: + type: array + items: + type: string + description: >- + (Optional) List of tool names that always require approval + never: + type: array + items: + type: string + description: >- + (Optional) List of tool names that never require approval + additionalProperties: false + title: ApprovalFilter + description: >- + Filter configuration for MCP tool approval requirements. + default: never + description: >- + Approval requirement for tool calls ("always", "never", or filter) + allowed_tools: + oneOf: + - type: array + items: + type: string + - type: object + properties: + tool_names: + type: array + items: + type: string + description: >- + (Optional) List of specific tool names that are allowed + additionalProperties: false + title: AllowedToolsFilter + description: >- + Filter configuration for restricting which MCP tools can be used. + description: >- + (Optional) Restriction on which tools can be used from this server + additionalProperties: false + required: + - type + - server_label + - server_url + - require_approval + title: OpenAIResponseInputToolMCP + description: >- + Model Context Protocol (MCP) tool configuration for OpenAI response inputs. + CreateOpenaiResponseRequest: + type: object + properties: + input: + oneOf: + - type: string + - type: array + items: + $ref: '#/components/schemas/OpenAIResponseInput' + description: Input message(s) to create the response. + model: + type: string + description: The underlying LLM used for completions. + instructions: + type: string + previous_response_id: + type: string + description: >- + (Optional) if specified, the new response will be a continuation of the + previous response. This can be used to easily fork-off new responses from + existing responses. + conversation: + type: string + description: >- + (Optional) The ID of a conversation to add the response to. Must begin + with 'conv_'. Input and output messages will be automatically added to + the conversation. + store: + type: boolean + stream: + type: boolean + temperature: + type: number + text: + $ref: '#/components/schemas/OpenAIResponseText' + tools: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseInputTool' + include: + type: array + items: + type: string + description: >- + (Optional) Additional fields to include in the response. + max_infer_iters: + type: integer + additionalProperties: false + required: + - input + - model + title: CreateOpenaiResponseRequest + OpenAIResponseObject: + type: object + properties: + created_at: + type: integer + description: >- + Unix timestamp when the response was created + error: + $ref: '#/components/schemas/OpenAIResponseError' + description: >- + (Optional) Error details if the response generation failed + id: + type: string + description: Unique identifier for this response + model: + type: string + description: Model identifier used for generation + object: + type: string + const: response + default: response + description: >- + Object type identifier, always "response" + output: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseOutput' + description: >- + List of generated output items (messages, tool calls, etc.) + parallel_tool_calls: + type: boolean + default: false + description: >- + Whether tool calls can be executed in parallel + previous_response_id: + type: string + description: >- + (Optional) ID of the previous response in a conversation + status: + type: string + description: >- + Current status of the response generation + temperature: + type: number + description: >- + (Optional) Sampling temperature used for generation + text: + $ref: '#/components/schemas/OpenAIResponseText' + description: >- + Text formatting configuration for the response + top_p: + type: number + description: >- + (Optional) Nucleus sampling parameter used for generation + tools: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseTool' + description: >- + (Optional) An array of tools the model may call while generating a response. + truncation: + type: string + description: >- + (Optional) Truncation strategy applied to the response + usage: + $ref: '#/components/schemas/OpenAIResponseUsage' + description: >- + (Optional) Token usage information for the response + instructions: + type: string + description: >- + (Optional) System message inserted into the model's context + additionalProperties: false + required: + - created_at + - id + - model + - object + - output + - parallel_tool_calls + - status + - text + title: OpenAIResponseObject + description: >- + Complete OpenAI response object containing generation results and metadata. + OpenAIResponseContentPartOutputText: + type: object + properties: + type: + type: string + const: output_text + default: output_text + description: >- + Content part type identifier, always "output_text" + text: + type: string + description: Text emitted for this content part + annotations: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseAnnotations' + description: >- + Structured annotations associated with the text + logprobs: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: (Optional) Token log probability details + additionalProperties: false + required: + - type + - text + - annotations + title: OpenAIResponseContentPartOutputText + description: >- + Text content within a streamed response part. + "OpenAIResponseContentPartReasoningSummary": + type: object + properties: + type: + type: string + const: summary_text + default: summary_text + description: >- + Content part type identifier, always "summary_text" + text: + type: string + description: Summary text + additionalProperties: false + required: + - type + - text + title: >- + OpenAIResponseContentPartReasoningSummary + description: >- + Reasoning summary part in a streamed response. + OpenAIResponseContentPartReasoningText: + type: object + properties: + type: + type: string + const: reasoning_text + default: reasoning_text + description: >- + Content part type identifier, always "reasoning_text" + text: + type: string + description: Reasoning text supplied by the model + additionalProperties: false + required: + - type + - text + title: OpenAIResponseContentPartReasoningText + description: >- + Reasoning text emitted as part of a streamed response. + OpenAIResponseObjectStream: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseInProgress' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemAdded' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDelta' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallInProgress' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallSearching' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallCompleted' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsInProgress' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsFailed' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsCompleted' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningTextDelta' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningTextDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryPartAdded' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryPartDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryTextDelta' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryTextDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseRefusalDelta' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseRefusalDone' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextAnnotationAdded' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFileSearchCallInProgress' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFileSearchCallSearching' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFileSearchCallCompleted' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseIncomplete' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFailed' + - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted' + discriminator: + propertyName: type + mapping: + response.created: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated' + response.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseInProgress' + response.output_item.added: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemAdded' + response.output_item.done: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemDone' + response.output_text.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDelta' + response.output_text.done: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDone' + response.function_call_arguments.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta' + response.function_call_arguments.done: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone' + response.web_search_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallInProgress' + response.web_search_call.searching: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallSearching' + response.web_search_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallCompleted' + response.mcp_list_tools.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsInProgress' + response.mcp_list_tools.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsFailed' + response.mcp_list_tools.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsCompleted' + response.mcp_call.arguments.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta' + response.mcp_call.arguments.done: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDone' + response.mcp_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress' + response.mcp_call.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed' + response.mcp_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted' + response.content_part.added: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded' + response.content_part.done: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone' + response.reasoning_text.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningTextDelta' + response.reasoning_text.done: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningTextDone' + response.reasoning_summary_part.added: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryPartAdded' + response.reasoning_summary_part.done: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryPartDone' + response.reasoning_summary_text.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryTextDelta' + response.reasoning_summary_text.done: '#/components/schemas/OpenAIResponseObjectStreamResponseReasoningSummaryTextDone' + response.refusal.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseRefusalDelta' + response.refusal.done: '#/components/schemas/OpenAIResponseObjectStreamResponseRefusalDone' + response.output_text.annotation.added: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextAnnotationAdded' + response.file_search_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseFileSearchCallInProgress' + response.file_search_call.searching: '#/components/schemas/OpenAIResponseObjectStreamResponseFileSearchCallSearching' + response.file_search_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseFileSearchCallCompleted' + response.incomplete: '#/components/schemas/OpenAIResponseObjectStreamResponseIncomplete' + response.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseFailed' + response.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted' + "OpenAIResponseObjectStreamResponseCompleted": + type: object + properties: + response: + $ref: '#/components/schemas/OpenAIResponseObject' + description: Completed response object + type: + type: string + const: response.completed + default: response.completed + description: >- + Event type identifier, always "response.completed" + additionalProperties: false + required: + - response + - type + title: >- + OpenAIResponseObjectStreamResponseCompleted + description: >- + Streaming event indicating a response has been completed. + "OpenAIResponseObjectStreamResponseContentPartAdded": + type: object + properties: + content_index: + type: integer + description: >- + Index position of the part within the content array + response_id: + type: string + description: >- + Unique identifier of the response containing this content + item_id: + type: string + description: >- + Unique identifier of the output item containing this content part + output_index: + type: integer + description: >- + Index position of the output item in the response + part: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseContentPartOutputText' + - $ref: '#/components/schemas/OpenAIResponseContentPartRefusal' + - $ref: '#/components/schemas/OpenAIResponseContentPartReasoningText' + discriminator: + propertyName: type + mapping: + output_text: '#/components/schemas/OpenAIResponseContentPartOutputText' + refusal: '#/components/schemas/OpenAIResponseContentPartRefusal' + reasoning_text: '#/components/schemas/OpenAIResponseContentPartReasoningText' + description: The content part that was added + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.content_part.added + default: response.content_part.added + description: >- + Event type identifier, always "response.content_part.added" + additionalProperties: false + required: + - content_index + - response_id + - item_id + - output_index + - part + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseContentPartAdded + description: >- + Streaming event for when a new content part is added to a response item. + "OpenAIResponseObjectStreamResponseContentPartDone": + type: object + properties: + content_index: + type: integer + description: >- + Index position of the part within the content array + response_id: + type: string + description: >- + Unique identifier of the response containing this content + item_id: + type: string + description: >- + Unique identifier of the output item containing this content part + output_index: + type: integer + description: >- + Index position of the output item in the response + part: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseContentPartOutputText' + - $ref: '#/components/schemas/OpenAIResponseContentPartRefusal' + - $ref: '#/components/schemas/OpenAIResponseContentPartReasoningText' + discriminator: + propertyName: type + mapping: + output_text: '#/components/schemas/OpenAIResponseContentPartOutputText' + refusal: '#/components/schemas/OpenAIResponseContentPartRefusal' + reasoning_text: '#/components/schemas/OpenAIResponseContentPartReasoningText' + description: The completed content part + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.content_part.done + default: response.content_part.done + description: >- + Event type identifier, always "response.content_part.done" + additionalProperties: false + required: + - content_index + - response_id + - item_id + - output_index + - part + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseContentPartDone + description: >- + Streaming event for when a content part is completed. + "OpenAIResponseObjectStreamResponseCreated": + type: object + properties: + response: + $ref: '#/components/schemas/OpenAIResponseObject' + description: The response object that was created + type: + type: string + const: response.created + default: response.created + description: >- + Event type identifier, always "response.created" + additionalProperties: false + required: + - response + - type + title: >- + OpenAIResponseObjectStreamResponseCreated + description: >- + Streaming event indicating a new response has been created. + OpenAIResponseObjectStreamResponseFailed: + type: object + properties: + response: + $ref: '#/components/schemas/OpenAIResponseObject' + description: Response object describing the failure + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.failed + default: response.failed + description: >- + Event type identifier, always "response.failed" + additionalProperties: false + required: + - response + - sequence_number + - type + title: OpenAIResponseObjectStreamResponseFailed + description: >- + Streaming event emitted when a response fails. + "OpenAIResponseObjectStreamResponseFileSearchCallCompleted": + type: object + properties: + item_id: + type: string + description: >- + Unique identifier of the completed file search call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.file_search_call.completed + default: response.file_search_call.completed + description: >- + Event type identifier, always "response.file_search_call.completed" + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseFileSearchCallCompleted + description: >- + Streaming event for completed file search calls. + "OpenAIResponseObjectStreamResponseFileSearchCallInProgress": + type: object + properties: + item_id: + type: string + description: >- + Unique identifier of the file search call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.file_search_call.in_progress + default: response.file_search_call.in_progress + description: >- + Event type identifier, always "response.file_search_call.in_progress" + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseFileSearchCallInProgress + description: >- + Streaming event for file search calls in progress. + "OpenAIResponseObjectStreamResponseFileSearchCallSearching": + type: object + properties: + item_id: + type: string + description: >- + Unique identifier of the file search call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.file_search_call.searching + default: response.file_search_call.searching + description: >- + Event type identifier, always "response.file_search_call.searching" + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseFileSearchCallSearching + description: >- + Streaming event for file search currently searching. + "OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta": + type: object + properties: + delta: + type: string + description: >- + Incremental function call arguments being added + item_id: + type: string + description: >- + Unique identifier of the function call being updated + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.function_call_arguments.delta + default: response.function_call_arguments.delta + description: >- + Event type identifier, always "response.function_call_arguments.delta" + additionalProperties: false + required: + - delta + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta + description: >- + Streaming event for incremental function call argument updates. + "OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone": + type: object + properties: + arguments: + type: string + description: >- + Final complete arguments JSON string for the function call + item_id: + type: string + description: >- + Unique identifier of the completed function call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.function_call_arguments.done + default: response.function_call_arguments.done + description: >- + Event type identifier, always "response.function_call_arguments.done" + additionalProperties: false + required: + - arguments + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone + description: >- + Streaming event for when function call arguments are completed. + "OpenAIResponseObjectStreamResponseInProgress": + type: object + properties: + response: + $ref: '#/components/schemas/OpenAIResponseObject' + description: Current response state while in progress + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.in_progress + default: response.in_progress + description: >- + Event type identifier, always "response.in_progress" + additionalProperties: false + required: + - response + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseInProgress + description: >- + Streaming event indicating the response remains in progress. + "OpenAIResponseObjectStreamResponseIncomplete": + type: object + properties: + response: + $ref: '#/components/schemas/OpenAIResponseObject' + description: >- + Response object describing the incomplete state + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.incomplete + default: response.incomplete + description: >- + Event type identifier, always "response.incomplete" + additionalProperties: false + required: + - response + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseIncomplete + description: >- + Streaming event emitted when a response ends in an incomplete state. + "OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta": + type: object + properties: + delta: + type: string + item_id: + type: string + output_index: + type: integer + sequence_number: + type: integer + type: + type: string + const: response.mcp_call.arguments.delta + default: response.mcp_call.arguments.delta + additionalProperties: false + required: + - delta + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta + "OpenAIResponseObjectStreamResponseMcpCallArgumentsDone": + type: object + properties: + arguments: + type: string + item_id: + type: string + output_index: + type: integer + sequence_number: + type: integer + type: + type: string + const: response.mcp_call.arguments.done + default: response.mcp_call.arguments.done + additionalProperties: false + required: + - arguments + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpCallArgumentsDone + "OpenAIResponseObjectStreamResponseMcpCallCompleted": + type: object + properties: + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.mcp_call.completed + default: response.mcp_call.completed + description: >- + Event type identifier, always "response.mcp_call.completed" + additionalProperties: false + required: + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpCallCompleted + description: Streaming event for completed MCP calls. + "OpenAIResponseObjectStreamResponseMcpCallFailed": + type: object + properties: + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.mcp_call.failed + default: response.mcp_call.failed + description: >- + Event type identifier, always "response.mcp_call.failed" + additionalProperties: false + required: + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpCallFailed + description: Streaming event for failed MCP calls. + "OpenAIResponseObjectStreamResponseMcpCallInProgress": + type: object + properties: + item_id: + type: string + description: Unique identifier of the MCP call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.mcp_call.in_progress + default: response.mcp_call.in_progress + description: >- + Event type identifier, always "response.mcp_call.in_progress" + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpCallInProgress + description: >- + Streaming event for MCP calls in progress. + "OpenAIResponseObjectStreamResponseMcpListToolsCompleted": + type: object + properties: + sequence_number: + type: integer + type: + type: string + const: response.mcp_list_tools.completed + default: response.mcp_list_tools.completed + additionalProperties: false + required: + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpListToolsCompleted + "OpenAIResponseObjectStreamResponseMcpListToolsFailed": + type: object + properties: + sequence_number: + type: integer + type: + type: string + const: response.mcp_list_tools.failed + default: response.mcp_list_tools.failed + additionalProperties: false + required: + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpListToolsFailed + "OpenAIResponseObjectStreamResponseMcpListToolsInProgress": + type: object + properties: + sequence_number: + type: integer + type: + type: string + const: response.mcp_list_tools.in_progress + default: response.mcp_list_tools.in_progress + additionalProperties: false + required: + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseMcpListToolsInProgress + "OpenAIResponseObjectStreamResponseOutputItemAdded": + type: object + properties: + response_id: + type: string + description: >- + Unique identifier of the response containing this output + item: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseMessage' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + discriminator: + propertyName: type + mapping: + message: '#/components/schemas/OpenAIResponseMessage' + web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + description: >- + The output item that was added (message, tool call, etc.) + output_index: + type: integer + description: >- + Index position of this item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.output_item.added + default: response.output_item.added + description: >- + Event type identifier, always "response.output_item.added" + additionalProperties: false + required: + - response_id + - item + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseOutputItemAdded + description: >- + Streaming event for when a new output item is added to the response. + "OpenAIResponseObjectStreamResponseOutputItemDone": + type: object + properties: + response_id: + type: string + description: >- + Unique identifier of the response containing this output + item: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseMessage' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + - $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + discriminator: + propertyName: type + mapping: + message: '#/components/schemas/OpenAIResponseMessage' + web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' + file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' + function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' + mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' + mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' + mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest' + description: >- + The completed output item (message, tool call, etc.) + output_index: + type: integer + description: >- + Index position of this item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.output_item.done + default: response.output_item.done + description: >- + Event type identifier, always "response.output_item.done" + additionalProperties: false + required: + - response_id + - item + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseOutputItemDone + description: >- + Streaming event for when an output item is completed. + "OpenAIResponseObjectStreamResponseOutputTextAnnotationAdded": + type: object + properties: + item_id: + type: string + description: >- + Unique identifier of the item to which the annotation is being added + output_index: + type: integer + description: >- + Index position of the output item in the response's output array + content_index: + type: integer + description: >- + Index position of the content part within the output item + annotation_index: + type: integer + description: >- + Index of the annotation within the content part + annotation: + oneOf: + - $ref: '#/components/schemas/OpenAIResponseAnnotationFileCitation' + - $ref: '#/components/schemas/OpenAIResponseAnnotationCitation' + - $ref: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' + - $ref: '#/components/schemas/OpenAIResponseAnnotationFilePath' + discriminator: + propertyName: type + mapping: + file_citation: '#/components/schemas/OpenAIResponseAnnotationFileCitation' + url_citation: '#/components/schemas/OpenAIResponseAnnotationCitation' + container_file_citation: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' + file_path: '#/components/schemas/OpenAIResponseAnnotationFilePath' + description: The annotation object being added + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.output_text.annotation.added + default: response.output_text.annotation.added + description: >- + Event type identifier, always "response.output_text.annotation.added" + additionalProperties: false + required: + - item_id + - output_index + - content_index + - annotation_index + - annotation + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseOutputTextAnnotationAdded + description: >- + Streaming event for when an annotation is added to output text. + "OpenAIResponseObjectStreamResponseOutputTextDelta": + type: object + properties: + content_index: + type: integer + description: Index position within the text content + delta: + type: string + description: Incremental text content being added + item_id: + type: string + description: >- + Unique identifier of the output item being updated + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.output_text.delta + default: response.output_text.delta + description: >- + Event type identifier, always "response.output_text.delta" + additionalProperties: false + required: + - content_index + - delta + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseOutputTextDelta + description: >- + Streaming event for incremental text content updates. + "OpenAIResponseObjectStreamResponseOutputTextDone": + type: object + properties: + content_index: + type: integer + description: Index position within the text content + text: + type: string + description: >- + Final complete text content of the output item + item_id: + type: string + description: >- + Unique identifier of the completed output item + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.output_text.done + default: response.output_text.done + description: >- + Event type identifier, always "response.output_text.done" + additionalProperties: false + required: + - content_index + - text + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseOutputTextDone + description: >- + Streaming event for when text output is completed. + "OpenAIResponseObjectStreamResponseReasoningSummaryPartAdded": + type: object + properties: + item_id: + type: string + description: Unique identifier of the output item + output_index: + type: integer + description: Index position of the output item + part: + $ref: '#/components/schemas/OpenAIResponseContentPartReasoningSummary' + description: The summary part that was added + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + summary_index: + type: integer + description: >- + Index of the summary part within the reasoning summary + type: + type: string + const: response.reasoning_summary_part.added + default: response.reasoning_summary_part.added + description: >- + Event type identifier, always "response.reasoning_summary_part.added" + additionalProperties: false + required: + - item_id + - output_index + - part + - sequence_number + - summary_index + - type + title: >- + OpenAIResponseObjectStreamResponseReasoningSummaryPartAdded + description: >- + Streaming event for when a new reasoning summary part is added. + "OpenAIResponseObjectStreamResponseReasoningSummaryPartDone": + type: object + properties: + item_id: + type: string + description: Unique identifier of the output item + output_index: + type: integer + description: Index position of the output item + part: + $ref: '#/components/schemas/OpenAIResponseContentPartReasoningSummary' + description: The completed summary part + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + summary_index: + type: integer + description: >- + Index of the summary part within the reasoning summary + type: + type: string + const: response.reasoning_summary_part.done + default: response.reasoning_summary_part.done + description: >- + Event type identifier, always "response.reasoning_summary_part.done" + additionalProperties: false + required: + - item_id + - output_index + - part + - sequence_number + - summary_index + - type + title: >- + OpenAIResponseObjectStreamResponseReasoningSummaryPartDone + description: >- + Streaming event for when a reasoning summary part is completed. + "OpenAIResponseObjectStreamResponseReasoningSummaryTextDelta": + type: object + properties: + delta: + type: string + description: Incremental summary text being added + item_id: + type: string + description: Unique identifier of the output item + output_index: + type: integer + description: Index position of the output item + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + summary_index: + type: integer + description: >- + Index of the summary part within the reasoning summary + type: + type: string + const: response.reasoning_summary_text.delta + default: response.reasoning_summary_text.delta + description: >- + Event type identifier, always "response.reasoning_summary_text.delta" + additionalProperties: false + required: + - delta + - item_id + - output_index + - sequence_number + - summary_index + - type + title: >- + OpenAIResponseObjectStreamResponseReasoningSummaryTextDelta + description: >- + Streaming event for incremental reasoning summary text updates. + "OpenAIResponseObjectStreamResponseReasoningSummaryTextDone": + type: object + properties: + text: + type: string + description: Final complete summary text + item_id: + type: string + description: Unique identifier of the output item + output_index: + type: integer + description: Index position of the output item + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + summary_index: + type: integer + description: >- + Index of the summary part within the reasoning summary + type: + type: string + const: response.reasoning_summary_text.done + default: response.reasoning_summary_text.done + description: >- + Event type identifier, always "response.reasoning_summary_text.done" + additionalProperties: false + required: + - text + - item_id + - output_index + - sequence_number + - summary_index + - type + title: >- + OpenAIResponseObjectStreamResponseReasoningSummaryTextDone + description: >- + Streaming event for when reasoning summary text is completed. + "OpenAIResponseObjectStreamResponseReasoningTextDelta": + type: object + properties: + content_index: + type: integer + description: >- + Index position of the reasoning content part + delta: + type: string + description: Incremental reasoning text being added + item_id: + type: string + description: >- + Unique identifier of the output item being updated + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.reasoning_text.delta + default: response.reasoning_text.delta + description: >- + Event type identifier, always "response.reasoning_text.delta" + additionalProperties: false + required: + - content_index + - delta + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseReasoningTextDelta + description: >- + Streaming event for incremental reasoning text updates. + "OpenAIResponseObjectStreamResponseReasoningTextDone": + type: object + properties: + content_index: + type: integer + description: >- + Index position of the reasoning content part + text: + type: string + description: Final complete reasoning text + item_id: + type: string + description: >- + Unique identifier of the completed output item + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.reasoning_text.done + default: response.reasoning_text.done + description: >- + Event type identifier, always "response.reasoning_text.done" + additionalProperties: false + required: + - content_index + - text + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseReasoningTextDone + description: >- + Streaming event for when reasoning text is completed. + "OpenAIResponseObjectStreamResponseRefusalDelta": + type: object + properties: + content_index: + type: integer + description: Index position of the content part + delta: + type: string + description: Incremental refusal text being added + item_id: + type: string + description: Unique identifier of the output item + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.refusal.delta + default: response.refusal.delta + description: >- + Event type identifier, always "response.refusal.delta" + additionalProperties: false + required: + - content_index + - delta + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseRefusalDelta + description: >- + Streaming event for incremental refusal text updates. + "OpenAIResponseObjectStreamResponseRefusalDone": + type: object + properties: + content_index: + type: integer + description: Index position of the content part + refusal: + type: string + description: Final complete refusal text + item_id: + type: string + description: Unique identifier of the output item + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.refusal.done + default: response.refusal.done + description: >- + Event type identifier, always "response.refusal.done" + additionalProperties: false + required: + - content_index + - refusal + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseRefusalDone + description: >- + Streaming event for when refusal text is completed. + "OpenAIResponseObjectStreamResponseWebSearchCallCompleted": + type: object + properties: + item_id: + type: string + description: >- + Unique identifier of the completed web search call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.web_search_call.completed + default: response.web_search_call.completed + description: >- + Event type identifier, always "response.web_search_call.completed" + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseWebSearchCallCompleted + description: >- + Streaming event for completed web search calls. + "OpenAIResponseObjectStreamResponseWebSearchCallInProgress": + type: object + properties: + item_id: + type: string + description: Unique identifier of the web search call + output_index: + type: integer + description: >- + Index position of the item in the output list + sequence_number: + type: integer + description: >- + Sequential number for ordering streaming events + type: + type: string + const: response.web_search_call.in_progress + default: response.web_search_call.in_progress + description: >- + Event type identifier, always "response.web_search_call.in_progress" + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseWebSearchCallInProgress + description: >- + Streaming event for web search calls in progress. + "OpenAIResponseObjectStreamResponseWebSearchCallSearching": + type: object + properties: + item_id: + type: string + output_index: + type: integer + sequence_number: + type: integer + type: + type: string + const: response.web_search_call.searching + default: response.web_search_call.searching + additionalProperties: false + required: + - item_id + - output_index + - sequence_number + - type + title: >- + OpenAIResponseObjectStreamResponseWebSearchCallSearching + OpenAIDeleteResponseObject: + type: object + properties: + id: + type: string + description: >- + Unique identifier of the deleted response + object: + type: string + const: response + default: response + description: >- + Object type identifier, always "response" + deleted: + type: boolean + default: true + description: Deletion confirmation flag, always True + additionalProperties: false + required: + - id + - object + - deleted + title: OpenAIDeleteResponseObject + description: >- + Response object confirming deletion of an OpenAI response. + ListOpenAIResponseInputItem: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/OpenAIResponseInput' + description: List of input items + object: + type: string + const: list + default: list + description: Object type identifier, always "list" + additionalProperties: false + required: + - data + - object + title: ListOpenAIResponseInputItem + description: >- + List container for OpenAI response input items. + RunShieldRequest: + type: object + properties: + shield_id: + type: string + description: The identifier of the shield to run. + messages: + type: array + items: + $ref: '#/components/schemas/OpenAIMessageParam' + description: The messages to run the shield on. + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The parameters of the shield. + additionalProperties: false + required: + - shield_id + - messages + - params + title: RunShieldRequest + RunShieldResponse: + type: object + properties: + violation: + $ref: '#/components/schemas/SafetyViolation' + description: >- + (Optional) Safety violation detected by the shield, if any + additionalProperties: false + title: RunShieldResponse + description: Response from running a safety shield. + SafetyViolation: + type: object + properties: + violation_level: + $ref: '#/components/schemas/ViolationLevel' + description: Severity level of the violation + user_message: + type: string + description: >- + (Optional) Message to convey to the user about the violation + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Additional metadata including specific violation codes for debugging and + telemetry + additionalProperties: false + required: + - violation_level + - metadata + title: SafetyViolation + description: >- + Details of a safety violation detected by content moderation. + ViolationLevel: + type: string + enum: + - info + - warn + - error + title: ViolationLevel + description: Severity level of a safety violation. + AgentTurnInputType: + type: object + properties: + type: + type: string + const: agent_turn_input + default: agent_turn_input + description: >- + Discriminator type. Always "agent_turn_input" + additionalProperties: false + required: + - type + title: AgentTurnInputType + description: Parameter type for agent turn input. + AggregationFunctionType: + type: string + enum: + - average + - weighted_average + - median + - categorical_count + - accuracy + title: AggregationFunctionType + description: >- + Types of aggregation functions for scoring results. + ArrayType: + type: object + properties: + type: + type: string + const: array + default: array + description: Discriminator type. Always "array" + additionalProperties: false + required: + - type + title: ArrayType + description: Parameter type for array values. + BasicScoringFnParams: + type: object + properties: + type: + $ref: '#/components/schemas/ScoringFnParamsType' + const: basic + default: basic + description: >- + The type of scoring function parameters, always basic + aggregation_functions: + type: array + items: + $ref: '#/components/schemas/AggregationFunctionType' + description: >- + Aggregation functions to apply to the scores of each row + additionalProperties: false + required: + - type + - aggregation_functions + title: BasicScoringFnParams + description: >- + Parameters for basic scoring function configuration. + BooleanType: + type: object + properties: + type: + type: string + const: boolean + default: boolean + description: Discriminator type. Always "boolean" + additionalProperties: false + required: + - type + title: BooleanType + description: Parameter type for boolean values. + ChatCompletionInputType: + type: object + properties: + type: + type: string + const: chat_completion_input + default: chat_completion_input + description: >- + Discriminator type. Always "chat_completion_input" + additionalProperties: false + required: + - type + title: ChatCompletionInputType + description: >- + Parameter type for chat completion input. + CompletionInputType: + type: object + properties: + type: + type: string + const: completion_input + default: completion_input + description: >- + Discriminator type. Always "completion_input" + additionalProperties: false + required: + - type + title: CompletionInputType + description: Parameter type for completion input. + JsonType: + type: object + properties: + type: + type: string + const: json + default: json + description: Discriminator type. Always "json" + additionalProperties: false + required: + - type + title: JsonType + description: Parameter type for JSON values. + LLMAsJudgeScoringFnParams: + type: object + properties: + type: + $ref: '#/components/schemas/ScoringFnParamsType' + const: llm_as_judge + default: llm_as_judge + description: >- + The type of scoring function parameters, always llm_as_judge + judge_model: + type: string + description: >- + Identifier of the LLM model to use as a judge for scoring + prompt_template: + type: string + description: >- + (Optional) Custom prompt template for the judge model + judge_score_regexes: + type: array + items: + type: string + description: >- + Regexes to extract the answer from generated response + aggregation_functions: + type: array + items: + $ref: '#/components/schemas/AggregationFunctionType' + description: >- + Aggregation functions to apply to the scores of each row + additionalProperties: false + required: + - type + - judge_model + - judge_score_regexes + - aggregation_functions + title: LLMAsJudgeScoringFnParams + description: >- + Parameters for LLM-as-judge scoring function configuration. + NumberType: + type: object + properties: + type: + type: string + const: number + default: number + description: Discriminator type. Always "number" + additionalProperties: false + required: + - type + title: NumberType + description: Parameter type for numeric values. + ObjectType: + type: object + properties: + type: + type: string + const: object + default: object + description: Discriminator type. Always "object" + additionalProperties: false + required: + - type + title: ObjectType + description: Parameter type for object values. + RegexParserScoringFnParams: + type: object + properties: + type: + $ref: '#/components/schemas/ScoringFnParamsType' + const: regex_parser + default: regex_parser + description: >- + The type of scoring function parameters, always regex_parser + parsing_regexes: + type: array + items: + type: string + description: >- + Regex to extract the answer from generated response + aggregation_functions: + type: array + items: + $ref: '#/components/schemas/AggregationFunctionType' + description: >- + Aggregation functions to apply to the scores of each row + additionalProperties: false + required: + - type + - parsing_regexes + - aggregation_functions + title: RegexParserScoringFnParams + description: >- + Parameters for regex parser scoring function configuration. + ScoringFn: + type: object + properties: + identifier: + type: string + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + enum: + - model + - shield + - vector_db + - dataset + - scoring_function + - benchmark + - tool + - tool_group + - prompt + const: scoring_function + default: scoring_function + description: >- + The resource type, always scoring_function + description: + type: string + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + return_type: + oneOf: + - $ref: '#/components/schemas/StringType' + - $ref: '#/components/schemas/NumberType' + - $ref: '#/components/schemas/BooleanType' + - $ref: '#/components/schemas/ArrayType' + - $ref: '#/components/schemas/ObjectType' + - $ref: '#/components/schemas/JsonType' + - $ref: '#/components/schemas/UnionType' + - $ref: '#/components/schemas/ChatCompletionInputType' + - $ref: '#/components/schemas/CompletionInputType' + - $ref: '#/components/schemas/AgentTurnInputType' + discriminator: + propertyName: type + mapping: + string: '#/components/schemas/StringType' + number: '#/components/schemas/NumberType' + boolean: '#/components/schemas/BooleanType' + array: '#/components/schemas/ArrayType' + object: '#/components/schemas/ObjectType' + json: '#/components/schemas/JsonType' + union: '#/components/schemas/UnionType' + chat_completion_input: '#/components/schemas/ChatCompletionInputType' + completion_input: '#/components/schemas/CompletionInputType' + agent_turn_input: '#/components/schemas/AgentTurnInputType' + params: + $ref: '#/components/schemas/ScoringFnParams' + additionalProperties: false + required: + - identifier + - provider_id + - type + - metadata + - return_type + title: ScoringFn + description: >- + A scoring function resource for evaluating model outputs. + ScoringFnParams: + oneOf: + - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' + - $ref: '#/components/schemas/RegexParserScoringFnParams' + - $ref: '#/components/schemas/BasicScoringFnParams' + discriminator: + propertyName: type + mapping: + llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' + regex_parser: '#/components/schemas/RegexParserScoringFnParams' + basic: '#/components/schemas/BasicScoringFnParams' + ScoringFnParamsType: + type: string + enum: + - llm_as_judge + - regex_parser + - basic + title: ScoringFnParamsType + description: >- + Types of scoring function parameter configurations. + StringType: + type: object + properties: + type: + type: string + const: string + default: string + description: Discriminator type. Always "string" + additionalProperties: false + required: + - type + title: StringType + description: Parameter type for string values. + UnionType: + type: object + properties: + type: + type: string + const: union + default: union + description: Discriminator type. Always "union" + additionalProperties: false + required: + - type + title: UnionType + description: Parameter type for union values. + ListScoringFunctionsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ScoringFn' + additionalProperties: false + required: + - data + title: ListScoringFunctionsResponse + ParamType: + oneOf: + - $ref: '#/components/schemas/StringType' + - $ref: '#/components/schemas/NumberType' + - $ref: '#/components/schemas/BooleanType' + - $ref: '#/components/schemas/ArrayType' + - $ref: '#/components/schemas/ObjectType' + - $ref: '#/components/schemas/JsonType' + - $ref: '#/components/schemas/UnionType' + - $ref: '#/components/schemas/ChatCompletionInputType' + - $ref: '#/components/schemas/CompletionInputType' + - $ref: '#/components/schemas/AgentTurnInputType' + discriminator: + propertyName: type + mapping: + string: '#/components/schemas/StringType' + number: '#/components/schemas/NumberType' + boolean: '#/components/schemas/BooleanType' + array: '#/components/schemas/ArrayType' + object: '#/components/schemas/ObjectType' + json: '#/components/schemas/JsonType' + union: '#/components/schemas/UnionType' + chat_completion_input: '#/components/schemas/ChatCompletionInputType' + completion_input: '#/components/schemas/CompletionInputType' + agent_turn_input: '#/components/schemas/AgentTurnInputType' + RegisterScoringFunctionRequest: + type: object + properties: + scoring_fn_id: + type: string + description: >- + The ID of the scoring function to register. + description: + type: string + description: The description of the scoring function. + return_type: + $ref: '#/components/schemas/ParamType' + description: The return type of the scoring function. + provider_scoring_fn_id: + type: string + description: >- + The ID of the provider scoring function to use for the scoring function. + provider_id: + type: string + description: >- + The ID of the provider to use for the scoring function. + params: + $ref: '#/components/schemas/ScoringFnParams' + description: >- + The parameters for the scoring function for benchmark eval, these can + be overridden for app eval. + additionalProperties: false + required: + - scoring_fn_id + - description + - return_type + title: RegisterScoringFunctionRequest + ScoreRequest: + type: object + properties: + input_rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The rows to score. + scoring_functions: + type: object + additionalProperties: + oneOf: + - $ref: '#/components/schemas/ScoringFnParams' + - type: 'null' + description: >- + The scoring functions to use for the scoring. + additionalProperties: false + required: + - input_rows + - scoring_functions + title: ScoreRequest + ScoreResponse: + type: object + properties: + results: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringResult' + description: >- + A map of scoring function name to ScoringResult. + additionalProperties: false + required: + - results + title: ScoreResponse + description: The response from scoring. + ScoringResult: + type: object + properties: + score_rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The scoring result for each row. Each row is a map of column name to value. + aggregated_results: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Map of metric name to aggregated value + additionalProperties: false + required: + - score_rows + - aggregated_results + title: ScoringResult + description: A scoring result for a single row. + ScoreBatchRequest: + type: object + properties: + dataset_id: + type: string + description: The ID of the dataset to score. + scoring_functions: + type: object + additionalProperties: + oneOf: + - $ref: '#/components/schemas/ScoringFnParams' + - type: 'null' + description: >- + The scoring functions to use for the scoring. + save_results_dataset: + type: boolean + description: >- + Whether to save the results to a dataset. + additionalProperties: false + required: + - dataset_id + - scoring_functions + - save_results_dataset + title: ScoreBatchRequest + ScoreBatchResponse: + type: object + properties: + dataset_id: + type: string + description: >- + (Optional) The identifier of the dataset that was scored + results: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringResult' + description: >- + A map of scoring function name to ScoringResult + additionalProperties: false + required: + - results + title: ScoreBatchResponse + description: >- + Response from batch scoring operations on datasets. + Shield: + type: object + properties: + identifier: + type: string + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + enum: + - model + - shield + - vector_db + - dataset + - scoring_function + - benchmark + - tool + - tool_group + - prompt + const: shield + default: shield + description: The resource type, always shield + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Configuration parameters for the shield + additionalProperties: false + required: + - identifier + - provider_id + - type + title: Shield + description: >- + A safety shield resource that can be used to check content. + ListShieldsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Shield' + additionalProperties: false + required: + - data + title: ListShieldsResponse + RegisterShieldRequest: + type: object + properties: + shield_id: + type: string + description: >- + The identifier of the shield to register. + provider_shield_id: + type: string + description: >- + The identifier of the shield in the provider. + provider_id: + type: string + description: The identifier of the provider. + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The parameters of the shield. + additionalProperties: false + required: + - shield_id + title: RegisterShieldRequest + CompletionMessage: + type: object + properties: + role: + type: string + const: assistant + default: assistant + description: >- + Must be "assistant" to identify this as the model's response + content: + $ref: '#/components/schemas/InterleavedContent' + description: The content of the model's response + stop_reason: + type: string + enum: + - end_of_turn + - end_of_message + - out_of_tokens + description: >- + Reason why the model stopped generating. Options are: - `StopReason.end_of_turn`: + The model finished generating the entire response. - `StopReason.end_of_message`: + The model finished generating but generated a partial response -- usually, + a tool call. The user may call the tool and continue the conversation + with the tool's response. - `StopReason.out_of_tokens`: The model ran + out of token budget. + tool_calls: + type: array + items: + $ref: '#/components/schemas/ToolCall' + description: >- + List of tool calls. Each tool call is a ToolCall object. + additionalProperties: false + required: + - role + - content + - stop_reason + title: CompletionMessage + description: >- + A message containing the model's (assistant) response in a chat conversation. + ImageContentItem: + type: object + properties: + type: + type: string + const: image + default: image + description: >- + Discriminator type of the content item. Always "image" + image: + type: object + properties: + url: + $ref: '#/components/schemas/URL' + description: >- + A URL of the image or data URL in the format of data:image/{type};base64,{data}. + Note that URL could have length limits. + data: + type: string + contentEncoding: base64 + description: base64 encoded image data as string + additionalProperties: false + description: >- + Image as a base64 encoded string or an URL + additionalProperties: false + required: + - type + - image + title: ImageContentItem + description: A image content item + InterleavedContent: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + InterleavedContentItem: + oneOf: + - $ref: '#/components/schemas/ImageContentItem' + - $ref: '#/components/schemas/TextContentItem' + discriminator: + propertyName: type + mapping: + image: '#/components/schemas/ImageContentItem' + text: '#/components/schemas/TextContentItem' + Message: + oneOf: + - $ref: '#/components/schemas/UserMessage' + - $ref: '#/components/schemas/SystemMessage' + - $ref: '#/components/schemas/ToolResponseMessage' + - $ref: '#/components/schemas/CompletionMessage' + discriminator: + propertyName: role + mapping: + user: '#/components/schemas/UserMessage' + system: '#/components/schemas/SystemMessage' + tool: '#/components/schemas/ToolResponseMessage' + assistant: '#/components/schemas/CompletionMessage' + SystemMessage: + type: object + properties: + role: + type: string + const: system + default: system + description: >- + Must be "system" to identify this as a system message + content: + $ref: '#/components/schemas/InterleavedContent' + description: >- + The content of the "system prompt". If multiple system messages are provided, + they are concatenated. The underlying Llama Stack code may also add other + system messages (for example, for formatting tool definitions). + additionalProperties: false + required: + - role + - content + title: SystemMessage + description: >- + A system message providing instructions or context to the model. + TextContentItem: + type: object + properties: + type: + type: string + const: text + default: text + description: >- + Discriminator type of the content item. Always "text" + text: + type: string + description: Text content + additionalProperties: false + required: + - type + - text + title: TextContentItem + description: A text content item + ToolCall: + type: object + properties: + call_id: + type: string + tool_name: + oneOf: + - type: string + enum: + - brave_search + - wolfram_alpha + - photogen + - code_interpreter + title: BuiltinTool + - type: string + arguments: + type: string + additionalProperties: false + required: + - call_id + - tool_name + - arguments + title: ToolCall + ToolResponseMessage: + type: object + properties: + role: + type: string + const: tool + default: tool + description: >- + Must be "tool" to identify this as a tool response + call_id: + type: string + description: >- + Unique identifier for the tool call this response is for + content: + $ref: '#/components/schemas/InterleavedContent' + description: The response content from the tool + additionalProperties: false + required: + - role + - call_id + - content + title: ToolResponseMessage + description: >- + A message representing the result of a tool invocation. + URL: + type: object + properties: + uri: + type: string + description: The URL string pointing to the resource + additionalProperties: false + required: + - uri + title: URL + description: A URL reference to external content. + UserMessage: + type: object + properties: + role: + type: string + const: user + default: user + description: >- + Must be "user" to identify this as a user message + content: + $ref: '#/components/schemas/InterleavedContent' + description: >- + The content of the message, which can include text and other media + context: + $ref: '#/components/schemas/InterleavedContent' + description: >- + (Optional) This field is used internally by Llama Stack to pass RAG context. + This field may be removed in the API in the future. + additionalProperties: false + required: + - role + - content + title: UserMessage + description: >- + A message from the user in a chat conversation. + SyntheticDataGenerateRequest: + type: object + properties: + dialogs: + type: array + items: + $ref: '#/components/schemas/Message' + description: >- + List of conversation messages to use as input for synthetic data generation + filtering_function: + type: string + enum: + - none + - random + - top_k + - top_p + - top_k_top_p + - sigmoid + description: >- + Type of filtering to apply to generated synthetic data samples + model: + type: string + description: >- + (Optional) The identifier of the model to use. The model must be registered + with Llama Stack and available via the /models endpoint + additionalProperties: false + required: + - dialogs + - filtering_function + title: SyntheticDataGenerateRequest + SyntheticDataGenerationResponse: + type: object + properties: + synthetic_data: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + List of generated synthetic data samples that passed the filtering criteria + statistics: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Statistical information about the generation process and filtering + results + additionalProperties: false + required: + - synthetic_data + title: SyntheticDataGenerationResponse + description: >- + Response from the synthetic data generation. Batch of (prompt, response, score) + tuples that pass the threshold. + InvokeToolRequest: + type: object + properties: + tool_name: + type: string + description: The name of the tool to invoke. + kwargs: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + A dictionary of arguments to pass to the tool. + additionalProperties: false + required: + - tool_name + - kwargs + title: InvokeToolRequest + ToolInvocationResult: + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + description: >- + (Optional) The output content from the tool execution + error_message: + type: string + description: >- + (Optional) Error message if the tool execution failed + error_code: + type: integer + description: >- + (Optional) Numeric error code if the tool execution failed + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Additional metadata about the tool execution + additionalProperties: false + title: ToolInvocationResult + description: Result of a tool invocation. + ToolDef: + type: object + properties: + toolgroup_id: + type: string + description: >- + (Optional) ID of the tool group this tool belongs to + name: + type: string + description: Name of the tool + description: + type: string + description: >- + (Optional) Human-readable description of what the tool does + input_schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) JSON Schema for tool inputs (MCP inputSchema) + output_schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) JSON Schema for tool outputs (MCP outputSchema) + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Additional metadata about the tool + additionalProperties: false + required: + - name + title: ToolDef + description: >- + Tool definition used in runtime contexts. + ListToolDefsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ToolDef' + description: List of tool definitions + additionalProperties: false + required: + - data + title: ListToolDefsResponse + description: >- + Response containing a list of tool definitions. + RAGDocument: + type: object + properties: + document_id: + type: string + description: The unique identifier for the document. + content: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + - $ref: '#/components/schemas/URL' + description: The content of the document. + mime_type: + type: string + description: The MIME type of the document. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Additional metadata for the document. + additionalProperties: false + required: + - document_id + - content + - metadata + title: RAGDocument + description: >- + A document to be used for document ingestion in the RAG Tool. + InsertRequest: + type: object + properties: + documents: + type: array + items: + $ref: '#/components/schemas/RAGDocument' + description: >- + List of documents to index in the RAG system + vector_db_id: + type: string + description: >- + ID of the vector database to store the document embeddings + chunk_size_in_tokens: + type: integer + description: >- + (Optional) Size in tokens for document chunking during indexing + additionalProperties: false + required: + - documents + - vector_db_id + - chunk_size_in_tokens + title: InsertRequest + DefaultRAGQueryGeneratorConfig: + type: object + properties: + type: + type: string + const: default + default: default + description: >- + Type of query generator, always 'default' + separator: + type: string + default: ' ' + description: >- + String separator used to join query terms + additionalProperties: false + required: + - type + - separator + title: DefaultRAGQueryGeneratorConfig + description: >- + Configuration for the default RAG query generator. + LLMRAGQueryGeneratorConfig: + type: object + properties: + type: + type: string + const: llm + default: llm + description: Type of query generator, always 'llm' + model: + type: string + description: >- + Name of the language model to use for query generation + template: + type: string + description: >- + Template string for formatting the query generation prompt + additionalProperties: false + required: + - type + - model + - template + title: LLMRAGQueryGeneratorConfig + description: >- + Configuration for the LLM-based RAG query generator. + RAGQueryConfig: + type: object + properties: + query_generator_config: + oneOf: + - $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig' + - $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig' + discriminator: + propertyName: type + mapping: + default: '#/components/schemas/DefaultRAGQueryGeneratorConfig' + llm: '#/components/schemas/LLMRAGQueryGeneratorConfig' + description: Configuration for the query generator. + max_tokens_in_context: + type: integer + default: 4096 + description: Maximum number of tokens in the context. + max_chunks: + type: integer + default: 5 + description: Maximum number of chunks to retrieve. + chunk_template: + type: string + default: > + Result {index} + + Content: {chunk.content} + + Metadata: {metadata} + description: >- + Template for formatting each retrieved chunk in the context. Available + placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk + content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent: + {chunk.content}\nMetadata: {metadata}\n" + mode: + $ref: '#/components/schemas/RAGSearchMode' + default: vector + description: >- + Search mode for retrieval—either "vector", "keyword", or "hybrid". Default + "vector". + ranker: + $ref: '#/components/schemas/Ranker' + description: >- + Configuration for the ranker to use in hybrid search. Defaults to RRF + ranker. + additionalProperties: false + required: + - query_generator_config + - max_tokens_in_context + - max_chunks + - chunk_template + title: RAGQueryConfig + description: >- + Configuration for the RAG query generation. + RAGSearchMode: + type: string + enum: + - vector + - keyword + - hybrid + title: RAGSearchMode + description: >- + Search modes for RAG query retrieval: - VECTOR: Uses vector similarity search + for semantic matching - KEYWORD: Uses keyword-based search for exact matching + - HYBRID: Combines both vector and keyword search for better results + RRFRanker: + type: object + properties: + type: + type: string + const: rrf + default: rrf + description: The type of ranker, always "rrf" + impact_factor: + type: number + default: 60.0 + description: >- + The impact factor for RRF scoring. Higher values give more weight to higher-ranked + results. Must be greater than 0 + additionalProperties: false + required: + - type + - impact_factor + title: RRFRanker + description: >- + Reciprocal Rank Fusion (RRF) ranker configuration. + Ranker: + oneOf: + - $ref: '#/components/schemas/RRFRanker' + - $ref: '#/components/schemas/WeightedRanker' + discriminator: + propertyName: type + mapping: + rrf: '#/components/schemas/RRFRanker' + weighted: '#/components/schemas/WeightedRanker' + WeightedRanker: + type: object + properties: + type: + type: string + const: weighted + default: weighted + description: The type of ranker, always "weighted" + alpha: + type: number + default: 0.5 + description: >- + Weight factor between 0 and 1. 0 means only use keyword scores, 1 means + only use vector scores, values in between blend both scores. + additionalProperties: false + required: + - type + - alpha + title: WeightedRanker + description: >- + Weighted ranker configuration that combines vector and keyword scores. + QueryRequest: + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + description: >- + The query content to search for in the indexed documents + vector_db_ids: + type: array + items: + type: string + description: >- + List of vector database IDs to search within + query_config: + $ref: '#/components/schemas/RAGQueryConfig' + description: >- + (Optional) Configuration parameters for the query operation + additionalProperties: false + required: + - content + - vector_db_ids + title: QueryRequest + RAGQueryResult: + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + description: >- + (Optional) The retrieved content from the query + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Additional metadata about the query result + additionalProperties: false + required: + - metadata + title: RAGQueryResult + description: >- + Result of a RAG query containing retrieved content and metadata. + ToolGroup: + type: object + properties: + identifier: + type: string + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + enum: + - model + - shield + - vector_db + - dataset + - scoring_function + - benchmark + - tool + - tool_group + - prompt + const: tool_group + default: tool_group + description: Type of resource, always 'tool_group' + mcp_endpoint: + $ref: '#/components/schemas/URL' + description: >- + (Optional) Model Context Protocol endpoint for remote tools + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Additional arguments for the tool group + additionalProperties: false + required: + - identifier + - provider_id + - type + title: ToolGroup + description: >- + A group of related tools managed together. + ListToolGroupsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ToolGroup' + description: List of tool groups + additionalProperties: false + required: + - data + title: ListToolGroupsResponse + description: >- + Response containing a list of tool groups. + RegisterToolGroupRequest: + type: object + properties: + toolgroup_id: + type: string + description: The ID of the tool group to register. + provider_id: + type: string + description: >- + The ID of the provider to use for the tool group. + mcp_endpoint: + $ref: '#/components/schemas/URL' + description: >- + The MCP endpoint to use for the tool group. + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + A dictionary of arguments to pass to the tool group. + additionalProperties: false + required: + - toolgroup_id + - provider_id + title: RegisterToolGroupRequest + Chunk: + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + description: >- + The content of the chunk, which can be interleaved text, images, or other + types. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Metadata associated with the chunk that will be used in the model context + during inference. + embedding: + type: array + items: + type: number + description: >- + Optional embedding for the chunk. If not provided, it will be computed + later. + stored_chunk_id: + type: string + description: >- + The chunk ID that is stored in the vector database. Used for backend functionality. + chunk_metadata: + $ref: '#/components/schemas/ChunkMetadata' + description: >- + Metadata for the chunk that will NOT be used in the context during inference. + The `chunk_metadata` is required backend functionality. + additionalProperties: false + required: + - content + - metadata + title: Chunk + description: >- + A chunk of content that can be inserted into a vector database. + ChunkMetadata: + type: object + properties: + chunk_id: + type: string + description: >- + The ID of the chunk. If not set, it will be generated based on the document + ID and content. + document_id: + type: string + description: >- + The ID of the document this chunk belongs to. + source: + type: string + description: >- + The source of the content, such as a URL, file path, or other identifier. + created_timestamp: + type: integer + description: >- + An optional timestamp indicating when the chunk was created. + updated_timestamp: + type: integer + description: >- + An optional timestamp indicating when the chunk was last updated. + chunk_window: + type: string + description: >- + The window of the chunk, which can be used to group related chunks together. + chunk_tokenizer: + type: string + description: >- + The tokenizer used to create the chunk. Default is Tiktoken. + chunk_embedding_model: + type: string + description: >- + The embedding model used to create the chunk's embedding. + chunk_embedding_dimension: + type: integer + description: >- + The dimension of the embedding vector for the chunk. + content_token_count: + type: integer + description: >- + The number of tokens in the content of the chunk. + metadata_token_count: + type: integer + description: >- + The number of tokens in the metadata of the chunk. + additionalProperties: false + title: ChunkMetadata + description: >- + `ChunkMetadata` is backend metadata for a `Chunk` that is used to store additional + information about the chunk that will not be used in the context during + inference, but is required for backend functionality. The `ChunkMetadata` is + set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not + expected to change after. Use `Chunk.metadata` for metadata that will + be used in the context during inference. + InsertChunksRequest: + type: object + properties: + vector_db_id: + type: string + description: >- + The identifier of the vector database to insert the chunks into. + chunks: + type: array + items: + $ref: '#/components/schemas/Chunk' + description: >- + The chunks to insert. Each `Chunk` should contain content which can be + interleaved text, images, or other types. `metadata`: `dict[str, Any]` + and `embedding`: `List[float]` are optional. If `metadata` is provided, + you configure how Llama Stack formats the chunk during generation. If + `embedding` is not provided, it will be computed later. + ttl_seconds: + type: integer + description: The time to live of the chunks. + additionalProperties: false + required: + - vector_db_id + - chunks + title: InsertChunksRequest + QueryChunksRequest: + type: object + properties: + vector_db_id: + type: string + description: >- + The identifier of the vector database to query. + query: + $ref: '#/components/schemas/InterleavedContent' + description: The query to search for. + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The parameters of the query. + additionalProperties: false + required: + - vector_db_id + - query + title: QueryChunksRequest + QueryChunksResponse: + type: object + properties: + chunks: + type: array + items: + $ref: '#/components/schemas/Chunk' + description: >- + List of content chunks returned from the query + scores: + type: array + items: + type: number + description: >- + Relevance scores corresponding to each returned chunk + additionalProperties: false + required: + - chunks + - scores + title: QueryChunksResponse + description: >- + Response from querying chunks in a vector database. + VectorStoreFileCounts: + type: object + properties: + completed: + type: integer + description: >- + Number of files that have been successfully processed + cancelled: + type: integer + description: >- + Number of files that had their processing cancelled + failed: + type: integer + description: Number of files that failed to process + in_progress: + type: integer + description: >- + Number of files currently being processed + total: + type: integer + description: >- + Total number of files in the vector store + additionalProperties: false + required: + - completed + - cancelled + - failed + - in_progress + - total + title: VectorStoreFileCounts + description: >- + File processing status counts for a vector store. + VectorStoreListResponse: + type: object + properties: + object: + type: string + default: list + description: Object type identifier, always "list" + data: + type: array + items: + $ref: '#/components/schemas/VectorStoreObject' + description: List of vector store objects + first_id: + type: string + description: >- + (Optional) ID of the first vector store in the list for pagination + last_id: + type: string + description: >- + (Optional) ID of the last vector store in the list for pagination + has_more: + type: boolean + default: false + description: >- + Whether there are more vector stores available beyond this page + additionalProperties: false + required: + - object + - data + - has_more + title: VectorStoreListResponse + description: Response from listing vector stores. + VectorStoreObject: + type: object + properties: + id: + type: string + description: Unique identifier for the vector store + object: + type: string + default: vector_store + description: >- + Object type identifier, always "vector_store" + created_at: + type: integer + description: >- + Timestamp when the vector store was created + name: + type: string + description: (Optional) Name of the vector store + usage_bytes: + type: integer + default: 0 + description: >- + Storage space used by the vector store in bytes + file_counts: + $ref: '#/components/schemas/VectorStoreFileCounts' + description: >- + File processing status counts for the vector store + status: + type: string + default: completed + description: Current status of the vector store + expires_after: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Expiration policy for the vector store + expires_at: + type: integer + description: >- + (Optional) Timestamp when the vector store will expire + last_active_at: + type: integer + description: >- + (Optional) Timestamp of last activity on the vector store + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Set of key-value pairs that can be attached to the vector store + additionalProperties: false + required: + - id + - object + - created_at + - usage_bytes + - file_counts + - status + - metadata + title: VectorStoreObject + description: OpenAI Vector Store object. + "OpenAICreateVectorStoreRequestWithExtraBody": + type: object + properties: + name: + type: string + description: (Optional) A name for the vector store + file_ids: + type: array + items: + type: string + description: >- + List of file IDs to include in the vector store + expires_after: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Expiration policy for the vector store + chunking_strategy: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Strategy for splitting files into chunks + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Set of key-value pairs that can be attached to the vector store + additionalProperties: false + title: >- + OpenAICreateVectorStoreRequestWithExtraBody + description: >- + Request to create a vector store with extra_body support. + OpenaiUpdateVectorStoreRequest: + type: object + properties: + name: + type: string + description: The name of the vector store. + expires_after: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The expiration policy for a vector store. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Set of 16 key-value pairs that can be attached to an object. + additionalProperties: false + title: OpenaiUpdateVectorStoreRequest + VectorStoreDeleteResponse: + type: object + properties: + id: + type: string + description: >- + Unique identifier of the deleted vector store + object: + type: string + default: vector_store.deleted + description: >- + Object type identifier for the deletion response + deleted: + type: boolean + default: true + description: >- + Whether the deletion operation was successful + additionalProperties: false + required: + - id + - object + - deleted + title: VectorStoreDeleteResponse + description: Response from deleting a vector store. + VectorStoreChunkingStrategy: + oneOf: + - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' + - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' + discriminator: + propertyName: type + mapping: + auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' + static: '#/components/schemas/VectorStoreChunkingStrategyStatic' + VectorStoreChunkingStrategyAuto: + type: object + properties: + type: + type: string + const: auto + default: auto + description: >- + Strategy type, always "auto" for automatic chunking + additionalProperties: false + required: + - type + title: VectorStoreChunkingStrategyAuto + description: >- + Automatic chunking strategy for vector store files. + VectorStoreChunkingStrategyStatic: + type: object + properties: + type: + type: string + const: static + default: static + description: >- + Strategy type, always "static" for static chunking + static: + $ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig' + description: >- + Configuration parameters for the static chunking strategy + additionalProperties: false + required: + - type + - static + title: VectorStoreChunkingStrategyStatic + description: >- + Static chunking strategy with configurable parameters. + VectorStoreChunkingStrategyStaticConfig: + type: object + properties: + chunk_overlap_tokens: + type: integer + default: 400 + description: >- + Number of tokens to overlap between adjacent chunks + max_chunk_size_tokens: + type: integer + default: 800 + description: >- + Maximum number of tokens per chunk, must be between 100 and 4096 + additionalProperties: false + required: + - chunk_overlap_tokens + - max_chunk_size_tokens + title: VectorStoreChunkingStrategyStaticConfig + description: >- + Configuration for static chunking strategy. + "OpenAICreateVectorStoreFileBatchRequestWithExtraBody": + type: object + properties: + file_ids: + type: array + items: + type: string + description: >- + A list of File IDs that the vector store should use + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Key-value attributes to store with the files + chunking_strategy: + $ref: '#/components/schemas/VectorStoreChunkingStrategy' + description: >- + (Optional) The chunking strategy used to chunk the file(s). Defaults to + auto + additionalProperties: false + required: + - file_ids + title: >- + OpenAICreateVectorStoreFileBatchRequestWithExtraBody + description: >- + Request to create a vector store file batch with extra_body support. + VectorStoreFileBatchObject: + type: object + properties: + id: + type: string + description: Unique identifier for the file batch + object: + type: string + default: vector_store.file_batch + description: >- + Object type identifier, always "vector_store.file_batch" + created_at: + type: integer + description: >- + Timestamp when the file batch was created + vector_store_id: + type: string + description: >- + ID of the vector store containing the file batch + status: + $ref: '#/components/schemas/VectorStoreFileStatus' + description: >- + Current processing status of the file batch + file_counts: + $ref: '#/components/schemas/VectorStoreFileCounts' + description: >- + File processing status counts for the batch + additionalProperties: false + required: + - id + - object + - created_at + - vector_store_id + - status + - file_counts + title: VectorStoreFileBatchObject + description: OpenAI Vector Store File Batch object. + VectorStoreFileStatus: + oneOf: + - type: string + const: completed + - type: string + const: in_progress + - type: string + const: cancelled + - type: string + const: failed + VectorStoreFileLastError: + type: object + properties: + code: + oneOf: + - type: string + const: server_error + - type: string + const: rate_limit_exceeded + description: >- + Error code indicating the type of failure + message: + type: string + description: >- + Human-readable error message describing the failure + additionalProperties: false + required: + - code + - message + title: VectorStoreFileLastError + description: >- + Error information for failed vector store file processing. + VectorStoreFileObject: + type: object + properties: + id: + type: string + description: Unique identifier for the file + object: + type: string + default: vector_store.file + description: >- + Object type identifier, always "vector_store.file" + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Key-value attributes associated with the file + chunking_strategy: + oneOf: + - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' + - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' + discriminator: + propertyName: type + mapping: + auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' + static: '#/components/schemas/VectorStoreChunkingStrategyStatic' + description: >- + Strategy used for splitting the file into chunks + created_at: + type: integer + description: >- + Timestamp when the file was added to the vector store + last_error: + $ref: '#/components/schemas/VectorStoreFileLastError' + description: >- + (Optional) Error information if file processing failed + status: + $ref: '#/components/schemas/VectorStoreFileStatus' + description: Current processing status of the file + usage_bytes: + type: integer + default: 0 + description: Storage space used by this file in bytes + vector_store_id: + type: string + description: >- + ID of the vector store containing this file + additionalProperties: false + required: + - id + - object + - attributes + - chunking_strategy + - created_at + - status + - usage_bytes + - vector_store_id + title: VectorStoreFileObject + description: OpenAI Vector Store File object. + VectorStoreFilesListInBatchResponse: + type: object + properties: + object: + type: string + default: list + description: Object type identifier, always "list" + data: + type: array + items: + $ref: '#/components/schemas/VectorStoreFileObject' + description: >- + List of vector store file objects in the batch + first_id: + type: string + description: >- + (Optional) ID of the first file in the list for pagination + last_id: + type: string + description: >- + (Optional) ID of the last file in the list for pagination + has_more: + type: boolean + default: false + description: >- + Whether there are more files available beyond this page + additionalProperties: false + required: + - object + - data + - has_more + title: VectorStoreFilesListInBatchResponse + description: >- + Response from listing files in a vector store file batch. + VectorStoreListFilesResponse: + type: object + properties: + object: + type: string + default: list + description: Object type identifier, always "list" + data: + type: array + items: + $ref: '#/components/schemas/VectorStoreFileObject' + description: List of vector store file objects + first_id: + type: string + description: >- + (Optional) ID of the first file in the list for pagination + last_id: + type: string + description: >- + (Optional) ID of the last file in the list for pagination + has_more: + type: boolean + default: false + description: >- + Whether there are more files available beyond this page + additionalProperties: false + required: + - object + - data + - has_more + title: VectorStoreListFilesResponse + description: >- + Response from listing files in a vector store. + OpenaiAttachFileToVectorStoreRequest: + type: object + properties: + file_id: + type: string + description: >- + The ID of the file to attach to the vector store. + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The key-value attributes stored with the file, which can be used for filtering. + chunking_strategy: + $ref: '#/components/schemas/VectorStoreChunkingStrategy' + description: >- + The chunking strategy to use for the file. + additionalProperties: false + required: + - file_id + title: OpenaiAttachFileToVectorStoreRequest + OpenaiUpdateVectorStoreFileRequest: + type: object + properties: + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The updated key-value attributes to store with the file. + additionalProperties: false + required: + - attributes + title: OpenaiUpdateVectorStoreFileRequest + VectorStoreFileDeleteResponse: + type: object + properties: + id: + type: string + description: Unique identifier of the deleted file + object: + type: string + default: vector_store.file.deleted + description: >- + Object type identifier for the deletion response + deleted: + type: boolean + default: true + description: >- + Whether the deletion operation was successful + additionalProperties: false + required: + - id + - object + - deleted + title: VectorStoreFileDeleteResponse + description: >- + Response from deleting a vector store file. + VectorStoreContent: + type: object + properties: + type: + type: string + const: text + description: >- + Content type, currently only "text" is supported + text: + type: string + description: The actual text content + additionalProperties: false + required: + - type + - text + title: VectorStoreContent + description: >- + Content item from a vector store file or search result. + VectorStoreFileContentsResponse: + type: object + properties: + file_id: + type: string + description: Unique identifier for the file + filename: + type: string + description: Name of the file + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Key-value attributes associated with the file + content: + type: array + items: + $ref: '#/components/schemas/VectorStoreContent' + description: List of content items from the file + additionalProperties: false + required: + - file_id + - filename + - attributes + - content + title: VectorStoreFileContentsResponse + description: >- + Response from retrieving the contents of a vector store file. + OpenaiSearchVectorStoreRequest: + type: object + properties: + query: + oneOf: + - type: string + - type: array + items: + type: string + description: >- + The query string or array for performing the search. + filters: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + Filters based on file attributes to narrow the search results. + max_num_results: + type: integer + description: >- + Maximum number of results to return (1 to 50 inclusive, default 10). + ranking_options: + type: object + properties: + ranker: + type: string + description: >- + (Optional) Name of the ranking algorithm to use + score_threshold: + type: number + default: 0.0 + description: >- + (Optional) Minimum relevance score threshold for results + additionalProperties: false + description: >- + Ranking options for fine-tuning the search results. + rewrite_query: + type: boolean + description: >- + Whether to rewrite the natural language query for vector search (default + false) + search_mode: + type: string + description: >- + The search mode to use - "keyword", "vector", or "hybrid" (default "vector") + additionalProperties: false + required: + - query + title: OpenaiSearchVectorStoreRequest + VectorStoreSearchResponse: + type: object + properties: + file_id: + type: string + description: >- + Unique identifier of the file containing the result + filename: + type: string + description: Name of the file containing the result + score: + type: number + description: Relevance score for this search result + attributes: + type: object + additionalProperties: + oneOf: + - type: string + - type: number + - type: boolean + description: >- + (Optional) Key-value attributes associated with the file + content: + type: array + items: + $ref: '#/components/schemas/VectorStoreContent' + description: >- + List of content items matching the search query + additionalProperties: false + required: + - file_id + - filename + - score + - content + title: VectorStoreSearchResponse + description: Response from searching a vector store. + VectorStoreSearchResponsePage: + type: object + properties: + object: + type: string + default: vector_store.search_results.page + description: >- + Object type identifier for the search results page + search_query: + type: string + description: >- + The original search query that was executed + data: + type: array + items: + $ref: '#/components/schemas/VectorStoreSearchResponse' + description: List of search result objects + has_more: + type: boolean + default: false + description: >- + Whether there are more results available beyond this page + next_page: + type: string + description: >- + (Optional) Token for retrieving the next page of results + additionalProperties: false + required: + - object + - search_query + - data + - has_more + title: VectorStoreSearchResponsePage + description: >- + Paginated response from searching a vector store. + VersionInfo: + type: object + properties: + version: + type: string + description: Version number of the service + additionalProperties: false + required: + - version + title: VersionInfo + description: Version information for the service. + AppendRowsRequest: + type: object + properties: + rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The rows to append to the dataset. + additionalProperties: false + required: + - rows + title: AppendRowsRequest + PaginatedResponse: + type: object + properties: + data: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The list of items for the current page + has_more: + type: boolean + description: >- + Whether there are more items available after this set + url: + type: string + description: The URL for accessing this list + additionalProperties: false + required: + - data + - has_more + title: PaginatedResponse + description: >- + A generic paginated response that follows a simple format. + Dataset: + type: object + properties: + identifier: + type: string + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + enum: + - model + - shield + - vector_db + - dataset + - scoring_function + - benchmark + - tool + - tool_group + - prompt + const: dataset + default: dataset + description: >- + Type of resource, always 'dataset' for datasets + purpose: + type: string + enum: + - post-training/messages + - eval/question-answer + - eval/messages-answer + description: >- + Purpose of the dataset indicating its intended use + source: + oneOf: + - $ref: '#/components/schemas/URIDataSource' + - $ref: '#/components/schemas/RowsDataSource' + discriminator: + propertyName: type + mapping: + uri: '#/components/schemas/URIDataSource' + rows: '#/components/schemas/RowsDataSource' + description: >- + Data source configuration for the dataset + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Additional metadata for the dataset + additionalProperties: false + required: + - identifier + - provider_id + - type + - purpose + - source + - metadata + title: Dataset + description: >- + Dataset resource for storing and accessing training or evaluation data. + RowsDataSource: + type: object + properties: + type: + type: string + const: rows + default: rows + rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The dataset is stored in rows. E.g. - [ {"messages": [{"role": "user", + "content": "Hello, world!"}, {"role": "assistant", "content": "Hello, + world!"}]} ] + additionalProperties: false + required: + - type + - rows + title: RowsDataSource + description: A dataset stored in rows. + URIDataSource: + type: object + properties: + type: + type: string + const: uri + default: uri + uri: + type: string + description: >- + The dataset can be obtained from a URI. E.g. - "https://mywebsite.com/mydata.jsonl" + - "lsfs://mydata.jsonl" - "data:csv;base64,{base64_content}" + additionalProperties: false + required: + - type + - uri + title: URIDataSource + description: >- + A dataset that can be obtained from a URI. + ListDatasetsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Dataset' + description: List of datasets + additionalProperties: false + required: + - data + title: ListDatasetsResponse + description: Response from listing datasets. + DataSource: + oneOf: + - $ref: '#/components/schemas/URIDataSource' + - $ref: '#/components/schemas/RowsDataSource' + discriminator: + propertyName: type + mapping: + uri: '#/components/schemas/URIDataSource' + rows: '#/components/schemas/RowsDataSource' + RegisterDatasetRequest: + type: object + properties: + purpose: + type: string + enum: + - post-training/messages + - eval/question-answer + - eval/messages-answer + description: >- + The purpose of the dataset. One of: - "post-training/messages": The dataset + contains a messages column with list of messages for post-training. { + "messages": [ {"role": "user", "content": "Hello, world!"}, {"role": "assistant", + "content": "Hello, world!"}, ] } - "eval/question-answer": The dataset + contains a question column and an answer column for evaluation. { "question": + "What is the capital of France?", "answer": "Paris" } - "eval/messages-answer": + The dataset contains a messages column with list of messages and an answer + column for evaluation. { "messages": [ {"role": "user", "content": "Hello, + my name is John Doe."}, {"role": "assistant", "content": "Hello, John + Doe. How can I help you today?"}, {"role": "user", "content": "What's + my name?"}, ], "answer": "John Doe" } + source: + $ref: '#/components/schemas/DataSource' + description: >- + The data source of the dataset. Ensure that the data source schema is + compatible with the purpose of the dataset. Examples: - { "type": "uri", + "uri": "https://mywebsite.com/mydata.jsonl" } - { "type": "uri", "uri": + "lsfs://mydata.jsonl" } - { "type": "uri", "uri": "data:csv;base64,{base64_content}" + } - { "type": "uri", "uri": "huggingface://llamastack/simpleqa?split=train" + } - { "type": "rows", "rows": [ { "messages": [ {"role": "user", "content": + "Hello, world!"}, {"role": "assistant", "content": "Hello, world!"}, ] + } ] } + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The metadata for the dataset. - E.g. {"description": "My dataset"}. + dataset_id: + type: string + description: >- + The ID of the dataset. If not provided, an ID will be generated. + additionalProperties: false + required: + - purpose + - source + title: RegisterDatasetRequest + AgentConfig: + type: object + properties: + sampling_params: + $ref: '#/components/schemas/SamplingParams' + input_shields: + type: array + items: + type: string + output_shields: + type: array + items: + type: string + toolgroups: + type: array + items: + $ref: '#/components/schemas/AgentTool' + client_tools: + type: array + items: + $ref: '#/components/schemas/ToolDef' + tool_choice: + type: string + enum: + - auto + - required + - none + title: ToolChoice + description: >- + Whether tool use is required or automatic. This is a hint to the model + which may not be followed. It depends on the Instruction Following capabilities + of the model. + deprecated: true + tool_prompt_format: + type: string + enum: + - json + - function_tag + - python_list + title: ToolPromptFormat + description: >- + Prompt format for calling custom / zero shot tools. + deprecated: true + tool_config: + $ref: '#/components/schemas/ToolConfig' + max_infer_iters: + type: integer + default: 10 + model: + type: string + description: >- + The model identifier to use for the agent + instructions: + type: string + description: The system instructions for the agent + name: + type: string + description: >- + Optional name for the agent, used in telemetry and identification + enable_session_persistence: + type: boolean + default: false + description: >- + Optional flag indicating whether session data has to be persisted + response_format: + $ref: '#/components/schemas/ResponseFormat' + description: Optional response format configuration + additionalProperties: false + required: + - model + - instructions + title: AgentConfig + description: Configuration for an agent. + AgentTool: + oneOf: + - type: string + - type: object + properties: + name: + type: string + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - name + - args + title: AgentToolGroupWithArgs + GrammarResponseFormat: + type: object + properties: + type: + type: string + enum: + - json_schema + - grammar + description: >- + Must be "grammar" to identify this format type + const: grammar + default: grammar + bnf: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The BNF grammar specification the response should conform to + additionalProperties: false + required: + - type + - bnf + title: GrammarResponseFormat + description: >- + Configuration for grammar-guided response generation. + GreedySamplingStrategy: + type: object + properties: + type: + type: string + const: greedy + default: greedy + description: >- + Must be "greedy" to identify this sampling strategy + additionalProperties: false + required: + - type + title: GreedySamplingStrategy + description: >- + Greedy sampling strategy that selects the highest probability token at each + step. + JsonSchemaResponseFormat: + type: object + properties: + type: + type: string + enum: + - json_schema + - grammar + description: >- + Must be "json_schema" to identify this format type + const: json_schema + default: json_schema + json_schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + The JSON schema the response should conform to. In a Python SDK, this + is often a `pydantic` model. + additionalProperties: false + required: + - type + - json_schema + title: JsonSchemaResponseFormat + description: >- + Configuration for JSON schema-guided response generation. + ResponseFormat: + oneOf: + - $ref: '#/components/schemas/JsonSchemaResponseFormat' + - $ref: '#/components/schemas/GrammarResponseFormat' + discriminator: + propertyName: type + mapping: + json_schema: '#/components/schemas/JsonSchemaResponseFormat' + grammar: '#/components/schemas/GrammarResponseFormat' + SamplingParams: + type: object + properties: + strategy: + oneOf: + - $ref: '#/components/schemas/GreedySamplingStrategy' + - $ref: '#/components/schemas/TopPSamplingStrategy' + - $ref: '#/components/schemas/TopKSamplingStrategy' + discriminator: + propertyName: type + mapping: + greedy: '#/components/schemas/GreedySamplingStrategy' + top_p: '#/components/schemas/TopPSamplingStrategy' + top_k: '#/components/schemas/TopKSamplingStrategy' + description: The sampling strategy. + max_tokens: + type: integer + default: 0 + description: >- + The maximum number of tokens that can be generated in the completion. + The token count of your prompt plus max_tokens cannot exceed the model's + context length. + repetition_penalty: + type: number + default: 1.0 + description: >- + Number between -2.0 and 2.0. Positive values penalize new tokens based + on whether they appear in the text so far, increasing the model's likelihood + to talk about new topics. + stop: + type: array + items: + type: string + description: >- + Up to 4 sequences where the API will stop generating further tokens. The + returned text will not contain the stop sequence. + additionalProperties: false + required: + - strategy + title: SamplingParams + description: Sampling parameters. + ToolConfig: + type: object + properties: + tool_choice: + oneOf: + - type: string + enum: + - auto + - required + - none + title: ToolChoice + description: >- + Whether tool use is required or automatic. This is a hint to the model + which may not be followed. It depends on the Instruction Following + capabilities of the model. + - type: string + default: auto + description: >- + (Optional) Whether tool use is automatic, required, or none. Can also + specify a tool name to use a specific tool. Defaults to ToolChoice.auto. + tool_prompt_format: + type: string + enum: + - json + - function_tag + - python_list + description: >- + (Optional) Instructs the model how to format tool calls. By default, Llama + Stack will attempt to use a format that is best adapted to the model. + - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. + - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a + tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python + syntax -- a list of function calls. + system_message_behavior: + type: string + enum: + - append + - replace + description: >- + (Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: + Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: + Replaces the default system prompt with the provided system message. The + system message can include the string '{{function_definitions}}' to indicate + where the function definitions should be inserted. + default: append + additionalProperties: false + title: ToolConfig + description: Configuration for tool use. + TopKSamplingStrategy: + type: object + properties: + type: + type: string + const: top_k + default: top_k + description: >- + Must be "top_k" to identify this sampling strategy + top_k: + type: integer + description: >- + Number of top tokens to consider for sampling. Must be at least 1 + additionalProperties: false + required: + - type + - top_k + title: TopKSamplingStrategy + description: >- + Top-k sampling strategy that restricts sampling to the k most likely tokens. + TopPSamplingStrategy: + type: object + properties: + type: + type: string + const: top_p + default: top_p + description: >- + Must be "top_p" to identify this sampling strategy + temperature: + type: number + description: >- + Controls randomness in sampling. Higher values increase randomness + top_p: + type: number + default: 0.95 + description: >- + Cumulative probability threshold for nucleus sampling. Defaults to 0.95 + additionalProperties: false + required: + - type + title: TopPSamplingStrategy + description: >- + Top-p (nucleus) sampling strategy that samples from the smallest set of tokens + with cumulative probability >= p. + CreateAgentRequest: + type: object + properties: + agent_config: + $ref: '#/components/schemas/AgentConfig' + description: The configuration for the agent. + additionalProperties: false + required: + - agent_config + title: CreateAgentRequest + AgentCreateResponse: + type: object + properties: + agent_id: + type: string + description: Unique identifier for the created agent + additionalProperties: false + required: + - agent_id + title: AgentCreateResponse + description: >- + Response returned when creating a new agent. + Agent: + type: object + properties: + agent_id: + type: string + description: Unique identifier for the agent + agent_config: + $ref: '#/components/schemas/AgentConfig' + description: Configuration settings for the agent + created_at: + type: string + format: date-time + description: Timestamp when the agent was created + additionalProperties: false + required: + - agent_id + - agent_config + - created_at + title: Agent + description: >- + An agent instance with configuration and metadata. + CreateAgentSessionRequest: + type: object + properties: + session_name: + type: string + description: The name of the session to create. + additionalProperties: false + required: + - session_name + title: CreateAgentSessionRequest + AgentSessionCreateResponse: + type: object + properties: + session_id: + type: string + description: >- + Unique identifier for the created session + additionalProperties: false + required: + - session_id + title: AgentSessionCreateResponse + description: >- + Response returned when creating a new agent session. + InferenceStep: + type: object + properties: + turn_id: + type: string + description: The ID of the turn. + step_id: + type: string + description: The ID of the step. + started_at: + type: string + format: date-time + description: The time the step started. + completed_at: + type: string + format: date-time + description: The time the step completed. + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + title: StepType + description: Type of the step in an agent turn. + const: inference + default: inference + model_response: + $ref: '#/components/schemas/CompletionMessage' + description: The response from the LLM. + additionalProperties: false + required: + - turn_id + - step_id + - step_type + - model_response + title: InferenceStep + description: An inference step in an agent turn. + MemoryRetrievalStep: + type: object + properties: + turn_id: + type: string + description: The ID of the turn. + step_id: + type: string + description: The ID of the step. + started_at: + type: string + format: date-time + description: The time the step started. + completed_at: + type: string + format: date-time + description: The time the step completed. + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + title: StepType + description: Type of the step in an agent turn. + const: memory_retrieval + default: memory_retrieval + vector_db_ids: + type: string + description: >- + The IDs of the vector databases to retrieve context from. + inserted_context: + $ref: '#/components/schemas/InterleavedContent' + description: >- + The context retrieved from the vector databases. + additionalProperties: false + required: + - turn_id + - step_id + - step_type + - vector_db_ids + - inserted_context + title: MemoryRetrievalStep + description: >- + A memory retrieval step in an agent turn. + Session: + type: object + properties: + session_id: + type: string + description: >- + Unique identifier for the conversation session + session_name: + type: string + description: Human-readable name for the session + turns: + type: array + items: + $ref: '#/components/schemas/Turn' + description: >- + List of all turns that have occurred in this session + started_at: + type: string + format: date-time + description: Timestamp when the session was created + additionalProperties: false + required: + - session_id + - session_name + - turns + - started_at + title: Session + description: >- + A single session of an interaction with an Agentic System. + ShieldCallStep: + type: object + properties: + turn_id: + type: string + description: The ID of the turn. + step_id: + type: string + description: The ID of the step. + started_at: + type: string + format: date-time + description: The time the step started. + completed_at: + type: string + format: date-time + description: The time the step completed. + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + title: StepType + description: Type of the step in an agent turn. + const: shield_call + default: shield_call + violation: + $ref: '#/components/schemas/SafetyViolation' + description: The violation from the shield call. + additionalProperties: false + required: + - turn_id + - step_id + - step_type + title: ShieldCallStep + description: A shield call step in an agent turn. + ToolExecutionStep: + type: object + properties: + turn_id: + type: string + description: The ID of the turn. + step_id: + type: string + description: The ID of the step. + started_at: + type: string + format: date-time + description: The time the step started. + completed_at: + type: string + format: date-time + description: The time the step completed. + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + title: StepType + description: Type of the step in an agent turn. + const: tool_execution + default: tool_execution + tool_calls: + type: array + items: + $ref: '#/components/schemas/ToolCall' + description: The tool calls to execute. + tool_responses: + type: array + items: + $ref: '#/components/schemas/ToolResponse' + description: The tool responses from the tool calls. + additionalProperties: false + required: + - turn_id + - step_id + - step_type + - tool_calls + - tool_responses + title: ToolExecutionStep + description: A tool execution step in an agent turn. + ToolResponse: + type: object + properties: + call_id: + type: string + description: >- + Unique identifier for the tool call this response is for + tool_name: + oneOf: + - type: string + enum: + - brave_search + - wolfram_alpha + - photogen + - code_interpreter + title: BuiltinTool + - type: string + description: Name of the tool that was invoked + content: + $ref: '#/components/schemas/InterleavedContent' + description: The response content from the tool + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Additional metadata about the tool response + additionalProperties: false + required: + - call_id + - tool_name + - content + title: ToolResponse + description: Response from a tool invocation. + Turn: + type: object + properties: + turn_id: + type: string + description: >- + Unique identifier for the turn within a session + session_id: + type: string + description: >- + Unique identifier for the conversation session + input_messages: + type: array + items: + oneOf: + - $ref: '#/components/schemas/UserMessage' + - $ref: '#/components/schemas/ToolResponseMessage' + description: >- + List of messages that initiated this turn + steps: + type: array + items: + oneOf: + - $ref: '#/components/schemas/InferenceStep' + - $ref: '#/components/schemas/ToolExecutionStep' + - $ref: '#/components/schemas/ShieldCallStep' + - $ref: '#/components/schemas/MemoryRetrievalStep' + discriminator: + propertyName: step_type + mapping: + inference: '#/components/schemas/InferenceStep' + tool_execution: '#/components/schemas/ToolExecutionStep' + shield_call: '#/components/schemas/ShieldCallStep' + memory_retrieval: '#/components/schemas/MemoryRetrievalStep' + description: >- + Ordered list of processing steps executed during this turn + output_message: + $ref: '#/components/schemas/CompletionMessage' + description: >- + The model's generated response containing content and metadata + output_attachments: + type: array + items: + type: object + properties: + content: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + - $ref: '#/components/schemas/URL' + description: The content of the attachment. + mime_type: + type: string + description: The MIME type of the attachment. + additionalProperties: false + required: + - content + - mime_type + title: Attachment + description: An attachment to an agent turn. + description: >- + (Optional) Files or media attached to the agent's response + started_at: + type: string + format: date-time + description: Timestamp when the turn began + completed_at: + type: string + format: date-time + description: >- + (Optional) Timestamp when the turn finished, if completed + additionalProperties: false + required: + - turn_id + - session_id + - input_messages + - steps + - output_message + - started_at + title: Turn + description: >- + A single turn in an interaction with an Agentic System. + CreateAgentTurnRequest: + type: object + properties: + messages: + type: array + items: + oneOf: + - $ref: '#/components/schemas/UserMessage' + - $ref: '#/components/schemas/ToolResponseMessage' + description: List of messages to start the turn with. + stream: + type: boolean + description: >- + (Optional) If True, generate an SSE event stream of the response. Defaults + to False. + documents: + type: array + items: + type: object + properties: + content: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + - $ref: '#/components/schemas/URL' + description: The content of the document. + mime_type: + type: string + description: The MIME type of the document. + additionalProperties: false + required: + - content + - mime_type + title: Document + description: A document to be used by an agent. + description: >- + (Optional) List of documents to create the turn with. + toolgroups: + type: array + items: + $ref: '#/components/schemas/AgentTool' + description: >- + (Optional) List of toolgroups to create the turn with, will be used in + addition to the agent's config toolgroups for the request. + tool_config: + $ref: '#/components/schemas/ToolConfig' + description: >- + (Optional) The tool configuration to create the turn with, will be used + to override the agent's tool_config. + additionalProperties: false + required: + - messages + title: CreateAgentTurnRequest + AgentTurnResponseEvent: + type: object + properties: + payload: + oneOf: + - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload' + - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload' + - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload' + - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload' + - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload' + - $ref: '#/components/schemas/AgentTurnResponseTurnAwaitingInputPayload' + discriminator: + propertyName: event_type + mapping: + step_start: '#/components/schemas/AgentTurnResponseStepStartPayload' + step_progress: '#/components/schemas/AgentTurnResponseStepProgressPayload' + step_complete: '#/components/schemas/AgentTurnResponseStepCompletePayload' + turn_start: '#/components/schemas/AgentTurnResponseTurnStartPayload' + turn_complete: '#/components/schemas/AgentTurnResponseTurnCompletePayload' + turn_awaiting_input: '#/components/schemas/AgentTurnResponseTurnAwaitingInputPayload' + description: >- + Event-specific payload containing event data + additionalProperties: false + required: + - payload + title: AgentTurnResponseEvent + description: >- + An event in an agent turn response stream. + AgentTurnResponseStepCompletePayload: + type: object + properties: + event_type: + type: string + enum: + - step_start + - step_complete + - step_progress + - turn_start + - turn_complete + - turn_awaiting_input + const: step_complete + default: step_complete + description: Type of event being reported + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + description: Type of step being executed + step_id: + type: string + description: >- + Unique identifier for the step within a turn + step_details: + oneOf: + - $ref: '#/components/schemas/InferenceStep' + - $ref: '#/components/schemas/ToolExecutionStep' + - $ref: '#/components/schemas/ShieldCallStep' + - $ref: '#/components/schemas/MemoryRetrievalStep' + discriminator: + propertyName: step_type + mapping: + inference: '#/components/schemas/InferenceStep' + tool_execution: '#/components/schemas/ToolExecutionStep' + shield_call: '#/components/schemas/ShieldCallStep' + memory_retrieval: '#/components/schemas/MemoryRetrievalStep' + description: Complete details of the executed step + additionalProperties: false + required: + - event_type + - step_type + - step_id + - step_details + title: AgentTurnResponseStepCompletePayload + description: >- + Payload for step completion events in agent turn responses. + AgentTurnResponseStepProgressPayload: + type: object + properties: + event_type: + type: string + enum: + - step_start + - step_complete + - step_progress + - turn_start + - turn_complete + - turn_awaiting_input + const: step_progress + default: step_progress + description: Type of event being reported + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + description: Type of step being executed + step_id: + type: string + description: >- + Unique identifier for the step within a turn + delta: + oneOf: + - $ref: '#/components/schemas/TextDelta' + - $ref: '#/components/schemas/ImageDelta' + - $ref: '#/components/schemas/ToolCallDelta' + discriminator: + propertyName: type + mapping: + text: '#/components/schemas/TextDelta' + image: '#/components/schemas/ImageDelta' + tool_call: '#/components/schemas/ToolCallDelta' + description: >- + Incremental content changes during step execution + additionalProperties: false + required: + - event_type + - step_type + - step_id + - delta + title: AgentTurnResponseStepProgressPayload + description: >- + Payload for step progress events in agent turn responses. + AgentTurnResponseStepStartPayload: + type: object + properties: + event_type: + type: string + enum: + - step_start + - step_complete + - step_progress + - turn_start + - turn_complete + - turn_awaiting_input + const: step_start + default: step_start + description: Type of event being reported + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + description: Type of step being executed + step_id: + type: string + description: >- + Unique identifier for the step within a turn + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Additional metadata for the step + additionalProperties: false + required: + - event_type + - step_type + - step_id + title: AgentTurnResponseStepStartPayload + description: >- + Payload for step start events in agent turn responses. + AgentTurnResponseStreamChunk: + type: object + properties: + event: + $ref: '#/components/schemas/AgentTurnResponseEvent' + description: >- + Individual event in the agent turn response stream + additionalProperties: false + required: + - event + title: AgentTurnResponseStreamChunk + description: Streamed agent turn completion response. + "AgentTurnResponseTurnAwaitingInputPayload": + type: object + properties: + event_type: + type: string + enum: + - step_start + - step_complete + - step_progress + - turn_start + - turn_complete + - turn_awaiting_input + const: turn_awaiting_input + default: turn_awaiting_input + description: Type of event being reported + turn: + $ref: '#/components/schemas/Turn' + description: >- + Turn data when waiting for external tool responses + additionalProperties: false + required: + - event_type + - turn + title: >- + AgentTurnResponseTurnAwaitingInputPayload + description: >- + Payload for turn awaiting input events in agent turn responses. + AgentTurnResponseTurnCompletePayload: + type: object + properties: + event_type: + type: string + enum: + - step_start + - step_complete + - step_progress + - turn_start + - turn_complete + - turn_awaiting_input + const: turn_complete + default: turn_complete + description: Type of event being reported + turn: + $ref: '#/components/schemas/Turn' + description: >- + Complete turn data including all steps and results + additionalProperties: false + required: + - event_type + - turn + title: AgentTurnResponseTurnCompletePayload + description: >- + Payload for turn completion events in agent turn responses. + AgentTurnResponseTurnStartPayload: + type: object + properties: + event_type: + type: string + enum: + - step_start + - step_complete + - step_progress + - turn_start + - turn_complete + - turn_awaiting_input + const: turn_start + default: turn_start + description: Type of event being reported + turn_id: + type: string + description: >- + Unique identifier for the turn within a session + additionalProperties: false + required: + - event_type + - turn_id + title: AgentTurnResponseTurnStartPayload + description: >- + Payload for turn start events in agent turn responses. + ImageDelta: + type: object + properties: + type: + type: string + const: image + default: image + description: >- + Discriminator type of the delta. Always "image" + image: + type: string + contentEncoding: base64 + description: The incremental image data as bytes + additionalProperties: false + required: + - type + - image + title: ImageDelta + description: >- + An image content delta for streaming responses. + TextDelta: + type: object + properties: + type: + type: string + const: text + default: text + description: >- + Discriminator type of the delta. Always "text" + text: + type: string + description: The incremental text content + additionalProperties: false + required: + - type + - text + title: TextDelta + description: >- + A text content delta for streaming responses. + ToolCallDelta: + type: object + properties: + type: + type: string + const: tool_call + default: tool_call + description: >- + Discriminator type of the delta. Always "tool_call" + tool_call: + oneOf: + - type: string + - $ref: '#/components/schemas/ToolCall' + description: >- + Either an in-progress tool call string or the final parsed tool call + parse_status: + type: string + enum: + - started + - in_progress + - failed + - succeeded + description: Current parsing status of the tool call + additionalProperties: false + required: + - type + - tool_call + - parse_status + title: ToolCallDelta + description: >- + A tool call content delta for streaming responses. + ResumeAgentTurnRequest: + type: object + properties: + tool_responses: + type: array + items: + $ref: '#/components/schemas/ToolResponse' + description: >- + The tool call responses to resume the turn with. + stream: + type: boolean + description: Whether to stream the response. + additionalProperties: false + required: + - tool_responses + title: ResumeAgentTurnRequest + AgentStepResponse: + type: object + properties: + step: + oneOf: + - $ref: '#/components/schemas/InferenceStep' + - $ref: '#/components/schemas/ToolExecutionStep' + - $ref: '#/components/schemas/ShieldCallStep' + - $ref: '#/components/schemas/MemoryRetrievalStep' + discriminator: + propertyName: step_type + mapping: + inference: '#/components/schemas/InferenceStep' + tool_execution: '#/components/schemas/ToolExecutionStep' + shield_call: '#/components/schemas/ShieldCallStep' + memory_retrieval: '#/components/schemas/MemoryRetrievalStep' + description: >- + The complete step data and execution details + additionalProperties: false + required: + - step + title: AgentStepResponse + description: >- + Response containing details of a specific agent step. + Benchmark: + type: object + properties: + identifier: + type: string + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + enum: + - model + - shield + - vector_db + - dataset + - scoring_function + - benchmark + - tool + - tool_group + - prompt + const: benchmark + default: benchmark + description: The resource type, always benchmark + dataset_id: + type: string + description: >- + Identifier of the dataset to use for the benchmark evaluation + scoring_functions: + type: array + items: + type: string + description: >- + List of scoring function identifiers to apply during evaluation + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Metadata for this evaluation task + additionalProperties: false + required: + - identifier + - provider_id + - type + - dataset_id + - scoring_functions + - metadata + title: Benchmark + description: >- + A benchmark resource for evaluating model performance. + ListBenchmarksResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Benchmark' + additionalProperties: false + required: + - data + title: ListBenchmarksResponse + RegisterBenchmarkRequest: + type: object + properties: + benchmark_id: + type: string + description: The ID of the benchmark to register. + dataset_id: + type: string + description: >- + The ID of the dataset to use for the benchmark. + scoring_functions: + type: array + items: + type: string + description: >- + The scoring functions to use for the benchmark. + provider_benchmark_id: + type: string + description: >- + The ID of the provider benchmark to use for the benchmark. + provider_id: + type: string + description: >- + The ID of the provider to use for the benchmark. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The metadata to use for the benchmark. + additionalProperties: false + required: + - benchmark_id + - dataset_id + - scoring_functions + title: RegisterBenchmarkRequest + AgentCandidate: + type: object + properties: + type: + type: string + const: agent + default: agent + config: + $ref: '#/components/schemas/AgentConfig' + description: >- + The configuration for the agent candidate. + additionalProperties: false + required: + - type + - config + title: AgentCandidate + description: An agent candidate for evaluation. + BenchmarkConfig: + type: object + properties: + eval_candidate: + oneOf: + - $ref: '#/components/schemas/ModelCandidate' + - $ref: '#/components/schemas/AgentCandidate' + discriminator: + propertyName: type + mapping: + model: '#/components/schemas/ModelCandidate' + agent: '#/components/schemas/AgentCandidate' + description: The candidate to evaluate. + scoring_params: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringFnParams' + description: >- + Map between scoring function id and parameters for each scoring function + you want to run + num_examples: + type: integer + description: >- + (Optional) The number of examples to evaluate. If not provided, all examples + in the dataset will be evaluated + additionalProperties: false + required: + - eval_candidate + - scoring_params + title: BenchmarkConfig + description: >- + A benchmark configuration for evaluation. + ModelCandidate: + type: object + properties: + type: + type: string + const: model + default: model + model: + type: string + description: The model ID to evaluate. + sampling_params: + $ref: '#/components/schemas/SamplingParams' + description: The sampling parameters for the model. + system_message: + $ref: '#/components/schemas/SystemMessage' + description: >- + (Optional) The system message providing instructions or context to the + model. + additionalProperties: false + required: + - type + - model + - sampling_params + title: ModelCandidate + description: A model candidate for evaluation. + EvaluateRowsRequest: + type: object + properties: + input_rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The rows to evaluate. + scoring_functions: + type: array + items: + type: string + description: >- + The scoring functions to use for the evaluation. + benchmark_config: + $ref: '#/components/schemas/BenchmarkConfig' + description: The configuration for the benchmark. + additionalProperties: false + required: + - input_rows + - scoring_functions + - benchmark_config + title: EvaluateRowsRequest + EvaluateResponse: + type: object + properties: + generations: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The generations from the evaluation. + scores: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringResult' + description: The scores from the evaluation. + additionalProperties: false + required: + - generations + - scores + title: EvaluateResponse + description: The response from an evaluation. + RunEvalRequest: + type: object + properties: + benchmark_config: + $ref: '#/components/schemas/BenchmarkConfig' + description: The configuration for the benchmark. + additionalProperties: false + required: + - benchmark_config + title: RunEvalRequest + Job: + type: object + properties: + job_id: + type: string + description: Unique identifier for the job + status: + type: string + enum: + - completed + - in_progress + - failed + - scheduled + - cancelled + description: Current execution status of the job + additionalProperties: false + required: + - job_id + - status + title: Job + description: >- + A job execution instance with status tracking. + RerankRequest: + type: object + properties: + model: + type: string + description: >- + The identifier of the reranking model to use. + query: + oneOf: + - type: string + - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' + description: >- + The search query to rank items against. Can be a string, text content + part, or image content part. The input must not exceed the model's max + input token length. + items: + type: array + items: + oneOf: + - type: string + - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' + - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' + description: >- + List of items to rerank. Each item can be a string, text content part, + or image content part. Each input must not exceed the model's max input + token length. + max_num_results: + type: integer + description: >- + (Optional) Maximum number of results to return. Default: returns all. + additionalProperties: false + required: + - model + - query + - items + title: RerankRequest + RerankData: + type: object + properties: + index: + type: integer + description: >- + The original index of the document in the input list + relevance_score: + type: number + description: >- + The relevance score from the model output. Values are inverted when applicable + so that higher scores indicate greater relevance. + additionalProperties: false + required: + - index + - relevance_score + title: RerankData + description: >- + A single rerank result from a reranking response. + RerankResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/RerankData' + description: >- + List of rerank result objects, sorted by relevance score (descending) + additionalProperties: false + required: + - data + title: RerankResponse + description: Response from a reranking request. + Checkpoint: + type: object + properties: + identifier: + type: string + description: Unique identifier for the checkpoint + created_at: + type: string + format: date-time + description: >- + Timestamp when the checkpoint was created + epoch: + type: integer + description: >- + Training epoch when the checkpoint was saved + post_training_job_id: + type: string + description: >- + Identifier of the training job that created this checkpoint + path: + type: string + description: >- + File system path where the checkpoint is stored + training_metrics: + $ref: '#/components/schemas/PostTrainingMetric' + description: >- + (Optional) Training metrics associated with this checkpoint + additionalProperties: false + required: + - identifier + - created_at + - epoch + - post_training_job_id + - path + title: Checkpoint + description: Checkpoint created during training runs. + PostTrainingJobArtifactsResponse: + type: object + properties: + job_uuid: + type: string + description: Unique identifier for the training job + checkpoints: + type: array + items: + $ref: '#/components/schemas/Checkpoint' + description: >- + List of model checkpoints created during training + additionalProperties: false + required: + - job_uuid + - checkpoints + title: PostTrainingJobArtifactsResponse + description: Artifacts of a finetuning job. + PostTrainingMetric: + type: object + properties: + epoch: + type: integer + description: Training epoch number + train_loss: + type: number + description: Loss value on the training dataset + validation_loss: + type: number + description: Loss value on the validation dataset + perplexity: + type: number + description: >- + Perplexity metric indicating model confidence + additionalProperties: false + required: + - epoch + - train_loss + - validation_loss + - perplexity + title: PostTrainingMetric + description: >- + Training metrics captured during post-training jobs. + CancelTrainingJobRequest: + type: object + properties: + job_uuid: + type: string + description: The UUID of the job to cancel. + additionalProperties: false + required: + - job_uuid + title: CancelTrainingJobRequest + PostTrainingJobStatusResponse: + type: object + properties: + job_uuid: + type: string + description: Unique identifier for the training job + status: + type: string + enum: + - completed + - in_progress + - failed + - scheduled + - cancelled + description: Current status of the training job + scheduled_at: + type: string + format: date-time + description: >- + (Optional) Timestamp when the job was scheduled + started_at: + type: string + format: date-time + description: >- + (Optional) Timestamp when the job execution began + completed_at: + type: string + format: date-time + description: >- + (Optional) Timestamp when the job finished, if completed + resources_allocated: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + (Optional) Information about computational resources allocated to the + job + checkpoints: + type: array + items: + $ref: '#/components/schemas/Checkpoint' + description: >- + List of model checkpoints created during training + additionalProperties: false + required: + - job_uuid + - status + - checkpoints + title: PostTrainingJobStatusResponse + description: Status of a finetuning job. + ListPostTrainingJobsResponse: + type: object + properties: + data: + type: array + items: + type: object + properties: + job_uuid: + type: string + additionalProperties: false + required: + - job_uuid + title: PostTrainingJob + additionalProperties: false + required: + - data + title: ListPostTrainingJobsResponse + DPOAlignmentConfig: + type: object + properties: + beta: + type: number + description: Temperature parameter for the DPO loss + loss_type: + $ref: '#/components/schemas/DPOLossType' + default: sigmoid + description: The type of loss function to use for DPO + additionalProperties: false + required: + - beta + - loss_type + title: DPOAlignmentConfig + description: >- + Configuration for Direct Preference Optimization (DPO) alignment. + DPOLossType: + type: string + enum: + - sigmoid + - hinge + - ipo + - kto_pair + title: DPOLossType + DataConfig: + type: object + properties: + dataset_id: + type: string + description: >- + Unique identifier for the training dataset + batch_size: + type: integer + description: Number of samples per training batch + shuffle: + type: boolean + description: >- + Whether to shuffle the dataset during training + data_format: + $ref: '#/components/schemas/DatasetFormat' + description: >- + Format of the dataset (instruct or dialog) + validation_dataset_id: + type: string + description: >- + (Optional) Unique identifier for the validation dataset + packed: + type: boolean + default: false + description: >- + (Optional) Whether to pack multiple samples into a single sequence for + efficiency + train_on_input: + type: boolean + default: false + description: >- + (Optional) Whether to compute loss on input tokens as well as output tokens + additionalProperties: false + required: + - dataset_id + - batch_size + - shuffle + - data_format + title: DataConfig + description: >- + Configuration for training data and data loading. + DatasetFormat: + type: string + enum: + - instruct + - dialog + title: DatasetFormat + description: Format of the training dataset. + EfficiencyConfig: + type: object + properties: + enable_activation_checkpointing: + type: boolean + default: false + description: >- + (Optional) Whether to use activation checkpointing to reduce memory usage + enable_activation_offloading: + type: boolean + default: false + description: >- + (Optional) Whether to offload activations to CPU to save GPU memory + memory_efficient_fsdp_wrap: + type: boolean + default: false + description: >- + (Optional) Whether to use memory-efficient FSDP wrapping + fsdp_cpu_offload: + type: boolean + default: false + description: >- + (Optional) Whether to offload FSDP parameters to CPU + additionalProperties: false + title: EfficiencyConfig + description: >- + Configuration for memory and compute efficiency optimizations. + OptimizerConfig: + type: object + properties: + optimizer_type: + $ref: '#/components/schemas/OptimizerType' + description: >- + Type of optimizer to use (adam, adamw, or sgd) + lr: + type: number + description: Learning rate for the optimizer + weight_decay: + type: number + description: >- + Weight decay coefficient for regularization + num_warmup_steps: + type: integer + description: Number of steps for learning rate warmup + additionalProperties: false + required: + - optimizer_type + - lr + - weight_decay + - num_warmup_steps + title: OptimizerConfig + description: >- + Configuration parameters for the optimization algorithm. + OptimizerType: + type: string + enum: + - adam + - adamw + - sgd + title: OptimizerType + description: >- + Available optimizer algorithms for training. + TrainingConfig: + type: object + properties: + n_epochs: + type: integer + description: Number of training epochs to run + max_steps_per_epoch: + type: integer + default: 1 + description: Maximum number of steps to run per epoch + gradient_accumulation_steps: + type: integer + default: 1 + description: >- + Number of steps to accumulate gradients before updating + max_validation_steps: + type: integer + default: 1 + description: >- + (Optional) Maximum number of validation steps per epoch + data_config: + $ref: '#/components/schemas/DataConfig' + description: >- + (Optional) Configuration for data loading and formatting + optimizer_config: + $ref: '#/components/schemas/OptimizerConfig' + description: >- + (Optional) Configuration for the optimization algorithm + efficiency_config: + $ref: '#/components/schemas/EfficiencyConfig' + description: >- + (Optional) Configuration for memory and compute optimizations + dtype: + type: string + default: bf16 + description: >- + (Optional) Data type for model parameters (bf16, fp16, fp32) + additionalProperties: false + required: + - n_epochs + - max_steps_per_epoch + - gradient_accumulation_steps + title: TrainingConfig + description: >- + Comprehensive configuration for the training process. + PreferenceOptimizeRequest: + type: object + properties: + job_uuid: + type: string + description: The UUID of the job to create. + finetuned_model: + type: string + description: The model to fine-tune. + algorithm_config: + $ref: '#/components/schemas/DPOAlignmentConfig' + description: The algorithm configuration. + training_config: + $ref: '#/components/schemas/TrainingConfig' + description: The training configuration. + hyperparam_search_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The hyperparam search configuration. + logger_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The logger configuration. + additionalProperties: false + required: + - job_uuid + - finetuned_model + - algorithm_config + - training_config + - hyperparam_search_config + - logger_config + title: PreferenceOptimizeRequest + PostTrainingJob: + type: object + properties: + job_uuid: + type: string + additionalProperties: false + required: + - job_uuid + title: PostTrainingJob + AlgorithmConfig: + oneOf: + - $ref: '#/components/schemas/LoraFinetuningConfig' + - $ref: '#/components/schemas/QATFinetuningConfig' + discriminator: + propertyName: type + mapping: + LoRA: '#/components/schemas/LoraFinetuningConfig' + QAT: '#/components/schemas/QATFinetuningConfig' + LoraFinetuningConfig: + type: object + properties: + type: + type: string + const: LoRA + default: LoRA + description: Algorithm type identifier, always "LoRA" + lora_attn_modules: + type: array + items: + type: string + description: >- + List of attention module names to apply LoRA to + apply_lora_to_mlp: + type: boolean + description: Whether to apply LoRA to MLP layers + apply_lora_to_output: + type: boolean + description: >- + Whether to apply LoRA to output projection layers + rank: + type: integer + description: >- + Rank of the LoRA adaptation (lower rank = fewer parameters) + alpha: + type: integer + description: >- + LoRA scaling parameter that controls adaptation strength + use_dora: + type: boolean + default: false + description: >- + (Optional) Whether to use DoRA (Weight-Decomposed Low-Rank Adaptation) + quantize_base: + type: boolean + default: false + description: >- + (Optional) Whether to quantize the base model weights + additionalProperties: false + required: + - type + - lora_attn_modules + - apply_lora_to_mlp + - apply_lora_to_output + - rank + - alpha + title: LoraFinetuningConfig + description: >- + Configuration for Low-Rank Adaptation (LoRA) fine-tuning. + QATFinetuningConfig: + type: object + properties: + type: + type: string + const: QAT + default: QAT + description: Algorithm type identifier, always "QAT" + quantizer_name: + type: string + description: >- + Name of the quantization algorithm to use + group_size: + type: integer + description: Size of groups for grouped quantization + additionalProperties: false + required: + - type + - quantizer_name + - group_size + title: QATFinetuningConfig + description: >- + Configuration for Quantization-Aware Training (QAT) fine-tuning. + SupervisedFineTuneRequest: + type: object + properties: + job_uuid: + type: string + description: The UUID of the job to create. + training_config: + $ref: '#/components/schemas/TrainingConfig' + description: The training configuration. + hyperparam_search_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The hyperparam search configuration. + logger_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The logger configuration. + model: + type: string + description: The model to fine-tune. + checkpoint_dir: + type: string + description: The directory to save checkpoint(s) to. + algorithm_config: + $ref: '#/components/schemas/AlgorithmConfig' + description: The algorithm configuration. + additionalProperties: false + required: + - job_uuid + - training_config + - hyperparam_search_config + - logger_config + title: SupervisedFineTuneRequest + responses: + BadRequest400: + description: The request was invalid or malformed + content: + application/json: + schema: + $ref: '#/components/schemas/Error' + example: + status: 400 + title: Bad Request + detail: The request was invalid or malformed + TooManyRequests429: + description: >- + The client has sent too many requests in a given amount of time + content: + application/json: + schema: + $ref: '#/components/schemas/Error' + example: + status: 429 + title: Too Many Requests + detail: >- + You have exceeded the rate limit. Please try again later. + InternalServerError500: + description: >- + The server encountered an unexpected error + content: + application/json: + schema: + $ref: '#/components/schemas/Error' + example: + status: 500 + title: Internal Server Error + detail: >- + An unexpected error occurred. Our team has been notified. + DefaultError: + description: An unexpected error occurred + content: + application/json: + schema: + $ref: '#/components/schemas/Error' + example: + status: 0 + title: Error + detail: An unexpected error occurred +security: + - Default: [] +tags: + - name: Agents + description: >- + APIs for creating and interacting with agentic systems. + x-displayName: Agents + - name: Benchmarks + description: '' + - name: Conversations + description: >- + Protocol for conversation management operations. + x-displayName: Conversations + - name: DatasetIO + description: '' + - name: Datasets + description: '' + - name: Eval + description: >- + Llama Stack Evaluation API for running evaluations on model and agent candidates. + x-displayName: Evaluations + - name: Files + description: >- + This API is used to upload documents that can be used with other Llama Stack + APIs. + x-displayName: Files + - name: Inference + description: >- + Llama Stack Inference API for generating completions, chat completions, and + embeddings. + + + This API provides the raw interface to the underlying models. Two kinds of models + are supported: + + - LLM models: these models generate "raw" and "chat" (conversational) completions. + + - Embedding models: these models generate embeddings to be used for semantic + search. + x-displayName: Inference + - name: Inspect + description: >- + APIs for inspecting the Llama Stack service, including health status, available + API routes with methods and implementing providers. + x-displayName: Inspect + - name: Models + description: '' + - name: PostTraining (Coming Soon) + description: '' + - name: Prompts + description: >- + Protocol for prompt management operations. + x-displayName: Prompts + - name: Providers + description: >- + Providers API for inspecting, listing, and modifying providers and their configurations. + x-displayName: Providers + - name: Safety + description: OpenAI-compatible Moderations API. + x-displayName: Safety + - name: Scoring + description: '' + - name: ScoringFunctions + description: '' + - name: Shields + description: '' + - name: SyntheticDataGeneration (Coming Soon) + description: '' + - name: ToolGroups + description: '' + - name: ToolRuntime + description: '' + - name: VectorIO + description: '' +x-tagGroups: + - name: Operations + tags: + - Agents + - Benchmarks + - Conversations + - DatasetIO + - Datasets + - Eval + - Files + - Inference + - Inspect + - Models + - PostTraining (Coming Soon) + - Prompts + - Providers + - Safety + - Scoring + - ScoringFunctions + - Shields + - SyntheticDataGeneration (Coming Soon) + - ToolGroups + - ToolRuntime + - VectorIO diff --git a/docs/openapi_generator/run_openapi_generator.sh b/docs/openapi_generator/run_openapi_generator.sh index 45d00d6e7..6cffd42b0 100755 --- a/docs/openapi_generator/run_openapi_generator.sh +++ b/docs/openapi_generator/run_openapi_generator.sh @@ -30,3 +30,5 @@ fi stack_dir=$(dirname $(dirname $THIS_DIR)) PYTHONPATH=$PYTHONPATH:$stack_dir \ python -m docs.openapi_generator.generate $(dirname $THIS_DIR)/static + +cp $stack_dir/docs/static/stainless-llama-stack-spec.yaml $stack_dir/client-sdks/stainless/openapi.yml