openapi: 3.1.0 info: title: Llama Stack Specification - Deprecated APIs 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. **⚠️ DEPRECATED**: Legacy APIs that may be removed in future versions. Use for migration reference only. version: v1 servers: - url: http://any-hosted-llama-stack.com paths: /v1/models: 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: true /v1/models/{model_id}: 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: true /v1/scoring-functions: 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: true /v1/scoring-functions/{scoring_fn_id}: 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: true /v1/shields: 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: true /v1/shields/{identifier}: 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: true /v1/toolgroups: 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: true /v1/toolgroups/{toolgroup_id}: 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: true /v1beta/datasets: 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: true /v1beta/datasets/{dataset_id}: 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: true /v1alpha/eval/benchmarks: 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: true /v1alpha/eval/benchmarks/{benchmark_id}: 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: true jsonSchemaDialect: >- https://json-schema.org/draft/2020-12/schema components: schemas: AggregationFunctionType: type: string enum: - average - weighted_average - median - categorical_count - accuracy title: AggregationFunctionType description: Types of aggregation functions for scoring results. AllowedToolsFilter: properties: tool_names: anyOf: - items: type: string type: array - type: 'null' title: Tool Names type: object title: AllowedToolsFilter description: Filter configuration for restricting which MCP tools can be used. ArrayType: properties: type: type: string const: array title: Type default: array type: object title: ArrayType description: Parameter type for array values. BasicScoringFnParams: properties: type: type: string const: basic title: Type default: basic aggregation_functions: items: $ref: '#/components/schemas/AggregationFunctionType' type: array title: Aggregation Functions description: Aggregation functions to apply to the scores of each row type: object title: BasicScoringFnParams description: Parameters for basic scoring function configuration. Batch: properties: id: type: string title: Id completion_window: type: string title: Completion Window created_at: type: integer title: Created At endpoint: type: string title: Endpoint input_file_id: type: string title: Input File Id object: type: string const: batch title: Object status: type: string enum: - validating - failed - in_progress - finalizing - completed - expired - cancelling - cancelled title: Status cancelled_at: anyOf: - type: integer - type: 'null' title: Cancelled At cancelling_at: anyOf: - type: integer - type: 'null' title: Cancelling At completed_at: anyOf: - type: integer - type: 'null' title: Completed At error_file_id: anyOf: - type: string - type: 'null' title: Error File Id errors: anyOf: - $ref: '#/components/schemas/Errors' - type: 'null' expired_at: anyOf: - type: integer - type: 'null' title: Expired At expires_at: anyOf: - type: integer - type: 'null' title: Expires At failed_at: anyOf: - type: integer - type: 'null' title: Failed At finalizing_at: anyOf: - type: integer - type: 'null' title: Finalizing At in_progress_at: anyOf: - type: integer - type: 'null' title: In Progress At metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata model: anyOf: - type: string - type: 'null' title: Model output_file_id: anyOf: - type: string - type: 'null' title: Output File Id request_counts: anyOf: - $ref: '#/components/schemas/BatchRequestCounts' - type: 'null' usage: anyOf: - $ref: '#/components/schemas/BatchUsage' - type: 'null' additionalProperties: true type: object required: - id - completion_window - created_at - endpoint - input_file_id - object - status title: Batch BatchError: properties: code: anyOf: - type: string - type: 'null' title: Code line: anyOf: - type: integer - type: 'null' title: Line message: anyOf: - type: string - type: 'null' title: Message param: anyOf: - type: string - type: 'null' title: Param additionalProperties: true type: object title: BatchError BatchRequestCounts: properties: completed: type: integer title: Completed failed: type: integer title: Failed total: type: integer title: Total additionalProperties: true type: object required: - completed - failed - total title: BatchRequestCounts BatchUsage: properties: input_tokens: type: integer title: Input Tokens input_tokens_details: $ref: '#/components/schemas/InputTokensDetails' output_tokens: type: integer title: Output Tokens output_tokens_details: $ref: '#/components/schemas/OutputTokensDetails' total_tokens: type: integer title: Total Tokens additionalProperties: true type: object required: - input_tokens - input_tokens_details - output_tokens - output_tokens_details - total_tokens title: BatchUsage Benchmark: properties: identifier: type: string title: Identifier description: Unique identifier for this resource in llama stack provider_resource_id: anyOf: - type: string - type: 'null' title: Provider Resource Id description: Unique identifier for this resource in the provider provider_id: type: string title: Provider Id description: ID of the provider that owns this resource type: type: string const: benchmark title: Type default: benchmark dataset_id: type: string title: Dataset Id scoring_functions: items: type: string type: array title: Scoring Functions metadata: additionalProperties: true type: object title: Metadata description: Metadata for this evaluation task type: object required: - identifier - provider_id - dataset_id - scoring_functions title: Benchmark description: A benchmark resource for evaluating model performance. BenchmarkConfig: properties: eval_candidate: $ref: '#/components/schemas/ModelCandidate' scoring_params: additionalProperties: oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' discriminator: propertyName: type mapping: basic: '#/components/schemas/BasicScoringFnParams' llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' regex_parser: '#/components/schemas/RegexParserScoringFnParams' type: object title: Scoring Params description: Map between scoring function id and parameters for each scoring function you want to run num_examples: anyOf: - type: integer - type: 'null' title: Num Examples description: Number of examples to evaluate (useful for testing), if not provided, all examples in the dataset will be evaluated type: object required: - eval_candidate title: BenchmarkConfig description: A benchmark configuration for evaluation. Body_openai_upload_file_v1_files_post: properties: file: type: string format: binary title: File purpose: $ref: '#/components/schemas/OpenAIFilePurpose' expires_after: anyOf: - $ref: '#/components/schemas/ExpiresAfter' - type: 'null' type: object required: - file - purpose title: Body_openai_upload_file_v1_files_post Body_register_benchmark_v1alpha_eval_benchmarks_post: properties: scoring_functions: items: type: string type: array title: Scoring Functions metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata type: object required: - scoring_functions title: Body_register_benchmark_v1alpha_eval_benchmarks_post Body_register_scoring_function_v1_scoring_functions_post: properties: return_type: anyOf: - $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' title: Return Type params: anyOf: - oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' discriminator: propertyName: type mapping: basic: '#/components/schemas/BasicScoringFnParams' llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' regex_parser: '#/components/schemas/RegexParserScoringFnParams' - type: 'null' title: Params type: object required: - return_type title: Body_register_scoring_function_v1_scoring_functions_post Body_register_tool_group_v1_toolgroups_post: properties: mcp_endpoint: anyOf: - $ref: '#/components/schemas/URL' - type: 'null' args: anyOf: - additionalProperties: true type: object - type: 'null' title: Args type: object title: Body_register_tool_group_v1_toolgroups_post BooleanType: properties: type: type: string const: boolean title: Type default: boolean type: object title: BooleanType description: Parameter type for boolean values. ChatCompletionInputType: properties: type: type: string const: chat_completion_input title: Type default: chat_completion_input type: object title: ChatCompletionInputType description: Parameter type for chat completion input. Chunk-Input: properties: content: anyOf: - type: string - oneOf: - $ref: '#/components/schemas/ImageContentItem-Input' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Input' text: '#/components/schemas/TextContentItem' - items: oneOf: - $ref: '#/components/schemas/ImageContentItem-Input' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Input' text: '#/components/schemas/TextContentItem' type: array title: Content chunk_id: type: string title: Chunk Id metadata: additionalProperties: true type: object title: Metadata embedding: anyOf: - items: type: number type: array - type: 'null' title: Embedding chunk_metadata: anyOf: - $ref: '#/components/schemas/ChunkMetadata' - type: 'null' type: object required: - content - chunk_id title: Chunk description: A chunk of content that can be inserted into a vector database. Chunk-Output: properties: content: anyOf: - type: string - oneOf: - $ref: '#/components/schemas/ImageContentItem-Output' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Output' text: '#/components/schemas/TextContentItem' - items: oneOf: - $ref: '#/components/schemas/ImageContentItem-Output' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Output' text: '#/components/schemas/TextContentItem' type: array title: Content chunk_id: type: string title: Chunk Id metadata: additionalProperties: true type: object title: Metadata embedding: anyOf: - items: type: number type: array - type: 'null' title: Embedding chunk_metadata: anyOf: - $ref: '#/components/schemas/ChunkMetadata' - type: 'null' type: object required: - content - chunk_id title: Chunk description: A chunk of content that can be inserted into a vector database. ChunkMetadata: properties: chunk_id: anyOf: - type: string - type: 'null' title: Chunk Id document_id: anyOf: - type: string - type: 'null' title: Document Id source: anyOf: - type: string - type: 'null' title: Source created_timestamp: anyOf: - type: integer - type: 'null' title: Created Timestamp updated_timestamp: anyOf: - type: integer - type: 'null' title: Updated Timestamp chunk_window: anyOf: - type: string - type: 'null' title: Chunk Window chunk_tokenizer: anyOf: - type: string - type: 'null' title: Chunk Tokenizer chunk_embedding_model: anyOf: - type: string - type: 'null' title: Chunk Embedding Model chunk_embedding_dimension: anyOf: - type: integer - type: 'null' title: Chunk Embedding Dimension content_token_count: anyOf: - type: integer - type: 'null' title: Content Token Count metadata_token_count: anyOf: - type: integer - type: 'null' title: Metadata Token Count type: object 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. CompletionInputType: properties: type: type: string const: completion_input title: Type default: completion_input type: object title: CompletionInputType description: Parameter type for completion input. Conversation: properties: id: type: string title: Id description: The unique ID of the conversation. object: type: string const: conversation title: Object description: The object type, which is always conversation. default: conversation created_at: type: integer title: Created At description: The time at which the conversation was created, measured in seconds since the Unix epoch. metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata description: Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. items: anyOf: - items: additionalProperties: true type: object type: array - type: 'null' title: Items description: Initial items to include in the conversation context. You may add up to 20 items at a time. type: object required: - id - created_at title: Conversation description: OpenAI-compatible conversation object. ConversationDeletedResource: properties: id: type: string title: Id description: The deleted conversation identifier object: type: string title: Object description: Object type default: conversation.deleted deleted: type: boolean title: Deleted description: Whether the object was deleted default: true type: object required: - id title: ConversationDeletedResource description: Response for deleted conversation. ConversationItemDeletedResource: properties: id: type: string title: Id description: The deleted item identifier object: type: string title: Object description: Object type default: conversation.item.deleted deleted: type: boolean title: Deleted description: Whether the object was deleted default: true type: object required: - id title: ConversationItemDeletedResource description: Response for deleted conversation item. ConversationItemInclude: type: string enum: - web_search_call.action.sources - 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 title: ConversationItemInclude description: Specify additional output data to include in the model response. ConversationItemList: properties: object: type: string title: Object description: Object type default: list data: items: oneOf: - $ref: '#/components/schemas/OpenAIResponseMessage-Output' - $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: 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' message: '#/components/schemas/OpenAIResponseMessage-Output' web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' type: array title: Data description: List of conversation items first_id: anyOf: - type: string - type: 'null' title: First Id description: The ID of the first item in the list last_id: anyOf: - type: string - type: 'null' title: Last Id description: The ID of the last item in the list has_more: type: boolean title: Has More description: Whether there are more items available default: false type: object required: - data title: ConversationItemList description: List of conversation items with pagination. DPOAlignmentConfig: properties: beta: type: number title: Beta loss_type: $ref: '#/components/schemas/DPOLossType' default: sigmoid type: object required: - beta title: DPOAlignmentConfig description: Configuration for Direct Preference Optimization (DPO) alignment. DPOLossType: type: string enum: - sigmoid - hinge - ipo - kto_pair title: DPOLossType DataConfig: properties: dataset_id: type: string title: Dataset Id batch_size: type: integer title: Batch Size shuffle: type: boolean title: Shuffle data_format: $ref: '#/components/schemas/DatasetFormat' validation_dataset_id: anyOf: - type: string - type: 'null' title: Validation Dataset Id packed: anyOf: - type: boolean - type: 'null' title: Packed default: false train_on_input: anyOf: - type: boolean - type: 'null' title: Train On Input default: false type: object required: - dataset_id - batch_size - shuffle - data_format title: DataConfig description: Configuration for training data and data loading. Dataset: properties: identifier: type: string title: Identifier description: Unique identifier for this resource in llama stack provider_resource_id: anyOf: - type: string - type: 'null' title: Provider Resource Id description: Unique identifier for this resource in the provider provider_id: type: string title: Provider Id description: ID of the provider that owns this resource type: type: string const: dataset title: Type default: dataset purpose: $ref: '#/components/schemas/DatasetPurpose' source: oneOf: - $ref: '#/components/schemas/URIDataSource' - $ref: '#/components/schemas/RowsDataSource' title: Source discriminator: propertyName: type mapping: rows: '#/components/schemas/RowsDataSource' uri: '#/components/schemas/URIDataSource' metadata: additionalProperties: true type: object title: Metadata description: Any additional metadata for this dataset type: object required: - identifier - provider_id - purpose - source title: Dataset description: Dataset resource for storing and accessing training or evaluation data. DatasetFormat: type: string enum: - instruct - dialog title: DatasetFormat description: Format of the training dataset. DatasetPurpose: type: string enum: - post-training/messages - eval/question-answer - eval/messages-answer title: DatasetPurpose description: Purpose of the dataset. Each purpose has a required input data schema. EfficiencyConfig: properties: enable_activation_checkpointing: anyOf: - type: boolean - type: 'null' title: Enable Activation Checkpointing default: false enable_activation_offloading: anyOf: - type: boolean - type: 'null' title: Enable Activation Offloading default: false memory_efficient_fsdp_wrap: anyOf: - type: boolean - type: 'null' title: Memory Efficient Fsdp Wrap default: false fsdp_cpu_offload: anyOf: - type: boolean - type: 'null' title: Fsdp Cpu Offload default: false type: object title: EfficiencyConfig description: Configuration for memory and compute efficiency optimizations. Errors: properties: data: anyOf: - items: $ref: '#/components/schemas/BatchError' type: array - type: 'null' title: Data object: anyOf: - type: string - type: 'null' title: Object additionalProperties: true type: object title: Errors EvaluateResponse: properties: generations: items: additionalProperties: true type: object type: array title: Generations scores: additionalProperties: $ref: '#/components/schemas/ScoringResult' type: object title: Scores type: object required: - generations - scores title: EvaluateResponse description: The response from an evaluation. ExpiresAfter: properties: anchor: type: string const: created_at title: Anchor seconds: type: integer maximum: 2592000.0 minimum: 3600.0 title: Seconds type: object 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) GreedySamplingStrategy: properties: type: type: string const: greedy title: Type default: greedy type: object title: GreedySamplingStrategy description: Greedy sampling strategy that selects the highest probability token at each step. HealthInfo: properties: status: $ref: '#/components/schemas/HealthStatus' type: object required: - status title: HealthInfo description: Health status information for the service. HealthStatus: type: string enum: - OK - Error - Not Implemented title: HealthStatus ImageContentItem-Input: properties: type: type: string const: image title: Type default: image image: $ref: '#/components/schemas/_URLOrData' type: object required: - image title: ImageContentItem description: A image content item ImageContentItem-Output: properties: type: type: string const: image title: Type default: image image: $ref: '#/components/schemas/_URLOrData' type: object required: - image title: ImageContentItem description: A image content item InputTokensDetails: properties: cached_tokens: type: integer title: Cached Tokens additionalProperties: true type: object required: - cached_tokens title: InputTokensDetails Job: properties: job_id: type: string title: Job Id status: $ref: '#/components/schemas/JobStatus' type: object required: - job_id - status title: Job description: A job execution instance with status tracking. JobStatus: type: string enum: - completed - in_progress - failed - scheduled - cancelled title: JobStatus description: Status of a job execution. JsonType: properties: type: type: string const: json title: Type default: json type: object title: JsonType description: Parameter type for JSON values. LLMAsJudgeScoringFnParams: properties: type: type: string const: llm_as_judge title: Type default: llm_as_judge judge_model: type: string title: Judge Model prompt_template: anyOf: - type: string - type: 'null' title: Prompt Template judge_score_regexes: items: type: string type: array title: Judge Score Regexes description: Regexes to extract the answer from generated response aggregation_functions: items: $ref: '#/components/schemas/AggregationFunctionType' type: array title: Aggregation Functions description: Aggregation functions to apply to the scores of each row type: object required: - judge_model title: LLMAsJudgeScoringFnParams description: Parameters for LLM-as-judge scoring function configuration. ListBenchmarksResponse: properties: data: items: $ref: '#/components/schemas/Benchmark' type: array title: Data type: object required: - data title: ListBenchmarksResponse ListDatasetsResponse: properties: data: items: $ref: '#/components/schemas/Dataset' type: array title: Data type: object required: - data title: ListDatasetsResponse description: Response from listing datasets. ListPostTrainingJobsResponse: properties: data: items: $ref: '#/components/schemas/PostTrainingJob' type: array title: Data type: object required: - data title: ListPostTrainingJobsResponse ListPromptsResponse: properties: data: items: $ref: '#/components/schemas/Prompt' type: array title: Data type: object required: - data title: ListPromptsResponse description: Response model to list prompts. ListProvidersResponse: properties: data: items: $ref: '#/components/schemas/ProviderInfo' type: array title: Data type: object required: - data title: ListProvidersResponse description: Response containing a list of all available providers. ListScoringFunctionsResponse: properties: data: items: $ref: '#/components/schemas/ScoringFn' type: array title: Data type: object required: - data title: ListScoringFunctionsResponse ListShieldsResponse: properties: data: items: $ref: '#/components/schemas/Shield' type: array title: Data type: object required: - data title: ListShieldsResponse ListToolGroupsResponse: properties: data: items: $ref: '#/components/schemas/ToolGroup' type: array title: Data type: object required: - data title: ListToolGroupsResponse description: Response containing a list of tool groups. LoraFinetuningConfig: properties: type: type: string const: LoRA title: Type default: LoRA lora_attn_modules: items: type: string type: array title: Lora Attn Modules apply_lora_to_mlp: type: boolean title: Apply Lora To Mlp apply_lora_to_output: type: boolean title: Apply Lora To Output rank: type: integer title: Rank alpha: type: integer title: Alpha use_dora: anyOf: - type: boolean - type: 'null' title: Use Dora default: false quantize_base: anyOf: - type: boolean - type: 'null' title: Quantize Base default: false type: object required: - lora_attn_modules - apply_lora_to_mlp - apply_lora_to_output - rank - alpha title: LoraFinetuningConfig description: Configuration for Low-Rank Adaptation (LoRA) fine-tuning. MCPListToolsTool: properties: input_schema: additionalProperties: true type: object title: Input Schema name: type: string title: Name description: anyOf: - type: string - type: 'null' title: Description type: object required: - input_schema - name title: MCPListToolsTool description: Tool definition returned by MCP list tools operation. Model: properties: identifier: type: string title: Identifier description: Unique identifier for this resource in llama stack provider_resource_id: anyOf: - type: string - type: 'null' title: Provider Resource Id description: Unique identifier for this resource in the provider provider_id: type: string title: Provider Id description: ID of the provider that owns this resource type: type: string const: model title: Type default: model metadata: additionalProperties: true type: object title: Metadata description: Any additional metadata for this model model_type: $ref: '#/components/schemas/ModelType' default: llm type: object required: - identifier - provider_id title: Model description: A model resource representing an AI model registered in Llama Stack. ModelCandidate: properties: type: type: string const: model title: Type default: model model: type: string title: Model sampling_params: $ref: '#/components/schemas/SamplingParams' system_message: anyOf: - $ref: '#/components/schemas/SystemMessage' - type: 'null' type: object required: - model - sampling_params title: ModelCandidate description: A model candidate for evaluation. ModelType: type: string enum: - llm - embedding - rerank title: ModelType description: Enumeration of supported model types in Llama Stack. ModerationObject: properties: id: type: string title: Id model: type: string title: Model results: items: $ref: '#/components/schemas/ModerationObjectResults' type: array title: Results type: object required: - id - model - results title: ModerationObject description: A moderation object. ModerationObjectResults: properties: flagged: type: boolean title: Flagged categories: anyOf: - additionalProperties: type: boolean type: object - type: 'null' title: Categories category_applied_input_types: anyOf: - additionalProperties: items: type: string type: array type: object - type: 'null' title: Category Applied Input Types category_scores: anyOf: - additionalProperties: type: number type: object - type: 'null' title: Category Scores user_message: anyOf: - type: string - type: 'null' title: User Message metadata: additionalProperties: true type: object title: Metadata type: object required: - flagged title: ModerationObjectResults description: A moderation object. NumberType: properties: type: type: string const: number title: Type default: number type: object title: NumberType description: Parameter type for numeric values. ObjectType: properties: type: type: string const: object title: Type default: object type: object title: ObjectType description: Parameter type for object values. OpenAIAssistantMessageParam-Input: properties: role: type: string const: assistant title: Role default: assistant content: anyOf: - type: string - items: $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array - type: 'null' title: Content name: anyOf: - type: string - type: 'null' title: Name tool_calls: anyOf: - items: $ref: '#/components/schemas/OpenAIChatCompletionToolCall' type: array - type: 'null' title: Tool Calls type: object title: OpenAIAssistantMessageParam description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request. OpenAIAssistantMessageParam-Output: properties: role: type: string const: assistant title: Role default: assistant content: anyOf: - type: string - items: $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array - type: 'null' title: Content name: anyOf: - type: string - type: 'null' title: Name tool_calls: anyOf: - items: $ref: '#/components/schemas/OpenAIChatCompletionToolCall' type: array - type: 'null' title: Tool Calls type: object title: OpenAIAssistantMessageParam description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request. OpenAIChatCompletion: properties: id: type: string title: Id choices: items: $ref: '#/components/schemas/OpenAIChoice-Output' type: array title: Choices object: type: string const: chat.completion title: Object default: chat.completion created: type: integer title: Created model: type: string title: Model usage: anyOf: - $ref: '#/components/schemas/OpenAIChatCompletionUsage' - type: 'null' type: object required: - id - choices - created - model title: OpenAIChatCompletion description: Response from an OpenAI-compatible chat completion request. OpenAIChatCompletionContentPartImageParam: properties: type: type: string const: image_url title: Type default: image_url image_url: $ref: '#/components/schemas/OpenAIImageURL' type: object required: - image_url title: OpenAIChatCompletionContentPartImageParam description: Image content part for OpenAI-compatible chat completion messages. OpenAIChatCompletionContentPartTextParam: properties: type: type: string const: text title: Type default: text text: type: string title: Text type: object required: - text title: OpenAIChatCompletionContentPartTextParam description: Text content part for OpenAI-compatible chat completion messages. OpenAIChatCompletionRequestWithExtraBody: properties: model: type: string title: Model messages: items: oneOf: - $ref: '#/components/schemas/OpenAIUserMessageParam-Input' - $ref: '#/components/schemas/OpenAISystemMessageParam' - $ref: '#/components/schemas/OpenAIAssistantMessageParam-Input' - $ref: '#/components/schemas/OpenAIToolMessageParam' - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' discriminator: propertyName: role mapping: assistant: '#/components/schemas/OpenAIAssistantMessageParam-Input' developer: '#/components/schemas/OpenAIDeveloperMessageParam' system: '#/components/schemas/OpenAISystemMessageParam' tool: '#/components/schemas/OpenAIToolMessageParam' user: '#/components/schemas/OpenAIUserMessageParam-Input' type: array minItems: 1 title: Messages frequency_penalty: anyOf: - type: number - type: 'null' title: Frequency Penalty function_call: anyOf: - type: string - additionalProperties: true type: object - type: 'null' title: Function Call functions: anyOf: - items: additionalProperties: true type: object type: array - type: 'null' title: Functions logit_bias: anyOf: - additionalProperties: type: number type: object - type: 'null' title: Logit Bias logprobs: anyOf: - type: boolean - type: 'null' title: Logprobs max_completion_tokens: anyOf: - type: integer - type: 'null' title: Max Completion Tokens max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens n: anyOf: - type: integer - type: 'null' title: N parallel_tool_calls: anyOf: - type: boolean - type: 'null' title: Parallel Tool Calls presence_penalty: anyOf: - type: number - type: 'null' title: Presence Penalty response_format: anyOf: - oneOf: - $ref: '#/components/schemas/OpenAIResponseFormatText' - $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema' - $ref: '#/components/schemas/OpenAIResponseFormatJSONObject' discriminator: propertyName: type mapping: json_object: '#/components/schemas/OpenAIResponseFormatJSONObject' json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema' text: '#/components/schemas/OpenAIResponseFormatText' - type: 'null' title: Response Format seed: anyOf: - type: integer - type: 'null' title: Seed stop: anyOf: - type: string - items: type: string type: array - type: 'null' title: Stop stream: anyOf: - type: boolean - type: 'null' title: Stream stream_options: anyOf: - additionalProperties: true type: object - type: 'null' title: Stream Options temperature: anyOf: - type: number - type: 'null' title: Temperature tool_choice: anyOf: - type: string - additionalProperties: true type: object - type: 'null' title: Tool Choice tools: anyOf: - items: additionalProperties: true type: object type: array - type: 'null' title: Tools top_logprobs: anyOf: - type: integer - type: 'null' title: Top Logprobs top_p: anyOf: - type: number - type: 'null' title: Top P user: anyOf: - type: string - type: 'null' title: User additionalProperties: true type: object required: - model - messages title: OpenAIChatCompletionRequestWithExtraBody description: Request parameters for OpenAI-compatible chat completion endpoint. OpenAIChatCompletionToolCall: properties: index: anyOf: - type: integer - type: 'null' title: Index id: anyOf: - type: string - type: 'null' title: Id type: type: string const: function title: Type default: function function: anyOf: - $ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction' - type: 'null' type: object title: OpenAIChatCompletionToolCall description: Tool call specification for OpenAI-compatible chat completion responses. OpenAIChatCompletionToolCallFunction: properties: name: anyOf: - type: string - type: 'null' title: Name arguments: anyOf: - type: string - type: 'null' title: Arguments type: object title: OpenAIChatCompletionToolCallFunction description: Function call details for OpenAI-compatible tool calls. OpenAIChatCompletionUsage: properties: prompt_tokens: type: integer title: Prompt Tokens completion_tokens: type: integer title: Completion Tokens total_tokens: type: integer title: Total Tokens prompt_tokens_details: anyOf: - $ref: '#/components/schemas/OpenAIChatCompletionUsagePromptTokensDetails' - type: 'null' completion_tokens_details: anyOf: - $ref: '#/components/schemas/OpenAIChatCompletionUsageCompletionTokensDetails' - type: 'null' type: object required: - prompt_tokens - completion_tokens - total_tokens title: OpenAIChatCompletionUsage description: Usage information for OpenAI chat completion. OpenAIChatCompletionUsageCompletionTokensDetails: properties: reasoning_tokens: anyOf: - type: integer - type: 'null' title: Reasoning Tokens type: object title: OpenAIChatCompletionUsageCompletionTokensDetails description: Token details for output tokens in OpenAI chat completion usage. OpenAIChatCompletionUsagePromptTokensDetails: properties: cached_tokens: anyOf: - type: integer - type: 'null' title: Cached Tokens type: object title: OpenAIChatCompletionUsagePromptTokensDetails description: Token details for prompt tokens in OpenAI chat completion usage. OpenAIChoice-Input: properties: message: oneOf: - $ref: '#/components/schemas/OpenAIUserMessageParam-Input' - $ref: '#/components/schemas/OpenAISystemMessageParam' - $ref: '#/components/schemas/OpenAIAssistantMessageParam-Input' - $ref: '#/components/schemas/OpenAIToolMessageParam' - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' title: Message discriminator: propertyName: role mapping: assistant: '#/components/schemas/OpenAIAssistantMessageParam-Input' developer: '#/components/schemas/OpenAIDeveloperMessageParam' system: '#/components/schemas/OpenAISystemMessageParam' tool: '#/components/schemas/OpenAIToolMessageParam' user: '#/components/schemas/OpenAIUserMessageParam-Input' finish_reason: type: string title: Finish Reason index: type: integer title: Index logprobs: anyOf: - $ref: '#/components/schemas/OpenAIChoiceLogprobs-Input' - type: 'null' type: object required: - message - finish_reason - index title: OpenAIChoice description: A choice from an OpenAI-compatible chat completion response. OpenAIChoice-Output: properties: message: oneOf: - $ref: '#/components/schemas/OpenAIUserMessageParam-Output' - $ref: '#/components/schemas/OpenAISystemMessageParam' - $ref: '#/components/schemas/OpenAIAssistantMessageParam-Output' - $ref: '#/components/schemas/OpenAIToolMessageParam' - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' title: Message discriminator: propertyName: role mapping: assistant: '#/components/schemas/OpenAIAssistantMessageParam-Output' developer: '#/components/schemas/OpenAIDeveloperMessageParam' system: '#/components/schemas/OpenAISystemMessageParam' tool: '#/components/schemas/OpenAIToolMessageParam' user: '#/components/schemas/OpenAIUserMessageParam-Output' finish_reason: type: string title: Finish Reason index: type: integer title: Index logprobs: anyOf: - $ref: '#/components/schemas/OpenAIChoiceLogprobs-Output' - type: 'null' type: object required: - message - finish_reason - index title: OpenAIChoice description: A choice from an OpenAI-compatible chat completion response. OpenAIChoiceLogprobs-Input: properties: content: anyOf: - items: $ref: '#/components/schemas/OpenAITokenLogProb' type: array - type: 'null' title: Content refusal: anyOf: - items: $ref: '#/components/schemas/OpenAITokenLogProb' type: array - type: 'null' title: Refusal type: object title: OpenAIChoiceLogprobs description: The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response. OpenAIChoiceLogprobs-Output: properties: content: anyOf: - items: $ref: '#/components/schemas/OpenAITokenLogProb' type: array - type: 'null' title: Content refusal: anyOf: - items: $ref: '#/components/schemas/OpenAITokenLogProb' type: array - type: 'null' title: Refusal type: object title: OpenAIChoiceLogprobs description: The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response. OpenAICompletion: properties: id: type: string title: Id choices: items: $ref: '#/components/schemas/OpenAICompletionChoice-Output' type: array title: Choices created: type: integer title: Created model: type: string title: Model object: type: string const: text_completion title: Object default: text_completion type: object required: - id - choices - created - model title: OpenAICompletion description: |- Response from an OpenAI-compatible completion request. :id: The ID of the completion :choices: List of choices :created: The Unix timestamp in seconds when the completion was created :model: The model that was used to generate the completion :object: The object type, which will be "text_completion" OpenAICompletionChoice-Input: properties: finish_reason: type: string title: Finish Reason text: type: string title: Text index: type: integer title: Index logprobs: anyOf: - $ref: '#/components/schemas/OpenAIChoiceLogprobs-Input' - type: 'null' type: object required: - finish_reason - text - index title: OpenAICompletionChoice description: |- A choice from an OpenAI-compatible completion response. :finish_reason: The reason the model stopped generating :text: The text of the choice :index: The index of the choice :logprobs: (Optional) The log probabilities for the tokens in the choice OpenAICompletionChoice-Output: properties: finish_reason: type: string title: Finish Reason text: type: string title: Text index: type: integer title: Index logprobs: anyOf: - $ref: '#/components/schemas/OpenAIChoiceLogprobs-Output' - type: 'null' type: object required: - finish_reason - text - index title: OpenAICompletionChoice description: |- A choice from an OpenAI-compatible completion response. :finish_reason: The reason the model stopped generating :text: The text of the choice :index: The index of the choice :logprobs: (Optional) The log probabilities for the tokens in the choice OpenAICompletionRequestWithExtraBody: properties: model: type: string title: Model prompt: anyOf: - type: string - items: type: string type: array - items: type: integer type: array - items: items: type: integer type: array type: array title: Prompt best_of: anyOf: - type: integer - type: 'null' title: Best Of echo: anyOf: - type: boolean - type: 'null' title: Echo frequency_penalty: anyOf: - type: number - type: 'null' title: Frequency Penalty logit_bias: anyOf: - additionalProperties: type: number type: object - type: 'null' title: Logit Bias logprobs: anyOf: - type: boolean - type: 'null' title: Logprobs max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens n: anyOf: - type: integer - type: 'null' title: N presence_penalty: anyOf: - type: number - type: 'null' title: Presence Penalty seed: anyOf: - type: integer - type: 'null' title: Seed stop: anyOf: - type: string - items: type: string type: array - type: 'null' title: Stop stream: anyOf: - type: boolean - type: 'null' title: Stream stream_options: anyOf: - additionalProperties: true type: object - type: 'null' title: Stream Options temperature: anyOf: - type: number - type: 'null' title: Temperature top_p: anyOf: - type: number - type: 'null' title: Top P user: anyOf: - type: string - type: 'null' title: User suffix: anyOf: - type: string - type: 'null' title: Suffix additionalProperties: true type: object required: - model - prompt title: OpenAICompletionRequestWithExtraBody description: Request parameters for OpenAI-compatible completion endpoint. OpenAICompletionWithInputMessages: properties: id: type: string title: Id choices: items: $ref: '#/components/schemas/OpenAIChoice-Output' type: array title: Choices object: type: string const: chat.completion title: Object default: chat.completion created: type: integer title: Created model: type: string title: Model usage: anyOf: - $ref: '#/components/schemas/OpenAIChatCompletionUsage' - type: 'null' input_messages: items: oneOf: - $ref: '#/components/schemas/OpenAIUserMessageParam-Output' - $ref: '#/components/schemas/OpenAISystemMessageParam' - $ref: '#/components/schemas/OpenAIAssistantMessageParam-Output' - $ref: '#/components/schemas/OpenAIToolMessageParam' - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' discriminator: propertyName: role mapping: assistant: '#/components/schemas/OpenAIAssistantMessageParam-Output' developer: '#/components/schemas/OpenAIDeveloperMessageParam' system: '#/components/schemas/OpenAISystemMessageParam' tool: '#/components/schemas/OpenAIToolMessageParam' user: '#/components/schemas/OpenAIUserMessageParam-Output' type: array title: Input Messages type: object required: - id - choices - created - model - input_messages title: OpenAICompletionWithInputMessages OpenAICreateVectorStoreFileBatchRequestWithExtraBody: properties: file_ids: items: type: string type: array title: File Ids attributes: anyOf: - additionalProperties: true type: object - type: 'null' title: Attributes chunking_strategy: anyOf: - oneOf: - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' discriminator: propertyName: type mapping: auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' static: '#/components/schemas/VectorStoreChunkingStrategyStatic' - type: 'null' title: Chunking Strategy additionalProperties: true type: object required: - file_ids title: OpenAICreateVectorStoreFileBatchRequestWithExtraBody description: Request to create a vector store file batch with extra_body support. OpenAICreateVectorStoreRequestWithExtraBody: properties: name: anyOf: - type: string - type: 'null' title: Name file_ids: anyOf: - items: type: string type: array - type: 'null' title: File Ids expires_after: anyOf: - additionalProperties: true type: object - type: 'null' title: Expires After chunking_strategy: anyOf: - oneOf: - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' discriminator: propertyName: type mapping: auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' static: '#/components/schemas/VectorStoreChunkingStrategyStatic' - type: 'null' title: Chunking Strategy metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata additionalProperties: true type: object title: OpenAICreateVectorStoreRequestWithExtraBody description: Request to create a vector store with extra_body support. OpenAIDeleteResponseObject: properties: id: type: string title: Id object: type: string const: response title: Object default: response deleted: type: boolean title: Deleted default: true type: object required: - id title: OpenAIDeleteResponseObject description: Response object confirming deletion of an OpenAI response. OpenAIDeveloperMessageParam: properties: role: type: string const: developer title: Role default: developer content: anyOf: - type: string - items: $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array title: Content name: anyOf: - type: string - type: 'null' title: Name type: object required: - content title: OpenAIDeveloperMessageParam description: A message from the developer in an OpenAI-compatible chat completion request. OpenAIEmbeddingData: properties: object: type: string const: embedding title: Object default: embedding embedding: anyOf: - items: type: number type: array - type: string title: Embedding index: type: integer title: Index type: object required: - embedding - index title: OpenAIEmbeddingData description: A single embedding data object from an OpenAI-compatible embeddings response. OpenAIEmbeddingUsage: properties: prompt_tokens: type: integer title: Prompt Tokens total_tokens: type: integer title: Total Tokens type: object required: - prompt_tokens - total_tokens title: OpenAIEmbeddingUsage description: Usage information for an OpenAI-compatible embeddings response. OpenAIEmbeddingsRequestWithExtraBody: properties: model: type: string title: Model input: anyOf: - type: string - items: type: string type: array title: Input encoding_format: anyOf: - type: string - type: 'null' title: Encoding Format default: float dimensions: anyOf: - type: integer - type: 'null' title: Dimensions user: anyOf: - type: string - type: 'null' title: User additionalProperties: true type: object required: - model - input title: OpenAIEmbeddingsRequestWithExtraBody description: Request parameters for OpenAI-compatible embeddings endpoint. OpenAIEmbeddingsResponse: properties: object: type: string const: list title: Object default: list data: items: $ref: '#/components/schemas/OpenAIEmbeddingData' type: array title: Data model: type: string title: Model usage: $ref: '#/components/schemas/OpenAIEmbeddingUsage' type: object required: - data - model - usage title: OpenAIEmbeddingsResponse description: Response from an OpenAI-compatible embeddings request. OpenAIFile: properties: type: type: string const: file title: Type default: file file: $ref: '#/components/schemas/OpenAIFileFile' type: object required: - file title: OpenAIFile OpenAIFileDeleteResponse: properties: id: type: string title: Id object: type: string const: file title: Object default: file deleted: type: boolean title: Deleted type: object required: - id - deleted title: OpenAIFileDeleteResponse description: Response for deleting a file in OpenAI Files API. OpenAIFileFile: properties: file_data: anyOf: - type: string - type: 'null' title: File Data file_id: anyOf: - type: string - type: 'null' title: File Id filename: anyOf: - type: string - type: 'null' title: Filename type: object title: OpenAIFileFile OpenAIFileObject: properties: object: type: string const: file title: Object default: file id: type: string title: Id bytes: type: integer title: Bytes created_at: type: integer title: Created At expires_at: type: integer title: Expires At filename: type: string title: Filename purpose: $ref: '#/components/schemas/OpenAIFilePurpose' type: object required: - id - bytes - created_at - expires_at - filename - purpose title: OpenAIFileObject description: OpenAI File object as defined in the OpenAI Files API. OpenAIFilePurpose: type: string enum: - assistants - batch title: OpenAIFilePurpose description: Valid purpose values for OpenAI Files API. OpenAIImageURL: properties: url: type: string title: Url detail: anyOf: - type: string - type: 'null' title: Detail type: object required: - url title: OpenAIImageURL description: Image URL specification for OpenAI-compatible chat completion messages. OpenAIJSONSchema: properties: name: type: string title: Name description: anyOf: - type: string - type: 'null' title: Description strict: anyOf: - type: boolean - type: 'null' title: Strict schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Schema type: object title: OpenAIJSONSchema description: JSON schema specification for OpenAI-compatible structured response format. OpenAIListModelsResponse: properties: data: items: $ref: '#/components/schemas/OpenAIModel' type: array title: Data type: object required: - data title: OpenAIListModelsResponse OpenAIModel: properties: id: type: string title: Id object: type: string const: model title: Object default: model created: type: integer title: Created owned_by: type: string title: Owned By custom_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Custom Metadata type: object required: - id - created - owned_by title: OpenAIModel description: |- A model from OpenAI. :id: The ID of the model :object: The object type, which will be "model" :created: The Unix timestamp in seconds when the model was created :owned_by: The owner of the model :custom_metadata: Llama Stack-specific metadata including model_type, provider info, and additional metadata OpenAIResponseAnnotationCitation: properties: type: type: string const: url_citation title: Type default: url_citation end_index: type: integer title: End Index start_index: type: integer title: Start Index title: type: string title: Title url: type: string title: Url type: object required: - end_index - start_index - title - url title: OpenAIResponseAnnotationCitation description: URL citation annotation for referencing external web resources. OpenAIResponseAnnotationContainerFileCitation: properties: type: type: string const: container_file_citation title: Type default: container_file_citation container_id: type: string title: Container Id end_index: type: integer title: End Index file_id: type: string title: File Id filename: type: string title: Filename start_index: type: integer title: Start Index type: object required: - container_id - end_index - file_id - filename - start_index title: OpenAIResponseAnnotationContainerFileCitation OpenAIResponseAnnotationFileCitation: properties: type: type: string const: file_citation title: Type default: file_citation file_id: type: string title: File Id filename: type: string title: Filename index: type: integer title: Index type: object required: - file_id - filename - index title: OpenAIResponseAnnotationFileCitation description: File citation annotation for referencing specific files in response content. OpenAIResponseAnnotationFilePath: properties: type: type: string const: file_path title: Type default: file_path file_id: type: string title: File Id index: type: integer title: Index type: object required: - file_id - index title: OpenAIResponseAnnotationFilePath OpenAIResponseContentPartRefusal: properties: type: type: string const: refusal title: Type default: refusal refusal: type: string title: Refusal type: object required: - refusal title: OpenAIResponseContentPartRefusal description: Refusal content within a streamed response part. OpenAIResponseError: properties: code: type: string title: Code message: type: string title: Message type: object required: - code - message title: OpenAIResponseError description: Error details for failed OpenAI response requests. OpenAIResponseFormatJSONObject: properties: type: type: string const: json_object title: Type default: json_object type: object title: OpenAIResponseFormatJSONObject description: JSON object response format for OpenAI-compatible chat completion requests. OpenAIResponseFormatJSONSchema: properties: type: type: string const: json_schema title: Type default: json_schema json_schema: $ref: '#/components/schemas/OpenAIJSONSchema' type: object required: - json_schema title: OpenAIResponseFormatJSONSchema description: JSON schema response format for OpenAI-compatible chat completion requests. OpenAIResponseFormatText: properties: type: type: string const: text title: Type default: text type: object title: OpenAIResponseFormatText description: Text response format for OpenAI-compatible chat completion requests. OpenAIResponseInputFunctionToolCallOutput: properties: call_id: type: string title: Call Id output: type: string title: Output type: type: string const: function_call_output title: Type default: function_call_output id: anyOf: - type: string - type: 'null' title: Id status: anyOf: - type: string - type: 'null' title: Status type: object required: - call_id - output title: OpenAIResponseInputFunctionToolCallOutput description: This represents the output of a function call that gets passed back to the model. OpenAIResponseInputMessageContentFile: properties: type: type: string const: input_file title: Type default: input_file file_data: anyOf: - type: string - type: 'null' title: File Data file_id: anyOf: - type: string - type: 'null' title: File Id file_url: anyOf: - type: string - type: 'null' title: File Url filename: anyOf: - type: string - type: 'null' title: Filename type: object title: OpenAIResponseInputMessageContentFile description: File content for input messages in OpenAI response format. OpenAIResponseInputMessageContentImage: properties: detail: anyOf: - type: string const: low - type: string const: high - type: string const: auto title: Detail default: auto type: type: string const: input_image title: Type default: input_image file_id: anyOf: - type: string - type: 'null' title: File Id image_url: anyOf: - type: string - type: 'null' title: Image Url type: object title: OpenAIResponseInputMessageContentImage description: Image content for input messages in OpenAI response format. OpenAIResponseInputMessageContentText: properties: text: type: string title: Text type: type: string const: input_text title: Type default: input_text type: object required: - text title: OpenAIResponseInputMessageContentText description: Text content for input messages in OpenAI response format. OpenAIResponseInputToolFileSearch: properties: type: type: string const: file_search title: Type default: file_search vector_store_ids: items: type: string type: array title: Vector Store Ids filters: anyOf: - additionalProperties: true type: object - type: 'null' title: Filters max_num_results: anyOf: - type: integer maximum: 50.0 minimum: 1.0 - type: 'null' title: Max Num Results default: 10 ranking_options: anyOf: - $ref: '#/components/schemas/SearchRankingOptions' - type: 'null' type: object required: - vector_store_ids title: OpenAIResponseInputToolFileSearch description: File search tool configuration for OpenAI response inputs. OpenAIResponseInputToolFunction: properties: type: type: string const: function title: Type default: function name: type: string title: Name description: anyOf: - type: string - type: 'null' title: Description parameters: anyOf: - additionalProperties: true type: object - type: 'null' title: Parameters strict: anyOf: - type: boolean - type: 'null' title: Strict type: object required: - name - parameters title: OpenAIResponseInputToolFunction description: Function tool configuration for OpenAI response inputs. OpenAIResponseInputToolWebSearch: properties: type: anyOf: - type: string const: web_search - type: string const: web_search_preview - type: string const: web_search_preview_2025_03_11 - type: string const: web_search_2025_08_26 title: Type default: web_search search_context_size: anyOf: - type: string pattern: ^low|medium|high$ - type: 'null' title: Search Context Size default: medium type: object title: OpenAIResponseInputToolWebSearch description: Web search tool configuration for OpenAI response inputs. OpenAIResponseMCPApprovalRequest: properties: arguments: type: string title: Arguments id: type: string title: Id name: type: string title: Name server_label: type: string title: Server Label type: type: string const: mcp_approval_request title: Type default: mcp_approval_request type: object required: - arguments - id - name - server_label title: OpenAIResponseMCPApprovalRequest description: A request for human approval of a tool invocation. OpenAIResponseMCPApprovalResponse: properties: approval_request_id: type: string title: Approval Request Id approve: type: boolean title: Approve type: type: string const: mcp_approval_response title: Type default: mcp_approval_response id: anyOf: - type: string - type: 'null' title: Id reason: anyOf: - type: string - type: 'null' title: Reason type: object required: - approval_request_id - approve title: OpenAIResponseMCPApprovalResponse description: A response to an MCP approval request. OpenAIResponseMessage-Input: properties: content: anyOf: - type: string - items: oneOf: - $ref: '#/components/schemas/OpenAIResponseInputMessageContentText' - $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage' - $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile' discriminator: propertyName: type mapping: input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile' input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage' input_text: '#/components/schemas/OpenAIResponseInputMessageContentText' type: array - items: oneOf: - $ref: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText' - $ref: '#/components/schemas/OpenAIResponseContentPartRefusal' discriminator: propertyName: type mapping: output_text: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText' refusal: '#/components/schemas/OpenAIResponseContentPartRefusal' type: array title: Content role: anyOf: - type: string const: system - type: string const: developer - type: string const: user - type: string const: assistant title: Role type: type: string const: message title: Type default: message id: anyOf: - type: string - type: 'null' title: Id status: anyOf: - type: string - type: 'null' title: Status type: object required: - content - role 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. OpenAIResponseMessage-Output: properties: content: anyOf: - type: string - items: oneOf: - $ref: '#/components/schemas/OpenAIResponseInputMessageContentText' - $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage' - $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile' discriminator: propertyName: type mapping: input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile' input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage' input_text: '#/components/schemas/OpenAIResponseInputMessageContentText' type: array - items: oneOf: - $ref: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText' - $ref: '#/components/schemas/OpenAIResponseContentPartRefusal' discriminator: propertyName: type mapping: output_text: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText' refusal: '#/components/schemas/OpenAIResponseContentPartRefusal' type: array title: Content role: anyOf: - type: string const: system - type: string const: developer - type: string const: user - type: string const: assistant title: Role type: type: string const: message title: Type default: message id: anyOf: - type: string - type: 'null' title: Id status: anyOf: - type: string - type: 'null' title: Status type: object required: - content - role 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. OpenAIResponseObject: properties: created_at: type: integer title: Created At error: anyOf: - $ref: '#/components/schemas/OpenAIResponseError' - type: 'null' id: type: string title: Id model: type: string title: Model object: type: string const: response title: Object default: response output: items: oneOf: - $ref: '#/components/schemas/OpenAIResponseMessage-Output' - $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: file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest' mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' message: '#/components/schemas/OpenAIResponseMessage-Output' web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' type: array title: Output parallel_tool_calls: type: boolean title: Parallel Tool Calls default: false previous_response_id: anyOf: - type: string - type: 'null' title: Previous Response Id prompt: anyOf: - $ref: '#/components/schemas/OpenAIResponsePrompt' - type: 'null' status: type: string title: Status temperature: anyOf: - type: number - type: 'null' title: Temperature text: $ref: '#/components/schemas/OpenAIResponseText' default: format: type: text top_p: anyOf: - type: number - type: 'null' title: Top P tools: anyOf: - items: oneOf: - $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch' - $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch' - $ref: '#/components/schemas/OpenAIResponseInputToolFunction' - $ref: '#/components/schemas/OpenAIResponseToolMCP' discriminator: propertyName: type mapping: file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch' function: '#/components/schemas/OpenAIResponseInputToolFunction' mcp: '#/components/schemas/OpenAIResponseToolMCP' web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch' web_search_2025_08_26: '#/components/schemas/OpenAIResponseInputToolWebSearch' web_search_preview: '#/components/schemas/OpenAIResponseInputToolWebSearch' web_search_preview_2025_03_11: '#/components/schemas/OpenAIResponseInputToolWebSearch' type: array - type: 'null' title: Tools truncation: anyOf: - type: string - type: 'null' title: Truncation usage: anyOf: - $ref: '#/components/schemas/OpenAIResponseUsage' - type: 'null' instructions: anyOf: - type: string - type: 'null' title: Instructions type: object required: - created_at - id - model - output - status title: OpenAIResponseObject description: Complete OpenAI response object containing generation results and metadata. OpenAIResponseOutputMessageContentOutputText: properties: text: type: string title: Text type: type: string const: output_text title: Type default: output_text annotations: items: oneOf: - $ref: '#/components/schemas/OpenAIResponseAnnotationFileCitation' - $ref: '#/components/schemas/OpenAIResponseAnnotationCitation' - $ref: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' - $ref: '#/components/schemas/OpenAIResponseAnnotationFilePath' discriminator: propertyName: type mapping: container_file_citation: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' file_citation: '#/components/schemas/OpenAIResponseAnnotationFileCitation' file_path: '#/components/schemas/OpenAIResponseAnnotationFilePath' url_citation: '#/components/schemas/OpenAIResponseAnnotationCitation' type: array title: Annotations type: object required: - text title: OpenAIResponseOutputMessageContentOutputText OpenAIResponseOutputMessageFileSearchToolCall: properties: id: type: string title: Id queries: items: type: string type: array title: Queries status: type: string title: Status type: type: string const: file_search_call title: Type default: file_search_call results: anyOf: - items: $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCallResults' type: array - type: 'null' title: Results type: object required: - id - queries - status title: OpenAIResponseOutputMessageFileSearchToolCall description: File search tool call output message for OpenAI responses. OpenAIResponseOutputMessageFileSearchToolCallResults: properties: attributes: additionalProperties: true type: object title: Attributes file_id: type: string title: File Id filename: type: string title: Filename score: type: number title: Score text: type: string title: Text type: object required: - attributes - file_id - filename - score - text title: OpenAIResponseOutputMessageFileSearchToolCallResults description: Search results returned by the file search operation. OpenAIResponseOutputMessageFunctionToolCall: properties: call_id: type: string title: Call Id name: type: string title: Name arguments: type: string title: Arguments type: type: string const: function_call title: Type default: function_call id: anyOf: - type: string - type: 'null' title: Id status: anyOf: - type: string - type: 'null' title: Status type: object required: - call_id - name - arguments title: OpenAIResponseOutputMessageFunctionToolCall description: Function tool call output message for OpenAI responses. OpenAIResponseOutputMessageMCPCall: properties: id: type: string title: Id type: type: string const: mcp_call title: Type default: mcp_call arguments: type: string title: Arguments name: type: string title: Name server_label: type: string title: Server Label error: anyOf: - type: string - type: 'null' title: Error output: anyOf: - type: string - type: 'null' title: Output type: object required: - id - arguments - name - server_label title: OpenAIResponseOutputMessageMCPCall description: Model Context Protocol (MCP) call output message for OpenAI responses. OpenAIResponseOutputMessageMCPListTools: properties: id: type: string title: Id type: type: string const: mcp_list_tools title: Type default: mcp_list_tools server_label: type: string title: Server Label tools: items: $ref: '#/components/schemas/MCPListToolsTool' type: array title: Tools type: object required: - id - server_label - tools title: OpenAIResponseOutputMessageMCPListTools description: MCP list tools output message containing available tools from an MCP server. OpenAIResponseOutputMessageWebSearchToolCall: properties: id: type: string title: Id status: type: string title: Status type: type: string const: web_search_call title: Type default: web_search_call type: object required: - id - status title: OpenAIResponseOutputMessageWebSearchToolCall description: Web search tool call output message for OpenAI responses. OpenAIResponsePrompt: properties: id: type: string title: Id variables: anyOf: - additionalProperties: oneOf: - $ref: '#/components/schemas/OpenAIResponseInputMessageContentText' - $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage' - $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile' discriminator: propertyName: type mapping: input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile' input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage' input_text: '#/components/schemas/OpenAIResponseInputMessageContentText' type: object - type: 'null' title: Variables version: anyOf: - type: string - type: 'null' title: Version type: object required: - id title: OpenAIResponsePrompt description: OpenAI compatible Prompt object that is used in OpenAI responses. OpenAIResponseText: properties: format: anyOf: - $ref: '#/components/schemas/OpenAIResponseTextFormat' - type: 'null' type: object title: OpenAIResponseText description: Text response configuration for OpenAI responses. OpenAIResponseTextFormat: properties: type: anyOf: - type: string const: text - type: string const: json_schema - type: string const: json_object title: Type name: anyOf: - type: string - type: 'null' title: Name schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Schema description: anyOf: - type: string - type: 'null' title: Description strict: anyOf: - type: boolean - type: 'null' title: Strict type: object title: OpenAIResponseTextFormat description: Configuration for Responses API text format. OpenAIResponseToolMCP: properties: type: type: string const: mcp title: Type default: mcp server_label: type: string title: Server Label allowed_tools: anyOf: - items: type: string type: array - $ref: '#/components/schemas/AllowedToolsFilter' - type: 'null' title: Allowed Tools type: object required: - server_label title: OpenAIResponseToolMCP description: Model Context Protocol (MCP) tool configuration for OpenAI response object. OpenAIResponseUsage: properties: input_tokens: type: integer title: Input Tokens output_tokens: type: integer title: Output Tokens total_tokens: type: integer title: Total Tokens input_tokens_details: anyOf: - $ref: '#/components/schemas/OpenAIResponseUsageInputTokensDetails' - type: 'null' output_tokens_details: anyOf: - $ref: '#/components/schemas/OpenAIResponseUsageOutputTokensDetails' - type: 'null' type: object required: - input_tokens - output_tokens - total_tokens title: OpenAIResponseUsage description: Usage information for OpenAI response. OpenAIResponseUsageInputTokensDetails: properties: cached_tokens: anyOf: - type: integer - type: 'null' title: Cached Tokens type: object title: OpenAIResponseUsageInputTokensDetails description: Token details for input tokens in OpenAI response usage. OpenAIResponseUsageOutputTokensDetails: properties: reasoning_tokens: anyOf: - type: integer - type: 'null' title: Reasoning Tokens type: object title: OpenAIResponseUsageOutputTokensDetails description: Token details for output tokens in OpenAI response usage. OpenAISystemMessageParam: properties: role: type: string const: system title: Role default: system content: anyOf: - type: string - items: $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array title: Content name: anyOf: - type: string - type: 'null' title: Name type: object required: - content title: OpenAISystemMessageParam description: A system message providing instructions or context to the model. OpenAITokenLogProb: properties: token: type: string title: Token bytes: anyOf: - items: type: integer type: array - type: 'null' title: Bytes logprob: type: number title: Logprob top_logprobs: items: $ref: '#/components/schemas/OpenAITopLogProb' type: array title: Top Logprobs type: object required: - token - logprob - top_logprobs title: OpenAITokenLogProb description: |- The log probability for a token from an OpenAI-compatible chat completion response. :token: The token :bytes: (Optional) The bytes for the token :logprob: The log probability of the token :top_logprobs: The top log probabilities for the token OpenAIToolMessageParam: properties: role: type: string const: tool title: Role default: tool tool_call_id: type: string title: Tool Call Id content: anyOf: - type: string - items: $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array title: Content type: object required: - tool_call_id - content title: OpenAIToolMessageParam description: A message representing the result of a tool invocation in an OpenAI-compatible chat completion request. OpenAITopLogProb: properties: token: type: string title: Token bytes: anyOf: - items: type: integer type: array - type: 'null' title: Bytes logprob: type: number title: Logprob type: object required: - token - logprob title: OpenAITopLogProb description: |- The top log probability for a token from an OpenAI-compatible chat completion response. :token: The token :bytes: (Optional) The bytes for the token :logprob: The log probability of the token OpenAIUserMessageParam-Input: properties: role: type: string const: user title: Role default: user content: anyOf: - type: string - items: oneOf: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' - $ref: '#/components/schemas/OpenAIFile' discriminator: propertyName: type mapping: file: '#/components/schemas/OpenAIFile' image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array title: Content name: anyOf: - type: string - type: 'null' title: Name type: object required: - content title: OpenAIUserMessageParam description: A message from the user in an OpenAI-compatible chat completion request. OpenAIUserMessageParam-Output: properties: role: type: string const: user title: Role default: user content: anyOf: - type: string - items: oneOf: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' - $ref: '#/components/schemas/OpenAIFile' discriminator: propertyName: type mapping: file: '#/components/schemas/OpenAIFile' image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' type: array title: Content name: anyOf: - type: string - type: 'null' title: Name type: object required: - content title: OpenAIUserMessageParam description: A message from the user in an OpenAI-compatible chat completion request. OptimizerConfig: properties: optimizer_type: $ref: '#/components/schemas/OptimizerType' lr: type: number title: Lr weight_decay: type: number title: Weight Decay num_warmup_steps: type: integer title: Num Warmup Steps type: object 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. Order: type: string enum: - asc - desc title: Order description: Sort order for paginated responses. OutputTokensDetails: properties: reasoning_tokens: type: integer title: Reasoning Tokens additionalProperties: true type: object required: - reasoning_tokens title: OutputTokensDetails PostTrainingJob: properties: job_uuid: type: string title: Job Uuid type: object required: - job_uuid title: PostTrainingJob Prompt: properties: prompt: anyOf: - type: string - type: 'null' title: Prompt description: The system prompt with variable placeholders version: type: integer minimum: 1.0 title: Version description: Version (integer starting at 1, incremented on save) prompt_id: type: string title: Prompt Id description: Unique identifier in format 'pmpt_<48-digit-hash>' variables: items: type: string type: array title: Variables description: List of variable names that can be used in the prompt template is_default: type: boolean title: Is Default description: Boolean indicating whether this version is the default version default: false type: object required: - version - prompt_id title: Prompt description: A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack. ProviderInfo: properties: api: type: string title: Api provider_id: type: string title: Provider Id provider_type: type: string title: Provider Type config: additionalProperties: true type: object title: Config health: additionalProperties: true type: object title: Health type: object required: - api - provider_id - provider_type - config - health title: ProviderInfo description: Information about a registered provider including its configuration and health status. QATFinetuningConfig: properties: type: type: string const: QAT title: Type default: QAT quantizer_name: type: string title: Quantizer Name group_size: type: integer title: Group Size type: object required: - quantizer_name - group_size title: QATFinetuningConfig description: Configuration for Quantization-Aware Training (QAT) fine-tuning. QueryChunksResponse: properties: chunks: items: $ref: '#/components/schemas/Chunk-Output' type: array title: Chunks scores: items: type: number type: array title: Scores type: object required: - chunks - scores title: QueryChunksResponse description: Response from querying chunks in a vector database. RegexParserScoringFnParams: properties: type: type: string const: regex_parser title: Type default: regex_parser parsing_regexes: items: type: string type: array title: Parsing Regexes description: Regex to extract the answer from generated response aggregation_functions: items: $ref: '#/components/schemas/AggregationFunctionType' type: array title: Aggregation Functions description: Aggregation functions to apply to the scores of each row type: object title: RegexParserScoringFnParams description: Parameters for regex parser scoring function configuration. RerankData: properties: index: type: integer title: Index relevance_score: type: number title: Relevance Score type: object required: - index - relevance_score title: RerankData description: A single rerank result from a reranking response. RerankResponse: properties: data: items: $ref: '#/components/schemas/RerankData' type: array title: Data type: object required: - data title: RerankResponse description: Response from a reranking request. RowsDataSource: properties: type: type: string const: rows title: Type default: rows rows: items: additionalProperties: true type: object type: array title: Rows type: object required: - rows title: RowsDataSource description: A dataset stored in rows. RunShieldResponse: properties: violation: anyOf: - $ref: '#/components/schemas/SafetyViolation' - type: 'null' type: object title: RunShieldResponse description: Response from running a safety shield. SafetyViolation: properties: violation_level: $ref: '#/components/schemas/ViolationLevel' user_message: anyOf: - type: string - type: 'null' title: User Message metadata: additionalProperties: true type: object title: Metadata type: object required: - violation_level title: SafetyViolation description: Details of a safety violation detected by content moderation. SamplingParams: properties: strategy: oneOf: - $ref: '#/components/schemas/GreedySamplingStrategy' - $ref: '#/components/schemas/TopPSamplingStrategy' - $ref: '#/components/schemas/TopKSamplingStrategy' title: Strategy discriminator: propertyName: type mapping: greedy: '#/components/schemas/GreedySamplingStrategy' top_k: '#/components/schemas/TopKSamplingStrategy' top_p: '#/components/schemas/TopPSamplingStrategy' max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens repetition_penalty: anyOf: - type: number - type: 'null' title: Repetition Penalty default: 1.0 stop: anyOf: - items: type: string type: array - type: 'null' title: Stop type: object title: SamplingParams description: Sampling parameters. ScoreBatchResponse: properties: dataset_id: anyOf: - type: string - type: 'null' title: Dataset Id results: additionalProperties: $ref: '#/components/schemas/ScoringResult' type: object title: Results type: object required: - results title: ScoreBatchResponse description: Response from batch scoring operations on datasets. ScoreResponse: properties: results: additionalProperties: $ref: '#/components/schemas/ScoringResult' type: object title: Results type: object required: - results title: ScoreResponse description: The response from scoring. ScoringFn: properties: identifier: type: string title: Identifier description: Unique identifier for this resource in llama stack provider_resource_id: anyOf: - type: string - type: 'null' title: Provider Resource Id description: Unique identifier for this resource in the provider provider_id: type: string title: Provider Id description: ID of the provider that owns this resource type: type: string const: scoring_function title: Type default: scoring_function description: anyOf: - type: string - type: 'null' title: Description metadata: additionalProperties: true type: object title: Metadata description: Any additional metadata for this definition 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' title: Return Type description: The return type of the deterministic function discriminator: propertyName: type mapping: array: '#/components/schemas/ArrayType' boolean: '#/components/schemas/BooleanType' chat_completion_input: '#/components/schemas/ChatCompletionInputType' completion_input: '#/components/schemas/CompletionInputType' json: '#/components/schemas/JsonType' number: '#/components/schemas/NumberType' object: '#/components/schemas/ObjectType' string: '#/components/schemas/StringType' union: '#/components/schemas/UnionType' params: anyOf: - oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' discriminator: propertyName: type mapping: basic: '#/components/schemas/BasicScoringFnParams' llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' regex_parser: '#/components/schemas/RegexParserScoringFnParams' - type: 'null' title: Params description: The parameters for the scoring function for benchmark eval, these can be overridden for app eval type: object required: - identifier - provider_id - return_type title: ScoringFn description: A scoring function resource for evaluating model outputs. ScoringResult: properties: score_rows: items: additionalProperties: true type: object type: array title: Score Rows aggregated_results: additionalProperties: true type: object title: Aggregated Results type: object required: - score_rows - aggregated_results title: ScoringResult description: A scoring result for a single row. SearchRankingOptions: properties: ranker: anyOf: - type: string - type: 'null' title: Ranker score_threshold: anyOf: - type: number - type: 'null' title: Score Threshold default: 0.0 type: object title: SearchRankingOptions description: Options for ranking and filtering search results. Shield: properties: identifier: type: string title: Identifier description: Unique identifier for this resource in llama stack provider_resource_id: anyOf: - type: string - type: 'null' title: Provider Resource Id description: Unique identifier for this resource in the provider provider_id: type: string title: Provider Id description: ID of the provider that owns this resource type: type: string const: shield title: Type default: shield params: anyOf: - additionalProperties: true type: object - type: 'null' title: Params type: object required: - identifier - provider_id title: Shield description: A safety shield resource that can be used to check content. StringType: properties: type: type: string const: string title: Type default: string type: object title: StringType description: Parameter type for string values. SystemMessage: properties: role: type: string const: system title: Role default: system content: anyOf: - type: string - oneOf: - $ref: '#/components/schemas/ImageContentItem-Input' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Input' text: '#/components/schemas/TextContentItem' - items: oneOf: - $ref: '#/components/schemas/ImageContentItem-Input' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Input' text: '#/components/schemas/TextContentItem' type: array title: Content type: object required: - content title: SystemMessage description: A system message providing instructions or context to the model. TextContentItem: properties: type: type: string const: text title: Type default: text text: type: string title: Text type: object required: - text title: TextContentItem description: A text content item ToolDef: properties: toolgroup_id: anyOf: - type: string - type: 'null' title: Toolgroup Id name: type: string title: Name description: anyOf: - type: string - type: 'null' title: Description input_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Input Schema output_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Output Schema metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata type: object required: - name title: ToolDef description: Tool definition used in runtime contexts. ToolGroup: properties: identifier: type: string title: Identifier description: Unique identifier for this resource in llama stack provider_resource_id: anyOf: - type: string - type: 'null' title: Provider Resource Id description: Unique identifier for this resource in the provider provider_id: type: string title: Provider Id description: ID of the provider that owns this resource type: type: string const: tool_group title: Type default: tool_group mcp_endpoint: anyOf: - $ref: '#/components/schemas/URL' - type: 'null' args: anyOf: - additionalProperties: true type: object - type: 'null' title: Args type: object required: - identifier - provider_id title: ToolGroup description: A group of related tools managed together. ToolInvocationResult: properties: content: anyOf: - type: string - oneOf: - $ref: '#/components/schemas/ImageContentItem-Output' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Output' text: '#/components/schemas/TextContentItem' - items: oneOf: - $ref: '#/components/schemas/ImageContentItem-Output' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Output' text: '#/components/schemas/TextContentItem' type: array - type: 'null' title: Content error_message: anyOf: - type: string - type: 'null' title: Error Message error_code: anyOf: - type: integer - type: 'null' title: Error Code metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata type: object title: ToolInvocationResult description: Result of a tool invocation. TopKSamplingStrategy: properties: type: type: string const: top_k title: Type default: top_k top_k: type: integer minimum: 1.0 title: Top K type: object required: - top_k title: TopKSamplingStrategy description: Top-k sampling strategy that restricts sampling to the k most likely tokens. TopPSamplingStrategy: properties: type: type: string const: top_p title: Type default: top_p temperature: anyOf: - type: number minimum: 0.0 - type: 'null' title: Temperature top_p: anyOf: - type: number - type: 'null' title: Top P default: 0.95 type: object required: - temperature title: TopPSamplingStrategy description: Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p. TrainingConfig: properties: n_epochs: type: integer title: N Epochs max_steps_per_epoch: type: integer title: Max Steps Per Epoch default: 1 gradient_accumulation_steps: type: integer title: Gradient Accumulation Steps default: 1 max_validation_steps: anyOf: - type: integer - type: 'null' title: Max Validation Steps default: 1 data_config: anyOf: - $ref: '#/components/schemas/DataConfig' - type: 'null' optimizer_config: anyOf: - $ref: '#/components/schemas/OptimizerConfig' - type: 'null' efficiency_config: anyOf: - $ref: '#/components/schemas/EfficiencyConfig' - type: 'null' dtype: anyOf: - type: string - type: 'null' title: Dtype default: bf16 type: object required: - n_epochs title: TrainingConfig description: Comprehensive configuration for the training process. URIDataSource: properties: type: type: string const: uri title: Type default: uri uri: type: string title: Uri type: object required: - uri title: URIDataSource description: A dataset that can be obtained from a URI. URL: properties: uri: type: string title: Uri type: object required: - uri title: URL description: A URL reference to external content. UnionType: properties: type: type: string const: union title: Type default: union type: object title: UnionType description: Parameter type for union values. VectorStoreChunkingStrategyAuto: properties: type: type: string const: auto title: Type default: auto type: object title: VectorStoreChunkingStrategyAuto description: Automatic chunking strategy for vector store files. VectorStoreChunkingStrategyStatic: properties: type: type: string const: static title: Type default: static static: $ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig' type: object required: - static title: VectorStoreChunkingStrategyStatic description: Static chunking strategy with configurable parameters. VectorStoreChunkingStrategyStaticConfig: properties: chunk_overlap_tokens: type: integer title: Chunk Overlap Tokens default: 400 max_chunk_size_tokens: type: integer maximum: 4096.0 minimum: 100.0 title: Max Chunk Size Tokens default: 800 type: object title: VectorStoreChunkingStrategyStaticConfig description: Configuration for static chunking strategy. VectorStoreContent: properties: type: type: string const: text title: Type text: type: string title: Text type: object required: - type - text title: VectorStoreContent description: Content item from a vector store file or search result. VectorStoreDeleteResponse: properties: id: type: string title: Id object: type: string title: Object default: vector_store.deleted deleted: type: boolean title: Deleted default: true type: object required: - id title: VectorStoreDeleteResponse description: Response from deleting a vector store. VectorStoreFileBatchObject: properties: id: type: string title: Id object: type: string title: Object default: vector_store.file_batch created_at: type: integer title: Created At vector_store_id: type: string title: Vector Store Id status: anyOf: - type: string const: completed - type: string const: in_progress - type: string const: cancelled - type: string const: failed title: Status file_counts: $ref: '#/components/schemas/VectorStoreFileCounts' type: object required: - id - created_at - vector_store_id - status - file_counts title: VectorStoreFileBatchObject description: OpenAI Vector Store File Batch object. VectorStoreFileContentsResponse: properties: file_id: type: string title: File Id filename: type: string title: Filename attributes: additionalProperties: true type: object title: Attributes content: items: $ref: '#/components/schemas/VectorStoreContent' type: array title: Content type: object required: - file_id - filename - attributes - content title: VectorStoreFileContentsResponse description: Response from retrieving the contents of a vector store file. VectorStoreFileCounts: properties: completed: type: integer title: Completed cancelled: type: integer title: Cancelled failed: type: integer title: Failed in_progress: type: integer title: In Progress total: type: integer title: Total type: object required: - completed - cancelled - failed - in_progress - total title: VectorStoreFileCounts description: File processing status counts for a vector store. VectorStoreFileDeleteResponse: properties: id: type: string title: Id object: type: string title: Object default: vector_store.file.deleted deleted: type: boolean title: Deleted default: true type: object required: - id title: VectorStoreFileDeleteResponse description: Response from deleting a vector store file. VectorStoreFileLastError: properties: code: anyOf: - type: string const: server_error - type: string const: rate_limit_exceeded title: Code message: type: string title: Message type: object required: - code - message title: VectorStoreFileLastError description: Error information for failed vector store file processing. VectorStoreFileObject: properties: id: type: string title: Id object: type: string title: Object default: vector_store.file attributes: additionalProperties: true type: object title: Attributes chunking_strategy: oneOf: - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' title: Chunking Strategy discriminator: propertyName: type mapping: auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' static: '#/components/schemas/VectorStoreChunkingStrategyStatic' created_at: type: integer title: Created At last_error: anyOf: - $ref: '#/components/schemas/VectorStoreFileLastError' - type: 'null' status: anyOf: - type: string const: completed - type: string const: in_progress - type: string const: cancelled - type: string const: failed title: Status usage_bytes: type: integer title: Usage Bytes default: 0 vector_store_id: type: string title: Vector Store Id type: object required: - id - chunking_strategy - created_at - status - vector_store_id title: VectorStoreFileObject description: OpenAI Vector Store File object. VectorStoreObject: properties: id: type: string title: Id object: type: string title: Object default: vector_store created_at: type: integer title: Created At name: anyOf: - type: string - type: 'null' title: Name usage_bytes: type: integer title: Usage Bytes default: 0 file_counts: $ref: '#/components/schemas/VectorStoreFileCounts' status: type: string title: Status default: completed expires_after: anyOf: - additionalProperties: true type: object - type: 'null' title: Expires After expires_at: anyOf: - type: integer - type: 'null' title: Expires At last_active_at: anyOf: - type: integer - type: 'null' title: Last Active At metadata: additionalProperties: true type: object title: Metadata type: object required: - id - created_at - file_counts title: VectorStoreObject description: OpenAI Vector Store object. VectorStoreSearchResponse: properties: file_id: type: string title: File Id filename: type: string title: Filename score: type: number title: Score attributes: anyOf: - additionalProperties: anyOf: - type: string - type: number - type: boolean type: object - type: 'null' title: Attributes content: items: $ref: '#/components/schemas/VectorStoreContent' type: array title: Content type: object required: - file_id - filename - score - content title: VectorStoreSearchResponse description: Response from searching a vector store. VectorStoreSearchResponsePage: properties: object: type: string title: Object default: vector_store.search_results.page search_query: items: type: string type: array title: Search Query data: items: $ref: '#/components/schemas/VectorStoreSearchResponse' type: array title: Data has_more: type: boolean title: Has More default: false next_page: anyOf: - type: string - type: 'null' title: Next Page type: object required: - search_query - data title: VectorStoreSearchResponsePage description: Paginated response from searching a vector store. VersionInfo: properties: version: type: string title: Version type: object required: - version title: VersionInfo description: Version information for the service. ViolationLevel: type: string enum: - info - warn - error title: ViolationLevel description: Severity level of a safety violation. _URLOrData: properties: url: anyOf: - $ref: '#/components/schemas/URL' - type: 'null' data: anyOf: - type: string - type: 'null' contentEncoding: base64 title: Data type: object title: _URLOrData description: A URL or a base64 encoded string _batches_Request: properties: input_file_id: type: string title: Input File Id endpoint: type: string title: Endpoint completion_window: type: string const: 24h title: Completion Window metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata idempotency_key: anyOf: - type: string - type: 'null' title: Idempotency Key type: object required: - input_file_id - endpoint - completion_window title: _batches_Request _conversations_Request: properties: items: anyOf: - items: oneOf: - $ref: '#/components/schemas/OpenAIResponseMessage-Input' - $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: 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' message: '#/components/schemas/OpenAIResponseMessage-Input' web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' type: array - type: 'null' title: Items metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata type: object title: _conversations_Request _conversations_conversation_id_Request: properties: metadata: additionalProperties: type: string type: object title: Metadata type: object required: - metadata title: _conversations_conversation_id_Request _conversations_conversation_id_items_Request: properties: items: items: oneOf: - $ref: '#/components/schemas/OpenAIResponseMessage-Input' - $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: 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' message: '#/components/schemas/OpenAIResponseMessage-Input' web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' type: array title: Items type: object required: - items title: _conversations_conversation_id_items_Request _datasets_Request: properties: purpose: title: Purpose source: title: Source metadata: title: Metadata dataset_id: title: Dataset Id type: object required: - purpose - source title: _datasets_Request _eval_benchmarks_benchmark_id_evaluations_Request: properties: input_rows: items: additionalProperties: true type: object type: array title: Input Rows scoring_functions: items: type: string type: array title: Scoring Functions benchmark_config: $ref: '#/components/schemas/BenchmarkConfig' type: object required: - input_rows - scoring_functions - benchmark_config title: _eval_benchmarks_benchmark_id_evaluations_Request _inference_rerank_Request: properties: model: type: string title: Model query: anyOf: - type: string - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' title: Query items: items: anyOf: - type: string - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' type: array title: Items max_num_results: anyOf: - type: integer - type: 'null' title: Max Num Results type: object required: - model - query - items title: _inference_rerank_Request _models_Request: properties: model_id: type: string title: Model Id provider_model_id: anyOf: - type: string - type: 'null' title: Provider Model Id provider_id: anyOf: - type: string - type: 'null' title: Provider Id metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata model_type: anyOf: - $ref: '#/components/schemas/ModelType' - type: 'null' type: object required: - model_id title: _models_Request _moderations_Request: properties: input: anyOf: - type: string - items: type: string type: array title: Input model: anyOf: - type: string - type: 'null' title: Model type: object required: - input title: _moderations_Request _post_training_preference_optimize_Request: properties: job_uuid: type: string title: Job Uuid finetuned_model: type: string title: Finetuned Model algorithm_config: $ref: '#/components/schemas/DPOAlignmentConfig' training_config: $ref: '#/components/schemas/TrainingConfig' hyperparam_search_config: additionalProperties: true type: object title: Hyperparam Search Config logger_config: additionalProperties: true type: object title: Logger Config type: object required: - job_uuid - finetuned_model - algorithm_config - training_config - hyperparam_search_config - logger_config title: _post_training_preference_optimize_Request _post_training_supervised_fine_tune_Request: properties: job_uuid: type: string title: Job Uuid training_config: $ref: '#/components/schemas/TrainingConfig' hyperparam_search_config: additionalProperties: true type: object title: Hyperparam Search Config logger_config: additionalProperties: true type: object title: Logger Config model: anyOf: - type: string - type: 'null' title: Model description: Model descriptor for training if not in provider config` checkpoint_dir: anyOf: - type: string - type: 'null' title: Checkpoint Dir algorithm_config: anyOf: - oneOf: - $ref: '#/components/schemas/LoraFinetuningConfig' - $ref: '#/components/schemas/QATFinetuningConfig' discriminator: propertyName: type mapping: LoRA: '#/components/schemas/LoraFinetuningConfig' QAT: '#/components/schemas/QATFinetuningConfig' - type: 'null' title: Algorithm Config type: object required: - job_uuid - training_config - hyperparam_search_config - logger_config title: _post_training_supervised_fine_tune_Request _prompts_Request: properties: prompt: type: string title: Prompt variables: anyOf: - items: type: string type: array - type: 'null' title: Variables type: object required: - prompt title: _prompts_Request _prompts_prompt_id_Request: properties: prompt: type: string title: Prompt version: type: integer title: Version variables: anyOf: - items: type: string type: array - type: 'null' title: Variables set_as_default: type: boolean title: Set As Default default: true type: object required: - prompt - version title: _prompts_prompt_id_Request _prompts_prompt_id_set_default_version_Request: properties: version: type: integer title: Version type: object required: - version title: _prompts_prompt_id_set_default_version_Request _responses_Request: properties: input: title: Input model: title: Model prompt: title: Prompt instructions: title: Instructions previous_response_id: title: Previous Response Id conversation: title: Conversation store: title: Store default: true stream: title: Stream default: false temperature: title: Temperature text: title: Text tools: title: Tools include: title: Include max_infer_iters: title: Max Infer Iters default: 10 guardrails: title: Guardrails type: object required: - input - model title: _responses_Request _scoring_score_Request: properties: input_rows: items: additionalProperties: true type: object type: array title: Input Rows scoring_functions: additionalProperties: anyOf: - oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' discriminator: propertyName: type mapping: basic: '#/components/schemas/BasicScoringFnParams' llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' regex_parser: '#/components/schemas/RegexParserScoringFnParams' - type: 'null' type: object title: Scoring Functions type: object required: - input_rows - scoring_functions title: _scoring_score_Request _scoring_score_batch_Request: properties: dataset_id: type: string title: Dataset Id scoring_functions: additionalProperties: anyOf: - oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' discriminator: propertyName: type mapping: basic: '#/components/schemas/BasicScoringFnParams' llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' regex_parser: '#/components/schemas/RegexParserScoringFnParams' - type: 'null' type: object title: Scoring Functions save_results_dataset: type: boolean title: Save Results Dataset default: false type: object required: - dataset_id - scoring_functions title: _scoring_score_batch_Request _shields_Request: properties: shield_id: type: string title: Shield Id provider_shield_id: anyOf: - type: string - type: 'null' title: Provider Shield Id provider_id: anyOf: - type: string - type: 'null' title: Provider Id params: anyOf: - additionalProperties: true type: object - type: 'null' title: Params type: object required: - shield_id title: _shields_Request _tool_runtime_invoke_Request: properties: tool_name: type: string title: Tool Name kwargs: additionalProperties: true type: object title: Kwargs type: object required: - tool_name - kwargs title: _tool_runtime_invoke_Request _vector_io_query_Request: properties: vector_store_id: type: string title: Vector Store Id query: anyOf: - type: string - oneOf: - $ref: '#/components/schemas/ImageContentItem-Input' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Input' text: '#/components/schemas/TextContentItem' - items: oneOf: - $ref: '#/components/schemas/ImageContentItem-Input' - $ref: '#/components/schemas/TextContentItem' discriminator: propertyName: type mapping: image: '#/components/schemas/ImageContentItem-Input' text: '#/components/schemas/TextContentItem' type: array title: Query params: anyOf: - additionalProperties: true type: object - type: 'null' title: Params type: object required: - vector_store_id - query title: _vector_io_query_Request _vector_stores_vector_store_id_Request: properties: name: anyOf: - type: string - type: 'null' title: Name expires_after: anyOf: - additionalProperties: true type: object - type: 'null' title: Expires After metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata type: object title: _vector_stores_vector_store_id_Request _vector_stores_vector_store_id_files_Request: properties: file_id: type: string title: File Id attributes: anyOf: - additionalProperties: true type: object - type: 'null' title: Attributes chunking_strategy: anyOf: - oneOf: - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' discriminator: propertyName: type mapping: auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' static: '#/components/schemas/VectorStoreChunkingStrategyStatic' - type: 'null' title: Chunking Strategy type: object required: - file_id title: _vector_stores_vector_store_id_files_Request _vector_stores_vector_store_id_files_file_id_Request: properties: attributes: additionalProperties: true type: object title: Attributes type: object required: - attributes title: _vector_stores_vector_store_id_files_file_id_Request _vector_stores_vector_store_id_search_Request: properties: query: anyOf: - type: string - items: type: string type: array title: Query filters: anyOf: - additionalProperties: true type: object - type: 'null' title: Filters max_num_results: anyOf: - type: integer - type: 'null' title: Max Num Results default: 10 ranking_options: anyOf: - $ref: '#/components/schemas/SearchRankingOptions' - type: 'null' rewrite_query: anyOf: - type: boolean - type: 'null' title: Rewrite Query default: false search_mode: anyOf: - type: string - type: 'null' title: Search Mode default: vector type: object required: - query title: _vector_stores_vector_store_id_search_Request Error: description: Error response from the API. Roughly follows RFC 7807. properties: status: title: Status type: integer title: title: Title type: string detail: title: Detail type: string instance: anyOf: - type: string - type: 'null' title: Instance nullable: true required: - status - title - detail title: Error description: >- Error response from the API. Roughly follows RFC 7807. ModelType: type: string enum: - llm - embedding - rerank title: ModelType description: >- Enumeration of supported model types in Llama Stack. 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 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_store - 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. 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. 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' 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' 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. 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. 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 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 Shield: type: object properties: identifier: type: string provider_resource_id: type: string provider_id: type: string type: type: string enum: - model - shield - vector_store - 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. 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. 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 DataSource: oneOf: - $ref: '#/components/schemas/URIDataSource' - $ref: '#/components/schemas/RowsDataSource' discriminator: propertyName: type mapping: uri: '#/components/schemas/URIDataSource' rows: '#/components/schemas/RowsDataSource' 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. 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 Dataset: type: object properties: identifier: type: string provider_resource_id: type: string provider_id: type: string type: type: string enum: - model - shield - vector_store - 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. 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 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 DefaultError: description: An error occurred content: application/json: schema: $ref: '#/components/schemas/Error' example: status: 0 title: Error detail: An unexpected error occurred security: - Default: [] tags: - name: Benchmarks description: '' - name: Datasets description: '' - name: Models description: '' - name: ScoringFunctions description: '' - name: Shields description: '' - name: ToolGroups description: '' x-tagGroups: - name: Operations tags: - Benchmarks - Datasets - Models - ScoringFunctions - Shields - ToolGroups