components: responses: {} schemas: AgentCandidate: additionalProperties: false properties: config: $ref: '#/components/schemas/AgentConfig' type: const: agent default: agent type: string required: - type - config type: object AgentConfig: additionalProperties: false properties: client_tools: items: $ref: '#/components/schemas/ToolDef' type: array enable_session_persistence: type: boolean input_shields: items: type: string type: array instructions: type: string max_infer_iters: default: 10 type: integer model: type: string output_shields: items: type: string type: array sampling_params: $ref: '#/components/schemas/SamplingParams' tool_choice: $ref: '#/components/schemas/ToolChoice' default: auto tool_prompt_format: $ref: '#/components/schemas/ToolPromptFormat' default: json toolgroups: items: $ref: '#/components/schemas/AgentTool' type: array required: - max_infer_iters - model - instructions - enable_session_persistence type: object AgentCreateResponse: additionalProperties: false properties: agent_id: type: string required: - agent_id type: object AgentSessionCreateResponse: additionalProperties: false properties: session_id: type: string required: - session_id type: object AgentStepResponse: additionalProperties: false properties: step: oneOf: - $ref: '#/components/schemas/InferenceStep' - $ref: '#/components/schemas/ToolExecutionStep' - $ref: '#/components/schemas/ShieldCallStep' - $ref: '#/components/schemas/MemoryRetrievalStep' required: - step type: object AgentTool: oneOf: - type: string - additionalProperties: false properties: args: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object name: type: string required: - name - args type: object AgentTurnInputType: additionalProperties: false properties: type: const: agent_turn_input default: agent_turn_input type: string required: - type type: object AgentTurnResponseEvent: additionalProperties: false properties: payload: oneOf: - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload' - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload' - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload' - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload' - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload' required: - payload title: Streamed agent execution response. type: object AgentTurnResponseStepCompletePayload: additionalProperties: false properties: event_type: const: step_complete default: step_complete type: string step_details: oneOf: - $ref: '#/components/schemas/InferenceStep' - $ref: '#/components/schemas/ToolExecutionStep' - $ref: '#/components/schemas/ShieldCallStep' - $ref: '#/components/schemas/MemoryRetrievalStep' step_id: type: string step_type: enum: - inference - tool_execution - shield_call - memory_retrieval type: string required: - event_type - step_type - step_id - step_details type: object AgentTurnResponseStepProgressPayload: additionalProperties: false properties: delta: $ref: '#/components/schemas/ContentDelta' event_type: const: step_progress default: step_progress type: string step_id: type: string step_type: enum: - inference - tool_execution - shield_call - memory_retrieval type: string required: - event_type - step_type - step_id - delta type: object AgentTurnResponseStepStartPayload: additionalProperties: false properties: event_type: const: step_start default: step_start type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object step_id: type: string step_type: enum: - inference - tool_execution - shield_call - memory_retrieval type: string required: - event_type - step_type - step_id type: object AgentTurnResponseStreamChunk: additionalProperties: false properties: event: $ref: '#/components/schemas/AgentTurnResponseEvent' required: - event title: streamed agent turn completion response. type: object AgentTurnResponseTurnCompletePayload: additionalProperties: false properties: event_type: const: turn_complete default: turn_complete type: string turn: $ref: '#/components/schemas/Turn' required: - event_type - turn type: object AgentTurnResponseTurnStartPayload: additionalProperties: false properties: event_type: const: turn_start default: turn_start type: string turn_id: type: string required: - event_type - turn_id type: object AggregationFunctionType: enum: - average - median - categorical_count - accuracy type: string AppEvalTaskConfig: additionalProperties: false properties: eval_candidate: oneOf: - $ref: '#/components/schemas/ModelCandidate' - $ref: '#/components/schemas/AgentCandidate' num_examples: type: integer scoring_params: additionalProperties: oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' type: object type: const: app default: app type: string required: - type - eval_candidate - scoring_params type: object AppendRowsRequest: additionalProperties: false properties: dataset_id: type: string rows: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array required: - dataset_id - rows type: object ArrayType: additionalProperties: false properties: type: const: array default: array type: string required: - type type: object BasicScoringFnParams: additionalProperties: false properties: aggregation_functions: items: $ref: '#/components/schemas/AggregationFunctionType' type: array type: const: basic default: basic type: string required: - type type: object BatchChatCompletionRequest: additionalProperties: false properties: logprobs: additionalProperties: false properties: top_k: default: 0 type: integer type: object messages_batch: items: items: $ref: '#/components/schemas/Message' type: array type: array model: type: string sampling_params: $ref: '#/components/schemas/SamplingParams' tool_choice: $ref: '#/components/schemas/ToolChoice' tool_prompt_format: $ref: '#/components/schemas/ToolPromptFormat' tools: items: $ref: '#/components/schemas/ToolDefinition' type: array required: - model - messages_batch type: object BatchChatCompletionResponse: additionalProperties: false properties: completion_message_batch: items: $ref: '#/components/schemas/CompletionMessage' type: array required: - completion_message_batch type: object BatchCompletionRequest: additionalProperties: false properties: content_batch: items: $ref: '#/components/schemas/InterleavedContent' type: array logprobs: additionalProperties: false properties: top_k: default: 0 type: integer type: object model: type: string sampling_params: $ref: '#/components/schemas/SamplingParams' required: - model - content_batch type: object BatchCompletionResponse: additionalProperties: false properties: completion_message_batch: items: $ref: '#/components/schemas/CompletionMessage' type: array required: - completion_message_batch type: object BenchmarkEvalTaskConfig: additionalProperties: false properties: eval_candidate: oneOf: - $ref: '#/components/schemas/ModelCandidate' - $ref: '#/components/schemas/AgentCandidate' num_examples: type: integer type: const: benchmark default: benchmark type: string required: - type - eval_candidate type: object BooleanType: additionalProperties: false properties: type: const: boolean default: boolean type: string required: - type type: object BuiltinTool: enum: - brave_search - wolfram_alpha - photogen - code_interpreter type: string CancelTrainingJobRequest: additionalProperties: false properties: job_uuid: type: string required: - job_uuid type: object ChatCompletionInputType: additionalProperties: false properties: type: const: chat_completion_input default: chat_completion_input type: string required: - type type: object ChatCompletionRequest: additionalProperties: false properties: logprobs: additionalProperties: false properties: top_k: default: 0 type: integer type: object messages: items: $ref: '#/components/schemas/Message' type: array model_id: type: string response_format: $ref: '#/components/schemas/ResponseFormat' sampling_params: $ref: '#/components/schemas/SamplingParams' stream: type: boolean tool_choice: $ref: '#/components/schemas/ToolChoice' tool_prompt_format: $ref: '#/components/schemas/ToolPromptFormat' tools: items: $ref: '#/components/schemas/ToolDefinition' type: array required: - model_id - messages type: object ChatCompletionResponse: additionalProperties: false properties: completion_message: $ref: '#/components/schemas/CompletionMessage' logprobs: items: $ref: '#/components/schemas/TokenLogProbs' type: array required: - completion_message title: Chat completion response. type: object ChatCompletionResponseEvent: additionalProperties: false properties: delta: $ref: '#/components/schemas/ContentDelta' event_type: $ref: '#/components/schemas/ChatCompletionResponseEventType' logprobs: items: $ref: '#/components/schemas/TokenLogProbs' type: array stop_reason: $ref: '#/components/schemas/StopReason' required: - event_type - delta title: Chat completion response event. type: object ChatCompletionResponseEventType: enum: - start - complete - progress type: string ChatCompletionResponseStreamChunk: additionalProperties: false properties: event: $ref: '#/components/schemas/ChatCompletionResponseEvent' required: - event title: SSE-stream of these events. type: object Checkpoint: description: Checkpoint created during training runs CompletionInputType: additionalProperties: false properties: type: const: completion_input default: completion_input type: string required: - type type: object CompletionMessage: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' role: const: assistant default: assistant type: string stop_reason: $ref: '#/components/schemas/StopReason' tool_calls: items: $ref: '#/components/schemas/ToolCall' type: array required: - role - content - stop_reason - tool_calls type: object CompletionRequest: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' logprobs: additionalProperties: false properties: top_k: default: 0 type: integer type: object model_id: type: string response_format: $ref: '#/components/schemas/ResponseFormat' sampling_params: $ref: '#/components/schemas/SamplingParams' stream: type: boolean required: - model_id - content type: object CompletionResponse: additionalProperties: false properties: content: type: string logprobs: items: $ref: '#/components/schemas/TokenLogProbs' type: array stop_reason: $ref: '#/components/schemas/StopReason' required: - content - stop_reason title: Completion response. type: object CompletionResponseStreamChunk: additionalProperties: false properties: delta: type: string logprobs: items: $ref: '#/components/schemas/TokenLogProbs' type: array stop_reason: $ref: '#/components/schemas/StopReason' required: - delta title: streamed completion response. type: object ContentDelta: oneOf: - $ref: '#/components/schemas/TextDelta' - $ref: '#/components/schemas/ImageDelta' - $ref: '#/components/schemas/ToolCallDelta' CreateAgentRequest: additionalProperties: false properties: agent_config: $ref: '#/components/schemas/AgentConfig' required: - agent_config type: object CreateAgentSessionRequest: additionalProperties: false properties: session_name: type: string required: - session_name type: object CreateAgentTurnRequest: additionalProperties: false properties: documents: items: additionalProperties: false properties: content: oneOf: - type: string - $ref: '#/components/schemas/InterleavedContentItem' - items: $ref: '#/components/schemas/InterleavedContentItem' type: array - $ref: '#/components/schemas/URL' mime_type: type: string required: - content - mime_type type: object type: array messages: items: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/ToolResponseMessage' type: array stream: type: boolean toolgroups: items: $ref: '#/components/schemas/AgentTool' type: array required: - messages type: object DPOAlignmentConfig: additionalProperties: false properties: epsilon: type: number gamma: type: number reward_clip: type: number reward_scale: type: number required: - reward_scale - reward_clip - epsilon - gamma type: object DataConfig: additionalProperties: false properties: batch_size: type: integer data_format: $ref: '#/components/schemas/DatasetFormat' dataset_id: type: string packed: default: false type: boolean shuffle: type: boolean train_on_input: default: false type: boolean validation_dataset_id: type: string required: - dataset_id - batch_size - shuffle - data_format type: object Dataset: additionalProperties: false properties: dataset_schema: additionalProperties: $ref: '#/components/schemas/ParamType' type: object identifier: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object provider_id: type: string provider_resource_id: type: string type: const: dataset default: dataset type: string url: $ref: '#/components/schemas/URL' required: - identifier - provider_resource_id - provider_id - type - dataset_schema - url - metadata type: object DatasetFormat: enum: - instruct - dialog type: string DefaultRAGQueryGeneratorConfig: additionalProperties: false properties: separator: default: ' ' type: string type: const: default default: default type: string required: - type - separator type: object EfficiencyConfig: additionalProperties: false properties: enable_activation_checkpointing: default: false type: boolean enable_activation_offloading: default: false type: boolean fsdp_cpu_offload: default: false type: boolean memory_efficient_fsdp_wrap: default: false type: boolean type: object EmbeddingsRequest: additionalProperties: false properties: contents: items: $ref: '#/components/schemas/InterleavedContent' type: array model_id: type: string required: - model_id - contents type: object EmbeddingsResponse: additionalProperties: false properties: embeddings: items: items: type: number type: array type: array required: - embeddings type: object EvalTask: additionalProperties: false properties: dataset_id: type: string identifier: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object provider_id: type: string provider_resource_id: type: string scoring_functions: items: type: string type: array type: const: eval_task default: eval_task type: string required: - identifier - provider_resource_id - provider_id - type - dataset_id - scoring_functions - metadata type: object EvaluateResponse: additionalProperties: false properties: generations: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array scores: additionalProperties: $ref: '#/components/schemas/ScoringResult' type: object required: - generations - scores type: object EvaluateRowsRequest: additionalProperties: false properties: input_rows: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array scoring_functions: items: type: string type: array task_config: oneOf: - $ref: '#/components/schemas/BenchmarkEvalTaskConfig' - $ref: '#/components/schemas/AppEvalTaskConfig' required: - input_rows - scoring_functions - task_config type: object GreedySamplingStrategy: additionalProperties: false properties: type: const: greedy default: greedy type: string required: - type type: object HealthInfo: additionalProperties: false properties: status: type: string required: - status type: object ImageContentItem: additionalProperties: false properties: data: contentEncoding: base64 type: string type: const: image default: image type: string url: $ref: '#/components/schemas/URL' required: - type type: object ImageDelta: additionalProperties: false properties: data: contentEncoding: base64 type: string type: const: image default: image type: string required: - type - data type: object InferenceStep: additionalProperties: false properties: completed_at: format: date-time type: string model_response: $ref: '#/components/schemas/CompletionMessage' started_at: format: date-time type: string step_id: type: string step_type: const: inference default: inference type: string turn_id: type: string required: - turn_id - step_id - step_type - model_response type: object InsertChunksRequest: additionalProperties: false properties: chunks: items: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object required: - content - metadata type: object type: array ttl_seconds: type: integer vector_db_id: type: string required: - vector_db_id - chunks type: object InsertRequest: additionalProperties: false properties: chunk_size_in_tokens: type: integer documents: items: $ref: '#/components/schemas/RAGDocument' type: array vector_db_id: type: string required: - documents - vector_db_id - chunk_size_in_tokens type: object InterleavedContent: oneOf: - type: string - $ref: '#/components/schemas/InterleavedContentItem' - items: $ref: '#/components/schemas/InterleavedContentItem' type: array InterleavedContentItem: oneOf: - $ref: '#/components/schemas/ImageContentItem' - $ref: '#/components/schemas/TextContentItem' InvokeToolRequest: additionalProperties: false properties: kwargs: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object tool_name: type: string required: - tool_name - kwargs type: object Job: additionalProperties: false properties: job_id: type: string required: - job_id type: object JobStatus: enum: - completed - in_progress - failed - scheduled type: string JsonType: additionalProperties: false properties: type: const: json default: json type: string required: - type type: object LLMAsJudgeScoringFnParams: additionalProperties: false properties: aggregation_functions: items: $ref: '#/components/schemas/AggregationFunctionType' type: array judge_model: type: string judge_score_regexes: items: type: string type: array prompt_template: type: string type: const: llm_as_judge default: llm_as_judge type: string required: - type - judge_model type: object LLMRAGQueryGeneratorConfig: additionalProperties: false properties: model: type: string template: type: string type: const: llm default: llm type: string required: - type - model - template type: object ListDatasetsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/Dataset' type: array required: - data type: object ListEvalTasksResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/EvalTask' type: array required: - data type: object ListModelsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/Model' type: array required: - data type: object ListPostTrainingJobsResponse: additionalProperties: false properties: data: items: additionalProperties: false properties: job_uuid: type: string required: - job_uuid type: object type: array required: - data type: object ListProvidersResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/ProviderInfo' type: array required: - data type: object ListRoutesResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/RouteInfo' type: array required: - data type: object ListScoringFunctionsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/ScoringFn' type: array required: - data type: object ListShieldsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/Shield' type: array required: - data type: object ListToolGroupsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/ToolGroup' type: array required: - data type: object ListToolsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/Tool' type: array required: - data type: object ListVectorDBsResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/VectorDB' type: array required: - data type: object LogEventRequest: additionalProperties: false properties: event: oneOf: - $ref: '#/components/schemas/UnstructuredLogEvent' - $ref: '#/components/schemas/MetricEvent' - $ref: '#/components/schemas/StructuredLogEvent' ttl_seconds: type: integer required: - event - ttl_seconds type: object LogSeverity: enum: - verbose - debug - info - warn - error - critical type: string LoraFinetuningConfig: additionalProperties: false properties: alpha: type: integer apply_lora_to_mlp: type: boolean apply_lora_to_output: type: boolean lora_attn_modules: items: type: string type: array quantize_base: default: false type: boolean rank: type: integer type: const: LoRA default: LoRA type: string use_dora: default: false type: boolean required: - type - lora_attn_modules - apply_lora_to_mlp - apply_lora_to_output - rank - alpha type: object MemoryRetrievalStep: additionalProperties: false properties: completed_at: format: date-time type: string inserted_context: $ref: '#/components/schemas/InterleavedContent' started_at: format: date-time type: string step_id: type: string step_type: const: memory_retrieval default: memory_retrieval type: string turn_id: type: string vector_db_ids: type: string required: - turn_id - step_id - step_type - vector_db_ids - inserted_context type: object Message: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/SystemMessage' - $ref: '#/components/schemas/ToolResponseMessage' - $ref: '#/components/schemas/CompletionMessage' MetricEvent: additionalProperties: false properties: attributes: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object metric: type: string span_id: type: string timestamp: format: date-time type: string trace_id: type: string type: const: metric default: metric type: string unit: type: string value: oneOf: - type: integer - type: number required: - trace_id - span_id - timestamp - type - metric - value - unit type: object Model: additionalProperties: false properties: identifier: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object model_type: $ref: '#/components/schemas/ModelType' default: llm provider_id: type: string provider_resource_id: type: string type: const: model default: model type: string required: - identifier - provider_resource_id - provider_id - type - metadata - model_type type: object ModelCandidate: additionalProperties: false properties: model: type: string sampling_params: $ref: '#/components/schemas/SamplingParams' system_message: $ref: '#/components/schemas/SystemMessage' type: const: model default: model type: string required: - type - model - sampling_params type: object ModelType: enum: - llm - embedding type: string NumberType: additionalProperties: false properties: type: const: number default: number type: string required: - type type: object ObjectType: additionalProperties: false properties: type: const: object default: object type: string required: - type type: object OptimizerConfig: additionalProperties: false properties: lr: type: number num_warmup_steps: type: integer optimizer_type: $ref: '#/components/schemas/OptimizerType' weight_decay: type: number required: - optimizer_type - lr - weight_decay - num_warmup_steps type: object OptimizerType: enum: - adam - adamw - sgd type: string PaginatedRowsResult: additionalProperties: false properties: next_page_token: type: string rows: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array total_count: type: integer required: - rows - total_count type: object ParamType: oneOf: - $ref: '#/components/schemas/StringType' - $ref: '#/components/schemas/NumberType' - $ref: '#/components/schemas/BooleanType' - $ref: '#/components/schemas/ArrayType' - $ref: '#/components/schemas/ObjectType' - $ref: '#/components/schemas/JsonType' - $ref: '#/components/schemas/UnionType' - $ref: '#/components/schemas/ChatCompletionInputType' - $ref: '#/components/schemas/CompletionInputType' - $ref: '#/components/schemas/AgentTurnInputType' PostTrainingJob: additionalProperties: false properties: job_uuid: type: string required: - job_uuid type: object PostTrainingJobArtifactsResponse: additionalProperties: false properties: checkpoints: items: $ref: '#/components/schemas/Checkpoint' type: array job_uuid: type: string required: - job_uuid - checkpoints title: Artifacts of a finetuning job. type: object PostTrainingJobStatusResponse: additionalProperties: false properties: checkpoints: items: $ref: '#/components/schemas/Checkpoint' type: array completed_at: format: date-time type: string job_uuid: type: string resources_allocated: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object scheduled_at: format: date-time type: string started_at: format: date-time type: string status: $ref: '#/components/schemas/JobStatus' required: - job_uuid - status - checkpoints title: Status of a finetuning job. type: object PreferenceOptimizeRequest: additionalProperties: false properties: algorithm_config: $ref: '#/components/schemas/DPOAlignmentConfig' finetuned_model: type: string hyperparam_search_config: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object job_uuid: type: string logger_config: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object training_config: $ref: '#/components/schemas/TrainingConfig' required: - job_uuid - finetuned_model - algorithm_config - training_config - hyperparam_search_config - logger_config type: object ProviderInfo: additionalProperties: false properties: api: type: string provider_id: type: string provider_type: type: string required: - api - provider_id - provider_type type: object QATFinetuningConfig: additionalProperties: false properties: group_size: type: integer quantizer_name: type: string type: const: QAT default: QAT type: string required: - type - quantizer_name - group_size type: object QueryChunksRequest: additionalProperties: false properties: params: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object query: $ref: '#/components/schemas/InterleavedContent' vector_db_id: type: string required: - vector_db_id - query type: object QueryChunksResponse: additionalProperties: false properties: chunks: items: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object required: - content - metadata type: object type: array scores: items: type: number type: array required: - chunks - scores type: object QueryCondition: additionalProperties: false properties: key: type: string op: $ref: '#/components/schemas/QueryConditionOp' value: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object required: - key - op - value type: object QueryConditionOp: enum: - eq - ne - gt - lt type: string QueryRequest: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' query_config: $ref: '#/components/schemas/RAGQueryConfig' vector_db_ids: items: type: string type: array required: - content - vector_db_ids type: object QuerySpanTreeResponse: additionalProperties: false properties: data: additionalProperties: $ref: '#/components/schemas/SpanWithStatus' type: object required: - data type: object QuerySpansResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/Span' type: array required: - data type: object QueryTracesResponse: additionalProperties: false properties: data: items: $ref: '#/components/schemas/Trace' type: array required: - data type: object RAGDocument: additionalProperties: false properties: content: oneOf: - type: string - $ref: '#/components/schemas/InterleavedContentItem' - items: $ref: '#/components/schemas/InterleavedContentItem' type: array - $ref: '#/components/schemas/URL' document_id: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object mime_type: type: string required: - document_id - content - metadata type: object RAGQueryConfig: additionalProperties: false properties: max_chunks: default: 5 type: integer max_tokens_in_context: default: 4096 type: integer query_generator_config: $ref: '#/components/schemas/RAGQueryGeneratorConfig' required: - query_generator_config - max_tokens_in_context - max_chunks type: object RAGQueryGeneratorConfig: oneOf: - $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig' - $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig' RAGQueryResult: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' type: object RegexParserScoringFnParams: additionalProperties: false properties: aggregation_functions: items: $ref: '#/components/schemas/AggregationFunctionType' type: array parsing_regexes: items: type: string type: array type: const: regex_parser default: regex_parser type: string required: - type type: object RegisterDatasetRequest: additionalProperties: false properties: dataset_id: type: string dataset_schema: additionalProperties: $ref: '#/components/schemas/ParamType' type: object metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object provider_dataset_id: type: string provider_id: type: string url: $ref: '#/components/schemas/URL' required: - dataset_id - dataset_schema - url type: object RegisterEvalTaskRequest: additionalProperties: false properties: dataset_id: type: string eval_task_id: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object provider_eval_task_id: type: string provider_id: type: string scoring_functions: items: type: string type: array required: - eval_task_id - dataset_id - scoring_functions type: object RegisterModelRequest: additionalProperties: false properties: metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object model_id: type: string model_type: $ref: '#/components/schemas/ModelType' provider_id: type: string provider_model_id: type: string required: - model_id type: object RegisterScoringFunctionRequest: additionalProperties: false properties: description: type: string params: oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' provider_id: type: string provider_scoring_fn_id: type: string return_type: $ref: '#/components/schemas/ParamType' scoring_fn_id: type: string required: - scoring_fn_id - description - return_type type: object RegisterShieldRequest: additionalProperties: false properties: params: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object provider_id: type: string provider_shield_id: type: string shield_id: type: string required: - shield_id type: object RegisterToolGroupRequest: additionalProperties: false properties: args: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object mcp_endpoint: $ref: '#/components/schemas/URL' provider_id: type: string toolgroup_id: type: string required: - toolgroup_id - provider_id type: object RegisterVectorDbRequest: additionalProperties: false properties: embedding_dimension: type: integer embedding_model: type: string provider_id: type: string provider_vector_db_id: type: string vector_db_id: type: string required: - vector_db_id - embedding_model type: object ResponseFormat: oneOf: - additionalProperties: false properties: json_schema: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: const: json_schema default: json_schema type: string required: - type - json_schema type: object - additionalProperties: false properties: bnf: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: const: grammar default: grammar type: string required: - type - bnf type: object RouteInfo: additionalProperties: false properties: method: type: string provider_types: items: type: string type: array route: type: string required: - route - method - provider_types type: object RunEvalRequest: additionalProperties: false properties: task_config: oneOf: - $ref: '#/components/schemas/BenchmarkEvalTaskConfig' - $ref: '#/components/schemas/AppEvalTaskConfig' required: - task_config type: object RunShieldRequest: additionalProperties: false properties: messages: items: $ref: '#/components/schemas/Message' type: array params: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object shield_id: type: string required: - shield_id - messages - params type: object RunShieldResponse: additionalProperties: false properties: violation: $ref: '#/components/schemas/SafetyViolation' type: object SafetyViolation: additionalProperties: false properties: metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object user_message: type: string violation_level: $ref: '#/components/schemas/ViolationLevel' required: - violation_level - metadata type: object SamplingParams: additionalProperties: false properties: max_tokens: default: 0 type: integer repetition_penalty: default: 1.0 type: number strategy: oneOf: - $ref: '#/components/schemas/GreedySamplingStrategy' - $ref: '#/components/schemas/TopPSamplingStrategy' - $ref: '#/components/schemas/TopKSamplingStrategy' required: - strategy type: object SaveSpansToDatasetRequest: additionalProperties: false properties: attribute_filters: items: $ref: '#/components/schemas/QueryCondition' type: array attributes_to_save: items: type: string type: array dataset_id: type: string max_depth: type: integer required: - attribute_filters - attributes_to_save - dataset_id type: object ScoreBatchRequest: additionalProperties: false properties: dataset_id: type: string save_results_dataset: type: boolean scoring_functions: additionalProperties: oneOf: - oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' - type: 'null' type: object required: - dataset_id - scoring_functions - save_results_dataset type: object ScoreBatchResponse: additionalProperties: false properties: dataset_id: type: string results: additionalProperties: $ref: '#/components/schemas/ScoringResult' type: object required: - results type: object ScoreRequest: additionalProperties: false properties: input_rows: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array scoring_functions: additionalProperties: oneOf: - oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' - type: 'null' type: object required: - input_rows - scoring_functions type: object ScoreResponse: additionalProperties: false properties: results: additionalProperties: $ref: '#/components/schemas/ScoringResult' type: object required: - results type: object ScoringFn: additionalProperties: false properties: description: type: string identifier: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object params: oneOf: - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - $ref: '#/components/schemas/RegexParserScoringFnParams' - $ref: '#/components/schemas/BasicScoringFnParams' provider_id: type: string provider_resource_id: type: string return_type: $ref: '#/components/schemas/ParamType' type: const: scoring_function default: scoring_function type: string required: - identifier - provider_resource_id - provider_id - type - metadata - return_type type: object ScoringResult: additionalProperties: false properties: aggregated_results: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object score_rows: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array required: - score_rows - aggregated_results type: object Session: additionalProperties: false properties: session_id: type: string session_name: type: string started_at: format: date-time type: string turns: items: $ref: '#/components/schemas/Turn' type: array required: - session_id - session_name - turns - started_at title: A single session of an interaction with an Agentic System. type: object Shield: additionalProperties: false properties: identifier: type: string params: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object provider_id: type: string provider_resource_id: type: string type: const: shield default: shield type: string required: - identifier - provider_resource_id - provider_id - type title: A safety shield resource that can be used to check content type: object ShieldCallStep: additionalProperties: false properties: completed_at: format: date-time type: string started_at: format: date-time type: string step_id: type: string step_type: const: shield_call default: shield_call type: string turn_id: type: string violation: $ref: '#/components/schemas/SafetyViolation' required: - turn_id - step_id - step_type type: object Span: additionalProperties: false properties: attributes: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object end_time: format: date-time type: string name: type: string parent_span_id: type: string span_id: type: string start_time: format: date-time type: string trace_id: type: string required: - span_id - trace_id - name - start_time type: object SpanEndPayload: additionalProperties: false properties: status: $ref: '#/components/schemas/SpanStatus' type: const: span_end default: span_end type: string required: - type - status type: object SpanStartPayload: additionalProperties: false properties: name: type: string parent_span_id: type: string type: const: span_start default: span_start type: string required: - type - name type: object SpanStatus: enum: - ok - error type: string SpanWithStatus: additionalProperties: false properties: attributes: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object end_time: format: date-time type: string name: type: string parent_span_id: type: string span_id: type: string start_time: format: date-time type: string status: $ref: '#/components/schemas/SpanStatus' trace_id: type: string required: - span_id - trace_id - name - start_time type: object StopReason: enum: - end_of_turn - end_of_message - out_of_tokens type: string StringType: additionalProperties: false properties: type: const: string default: string type: string required: - type type: object StructuredLogEvent: additionalProperties: false properties: attributes: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object payload: oneOf: - $ref: '#/components/schemas/SpanStartPayload' - $ref: '#/components/schemas/SpanEndPayload' span_id: type: string timestamp: format: date-time type: string trace_id: type: string type: const: structured_log default: structured_log type: string required: - trace_id - span_id - timestamp - type - payload type: object SupervisedFineTuneRequest: additionalProperties: false properties: algorithm_config: oneOf: - $ref: '#/components/schemas/LoraFinetuningConfig' - $ref: '#/components/schemas/QATFinetuningConfig' checkpoint_dir: type: string hyperparam_search_config: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object job_uuid: type: string logger_config: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object model: type: string training_config: $ref: '#/components/schemas/TrainingConfig' required: - job_uuid - training_config - hyperparam_search_config - logger_config - model type: object SyntheticDataGenerateRequest: additionalProperties: false properties: dialogs: items: $ref: '#/components/schemas/Message' type: array filtering_function: enum: - none - random - top_k - top_p - top_k_top_p - sigmoid title: The type of filtering function. type: string model: type: string required: - dialogs - filtering_function type: object SyntheticDataGenerationResponse: additionalProperties: false properties: statistics: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object synthetic_data: items: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object type: array required: - synthetic_data title: Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold. type: object SystemMessage: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' role: const: system default: system type: string required: - role - content type: object TextContentItem: additionalProperties: false properties: text: type: string type: const: text default: text type: string required: - type - text type: object TextDelta: additionalProperties: false properties: text: type: string type: const: text default: text type: string required: - type - text type: object TokenLogProbs: additionalProperties: false properties: logprobs_by_token: additionalProperties: type: number type: object required: - logprobs_by_token type: object Tool: additionalProperties: false properties: description: type: string identifier: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object parameters: items: $ref: '#/components/schemas/ToolParameter' type: array provider_id: type: string provider_resource_id: type: string tool_host: $ref: '#/components/schemas/ToolHost' toolgroup_id: type: string type: const: tool default: tool type: string required: - identifier - provider_resource_id - provider_id - type - toolgroup_id - tool_host - description - parameters type: object ToolCall: additionalProperties: false properties: arguments: additionalProperties: oneOf: - type: string - type: integer - type: number - type: boolean - type: 'null' - items: oneOf: - type: string - type: integer - type: number - type: boolean - type: 'null' type: array - additionalProperties: oneOf: - type: string - type: integer - type: number - type: boolean - type: 'null' type: object type: object call_id: type: string tool_name: oneOf: - $ref: '#/components/schemas/BuiltinTool' - type: string required: - call_id - tool_name - arguments type: object ToolCallDelta: additionalProperties: false properties: content: oneOf: - type: string - $ref: '#/components/schemas/ToolCall' parse_status: $ref: '#/components/schemas/ToolCallParseStatus' type: const: tool_call default: tool_call type: string required: - type - content - parse_status type: object ToolCallParseStatus: enum: - started - in_progress - failed - succeeded type: string ToolChoice: enum: - auto - required type: string ToolDef: additionalProperties: false properties: description: type: string metadata: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object name: type: string parameters: items: $ref: '#/components/schemas/ToolParameter' type: array required: - name type: object ToolDefinition: additionalProperties: false properties: description: type: string parameters: additionalProperties: $ref: '#/components/schemas/ToolParamDefinition' type: object tool_name: oneOf: - $ref: '#/components/schemas/BuiltinTool' - type: string required: - tool_name type: object ToolExecutionStep: additionalProperties: false properties: completed_at: format: date-time type: string started_at: format: date-time type: string step_id: type: string step_type: const: tool_execution default: tool_execution type: string tool_calls: items: $ref: '#/components/schemas/ToolCall' type: array tool_responses: items: $ref: '#/components/schemas/ToolResponse' type: array turn_id: type: string required: - turn_id - step_id - step_type - tool_calls - tool_responses type: object ToolGroup: additionalProperties: false properties: args: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object identifier: type: string mcp_endpoint: $ref: '#/components/schemas/URL' provider_id: type: string provider_resource_id: type: string type: const: tool_group default: tool_group type: string required: - identifier - provider_resource_id - provider_id - type type: object ToolHost: enum: - distribution - client - model_context_protocol type: string ToolInvocationResult: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' error_code: type: integer error_message: type: string required: - content type: object ToolParamDefinition: additionalProperties: false properties: default: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object description: type: string param_type: type: string required: default: true type: boolean required: - param_type type: object ToolParameter: additionalProperties: false properties: default: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object description: type: string name: type: string parameter_type: type: string required: default: true type: boolean required: - name - parameter_type - description - required type: object ToolPromptFormat: description: "`json` --\n Refers to the json format for calling tools.\n\ \ The json format takes the form like\n {\n \"type\": \"function\"\ ,\n \"function\" : {\n \"name\": \"function_name\",\n \ \ \"description\": \"function_description\",\n \"parameters\"\ : {...}\n }\n }\n\n`function_tag` --\n This is an example of\ \ how you could define\n your own user defined format for making tool calls.\n\ \ The function_tag format looks like this,\n (parameters)\n\ \nThe detailed prompts for each of these formats are added to llama cli" enum: - json - function_tag - python_list title: This Enum refers to the prompt format for calling custom / zero shot tools type: string ToolResponse: additionalProperties: false properties: call_id: type: string content: $ref: '#/components/schemas/InterleavedContent' tool_name: oneOf: - $ref: '#/components/schemas/BuiltinTool' - type: string required: - call_id - tool_name - content type: object ToolResponseMessage: additionalProperties: false properties: call_id: type: string content: $ref: '#/components/schemas/InterleavedContent' role: const: tool default: tool type: string tool_name: oneOf: - $ref: '#/components/schemas/BuiltinTool' - type: string required: - role - call_id - tool_name - content type: object TopKSamplingStrategy: additionalProperties: false properties: top_k: type: integer type: const: top_k default: top_k type: string required: - type - top_k type: object TopPSamplingStrategy: additionalProperties: false properties: temperature: type: number top_p: default: 0.95 type: number type: const: top_p default: top_p type: string required: - type type: object Trace: additionalProperties: false properties: end_time: format: date-time type: string root_span_id: type: string start_time: format: date-time type: string trace_id: type: string required: - trace_id - root_span_id - start_time type: object TrainingConfig: additionalProperties: false properties: data_config: $ref: '#/components/schemas/DataConfig' dtype: default: bf16 type: string efficiency_config: $ref: '#/components/schemas/EfficiencyConfig' gradient_accumulation_steps: type: integer max_steps_per_epoch: type: integer max_validation_steps: type: integer n_epochs: type: integer optimizer_config: $ref: '#/components/schemas/OptimizerConfig' required: - n_epochs - max_steps_per_epoch - gradient_accumulation_steps - max_validation_steps - data_config - optimizer_config type: object Turn: additionalProperties: false properties: completed_at: format: date-time type: string input_messages: items: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/ToolResponseMessage' type: array output_attachments: items: additionalProperties: false properties: content: oneOf: - type: string - $ref: '#/components/schemas/InterleavedContentItem' - items: $ref: '#/components/schemas/InterleavedContentItem' type: array - $ref: '#/components/schemas/URL' mime_type: type: string required: - content - mime_type type: object type: array output_message: $ref: '#/components/schemas/CompletionMessage' session_id: type: string started_at: format: date-time type: string steps: items: oneOf: - $ref: '#/components/schemas/InferenceStep' - $ref: '#/components/schemas/ToolExecutionStep' - $ref: '#/components/schemas/ShieldCallStep' - $ref: '#/components/schemas/MemoryRetrievalStep' type: array turn_id: type: string required: - turn_id - session_id - input_messages - steps - output_message - output_attachments - started_at title: A single turn in an interaction with an Agentic System. type: object URL: additionalProperties: false properties: uri: type: string required: - uri type: object UnionType: additionalProperties: false properties: type: const: union default: union type: string required: - type type: object UnstructuredLogEvent: additionalProperties: false properties: attributes: additionalProperties: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object type: object message: type: string severity: $ref: '#/components/schemas/LogSeverity' span_id: type: string timestamp: format: date-time type: string trace_id: type: string type: const: unstructured_log default: unstructured_log type: string required: - trace_id - span_id - timestamp - type - message - severity type: object UserMessage: additionalProperties: false properties: content: $ref: '#/components/schemas/InterleavedContent' context: $ref: '#/components/schemas/InterleavedContent' role: const: user default: user type: string required: - role - content type: object VectorDB: additionalProperties: false properties: embedding_dimension: type: integer embedding_model: type: string identifier: type: string provider_id: type: string provider_resource_id: type: string type: const: vector_db default: vector_db type: string required: - identifier - provider_resource_id - provider_id - type - embedding_model - embedding_dimension type: object VersionInfo: additionalProperties: false properties: version: type: string required: - version type: object ViolationLevel: enum: - info - warn - error type: string info: description: "This is the specification of the Llama Stack that provides\n \ \ a set of endpoints and their corresponding interfaces that are tailored\ \ to\n best leverage Llama Models." title: Llama Stack Specification version: v1 jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema openapi: 3.1.0 paths: /v1/agents: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateAgentRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/AgentCreateResponse' description: OK tags: - Agents /v1/agents/{agent_id}: delete: parameters: - in: path name: agent_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK tags: - Agents /v1/agents/{agent_id}/session: post: parameters: - in: path name: agent_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateAgentSessionRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/AgentSessionCreateResponse' description: OK tags: - Agents /v1/agents/{agent_id}/session/{session_id}: delete: parameters: - in: path name: session_id required: true schema: type: string - in: path name: agent_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK tags: - Agents get: parameters: - in: path name: session_id required: true schema: type: string - in: path name: agent_id required: true schema: type: string - in: query name: turn_ids required: false schema: items: type: string type: array - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/Session' description: OK tags: - Agents /v1/agents/{agent_id}/session/{session_id}/turn: post: parameters: - in: path name: agent_id required: true schema: type: string - in: path name: session_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateAgentTurnRequest' required: true responses: '200': content: text/event-stream: schema: oneOf: - $ref: '#/components/schemas/Turn' - $ref: '#/components/schemas/AgentTurnResponseStreamChunk' description: A single turn in an interaction with an Agentic System. **OR** streamed agent turn completion response. tags: - Agents /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}: get: parameters: - in: path name: agent_id required: true schema: type: string - in: path name: session_id required: true schema: type: string - in: path name: turn_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/Turn' description: OK tags: - Agents /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}: get: parameters: - in: path name: agent_id required: true schema: type: string - in: path name: session_id required: true schema: type: string - in: path name: turn_id required: true schema: type: string - in: path name: step_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/AgentStepResponse' description: OK tags: - Agents /v1/batch-inference/chat-completion: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/BatchChatCompletionRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/BatchChatCompletionResponse' description: OK tags: - BatchInference (Coming Soon) /v1/batch-inference/completion: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/BatchCompletionRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/BatchCompletionResponse' description: OK tags: - BatchInference (Coming Soon) /v1/datasetio/rows: get: parameters: - in: query name: dataset_id required: true schema: type: string - in: query name: rows_in_page required: true schema: type: integer - in: query name: page_token required: false schema: type: string - in: query name: filter_condition required: false schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/PaginatedRowsResult' description: OK tags: - DatasetIO post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/AppendRowsRequest' required: true responses: '200': description: OK tags: - DatasetIO /v1/datasets: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListDatasetsResponse' description: OK tags: - Datasets post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterDatasetRequest' required: true responses: '200': description: OK tags: - Datasets /v1/datasets/{dataset_id}: delete: parameters: - in: path name: dataset_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK tags: - Datasets get: parameters: - in: path name: dataset_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/Dataset' - type: 'null' description: OK tags: - Datasets /v1/eval-tasks: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListEvalTasksResponse' description: OK tags: - EvalTasks post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterEvalTaskRequest' required: true responses: '200': description: OK tags: - EvalTasks /v1/eval-tasks/{eval_task_id}: get: parameters: - in: path name: eval_task_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/EvalTask' - type: 'null' description: OK tags: - EvalTasks /v1/eval/tasks/{task_id}/evaluations: post: parameters: - in: path name: task_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/EvaluateRowsRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/EvaluateResponse' description: OK tags: - Eval /v1/eval/tasks/{task_id}/jobs: post: parameters: - in: path name: task_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RunEvalRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/Job' description: OK tags: - Eval /v1/eval/tasks/{task_id}/jobs/{job_id}: delete: parameters: - in: path name: task_id required: true schema: type: string - in: path name: job_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK tags: - Eval get: parameters: - in: path name: task_id required: true schema: type: string - in: path name: job_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/JobStatus' - type: 'null' description: OK tags: - Eval /v1/eval/tasks/{task_id}/jobs/{job_id}/result: get: parameters: - in: path name: job_id required: true schema: type: string - in: path name: task_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/EvaluateResponse' description: OK tags: - Eval /v1/health: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/HealthInfo' description: OK tags: - Inspect /v1/inference/chat-completion: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' required: true responses: '200': content: text/event-stream: schema: oneOf: - $ref: '#/components/schemas/ChatCompletionResponse' - $ref: '#/components/schemas/ChatCompletionResponseStreamChunk' description: Chat completion response. **OR** SSE-stream of these events. tags: - Inference /v1/inference/completion: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/CompletionRequest' required: true responses: '200': content: text/event-stream: schema: oneOf: - $ref: '#/components/schemas/CompletionResponse' - $ref: '#/components/schemas/CompletionResponseStreamChunk' description: Completion response. **OR** streamed completion response. tags: - Inference /v1/inference/embeddings: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/EmbeddingsRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/EmbeddingsResponse' description: OK tags: - Inference /v1/inspect/providers: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListProvidersResponse' description: OK tags: - Inspect /v1/inspect/routes: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListRoutesResponse' description: OK tags: - Inspect /v1/models: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListModelsResponse' description: OK tags: - Models post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterModelRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/Model' description: OK tags: - Models /v1/models/{model_id}: delete: parameters: - in: path name: model_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK tags: - Models get: parameters: - in: path name: model_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/Model' - type: 'null' description: OK tags: - Models /v1/post-training/job/artifacts: get: parameters: - in: query name: job_uuid required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/PostTrainingJobArtifactsResponse' - type: 'null' description: OK tags: - PostTraining (Coming Soon) /v1/post-training/job/cancel: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/CancelTrainingJobRequest' required: true responses: '200': description: OK tags: - PostTraining (Coming Soon) /v1/post-training/job/status: get: parameters: - in: query name: job_uuid required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/PostTrainingJobStatusResponse' - type: 'null' description: OK tags: - PostTraining (Coming Soon) /v1/post-training/jobs: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListPostTrainingJobsResponse' description: OK tags: - PostTraining (Coming Soon) /v1/post-training/preference-optimize: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/PreferenceOptimizeRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/PostTrainingJob' description: OK tags: - PostTraining (Coming Soon) /v1/post-training/supervised-fine-tune: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/SupervisedFineTuneRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/PostTrainingJob' description: OK tags: - PostTraining (Coming Soon) /v1/safety/run-shield: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RunShieldRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/RunShieldResponse' description: OK tags: - Safety /v1/scoring-functions: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListScoringFunctionsResponse' description: OK tags: - ScoringFunctions post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterScoringFunctionRequest' required: true responses: '200': description: OK tags: - ScoringFunctions /v1/scoring-functions/{scoring_fn_id}: get: parameters: - in: path name: scoring_fn_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/ScoringFn' - type: 'null' description: OK tags: - ScoringFunctions /v1/scoring/score: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/ScoreRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/ScoreResponse' description: OK tags: - Scoring /v1/scoring/score-batch: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/ScoreBatchRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/ScoreBatchResponse' description: OK tags: - Scoring /v1/shields: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListShieldsResponse' description: OK tags: - Shields post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterShieldRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/Shield' description: OK tags: - Shields /v1/shields/{identifier}: get: parameters: - in: path name: identifier required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/Shield' - type: 'null' description: OK tags: - Shields /v1/synthetic-data-generation/generate: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/SyntheticDataGenerateRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/SyntheticDataGenerationResponse' description: OK tags: - SyntheticDataGeneration (Coming Soon) /v1/telemetry/events: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/LogEventRequest' required: true responses: '200': description: OK tags: - Telemetry /v1/telemetry/spans: get: parameters: - in: query name: attribute_filters required: true schema: items: $ref: '#/components/schemas/QueryCondition' type: array - in: query name: attributes_to_return required: true schema: items: type: string type: array - in: query name: max_depth required: false schema: type: integer - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/QuerySpansResponse' description: OK tags: - Telemetry /v1/telemetry/spans/export: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/SaveSpansToDatasetRequest' required: true responses: '200': description: OK tags: - Telemetry /v1/telemetry/spans/{span_id}/tree: get: parameters: - in: path name: span_id required: true schema: type: string - in: query name: attributes_to_return required: false schema: items: type: string type: array - in: query name: max_depth required: false schema: type: integer - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/QuerySpanTreeResponse' description: OK tags: - Telemetry /v1/telemetry/traces: get: parameters: - in: query name: attribute_filters required: false schema: items: $ref: '#/components/schemas/QueryCondition' type: array - in: query name: limit required: false schema: type: integer - in: query name: offset required: false schema: type: integer - in: query name: order_by required: false schema: items: type: string type: array - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/QueryTracesResponse' description: OK tags: - Telemetry /v1/telemetry/traces/{trace_id}: get: parameters: - in: path name: trace_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/Trace' description: OK tags: - Telemetry /v1/telemetry/traces/{trace_id}/spans/{span_id}: get: parameters: - in: path name: trace_id required: true schema: type: string - in: path name: span_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/Span' description: OK tags: - Telemetry /v1/tool-runtime/invoke: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/InvokeToolRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/ToolInvocationResult' description: OK summary: Run a tool with the given arguments tags: - ToolRuntime /v1/tool-runtime/list-tools: get: parameters: - in: query name: tool_group_id required: false schema: type: string - in: query name: mcp_endpoint required: false schema: $ref: '#/components/schemas/URL' - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/jsonl: schema: $ref: '#/components/schemas/ToolDef' description: OK tags: - ToolRuntime /v1/tool-runtime/rag-tool/insert: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/InsertRequest' required: true responses: '200': description: OK summary: Index documents so they can be used by the RAG system tags: - ToolRuntime /v1/tool-runtime/rag-tool/query: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/QueryRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/RAGQueryResult' description: OK summary: Query the RAG system for context; typically invoked by the agent tags: - ToolRuntime /v1/toolgroups: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListToolGroupsResponse' description: OK summary: List tool groups with optional provider tags: - ToolGroups post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterToolGroupRequest' required: true responses: '200': description: OK summary: Register a tool group tags: - ToolGroups /v1/toolgroups/{toolgroup_id}: delete: parameters: - in: path name: toolgroup_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK summary: Unregister a tool group tags: - ToolGroups get: parameters: - in: path name: toolgroup_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ToolGroup' description: OK tags: - ToolGroups /v1/tools: get: parameters: - in: query name: toolgroup_id required: false schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListToolsResponse' description: OK summary: List tools with optional tool group tags: - ToolGroups /v1/tools/{tool_name}: get: parameters: - in: path name: tool_name required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/Tool' description: OK tags: - ToolGroups /v1/vector-dbs: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/ListVectorDBsResponse' description: OK tags: - VectorDBs post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/RegisterVectorDbRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/VectorDB' description: OK tags: - VectorDBs /v1/vector-dbs/{vector_db_id}: delete: parameters: - in: path name: vector_db_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': description: OK tags: - VectorDBs get: parameters: - in: path name: vector_db_id required: true schema: type: string - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: oneOf: - $ref: '#/components/schemas/VectorDB' - type: 'null' description: OK tags: - VectorDBs /v1/vector-io/insert: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/InsertChunksRequest' required: true responses: '200': description: OK tags: - VectorIO /v1/vector-io/query: post: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/QueryChunksRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/QueryChunksResponse' description: OK tags: - VectorIO /v1/version: get: parameters: - description: JSON-encoded provider data which will be made available to the adapter servicing the API in: header name: X-LlamaStack-Provider-Data required: false schema: type: string - description: Version of the client making the request. This is used to ensure that the client and server are compatible. in: header name: X-LlamaStack-Client-Version required: false schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/VersionInfo' description: OK tags: - Inspect security: - Default: [] servers: - url: http://any-hosted-llama-stack.com tags: - description: name: AgentCandidate - description: name: AgentConfig - description: name: AgentCreateResponse - description: name: AgentSessionCreateResponse - description: name: AgentStepResponse - description: name: AgentTool - description: name: AgentTurnInputType - description: 'Streamed agent execution response. ' name: AgentTurnResponseEvent - description: name: AgentTurnResponseStepCompletePayload - description: name: AgentTurnResponseStepProgressPayload - description: name: AgentTurnResponseStepStartPayload - description: 'streamed agent turn completion response. ' name: AgentTurnResponseStreamChunk - description: name: AgentTurnResponseTurnCompletePayload - description: name: AgentTurnResponseTurnStartPayload - name: Agents - description: name: AggregationFunctionType - description: name: AppEvalTaskConfig - description: name: AppendRowsRequest - description: name: ArrayType - description: name: BasicScoringFnParams - description: name: BatchChatCompletionRequest - description: name: BatchChatCompletionResponse - description: name: BatchCompletionRequest - description: name: BatchCompletionResponse - name: BatchInference (Coming Soon) - description: name: BenchmarkEvalTaskConfig - description: name: BooleanType - description: name: BuiltinTool - description: name: CancelTrainingJobRequest - description: name: ChatCompletionInputType - description: name: ChatCompletionRequest - description: 'Chat completion response. ' name: ChatCompletionResponse - description: 'Chat completion response event. ' name: ChatCompletionResponseEvent - description: name: ChatCompletionResponseEventType - description: 'SSE-stream of these events. ' name: ChatCompletionResponseStreamChunk - description: 'Checkpoint created during training runs ' name: Checkpoint - description: name: CompletionInputType - description: name: CompletionMessage - description: name: CompletionRequest - description: 'Completion response. ' name: CompletionResponse - description: 'streamed completion response. ' name: CompletionResponseStreamChunk - description: name: ContentDelta - description: name: CreateAgentRequest - description: name: CreateAgentSessionRequest - description: name: CreateAgentTurnRequest - description: name: DPOAlignmentConfig - description: name: DataConfig - description: name: Dataset - description: name: DatasetFormat - name: DatasetIO - name: Datasets - description: name: DefaultRAGQueryGeneratorConfig - description: name: EfficiencyConfig - description: name: EmbeddingsRequest - description: name: EmbeddingsResponse - name: Eval - description: name: EvalTask - name: EvalTasks - description: name: EvaluateResponse - description: name: EvaluateRowsRequest - description: name: GreedySamplingStrategy - description: name: HealthInfo - description: name: ImageContentItem - description: name: ImageDelta - name: Inference - description: name: InferenceStep - description: name: InsertChunksRequest - description: name: InsertRequest - name: Inspect - description: name: InterleavedContent - description: name: InterleavedContentItem - description: name: InvokeToolRequest - description: name: Job - description: name: JobStatus - description: name: JsonType - description: name: LLMAsJudgeScoringFnParams - description: name: LLMRAGQueryGeneratorConfig - description: name: ListDatasetsResponse - description: name: ListEvalTasksResponse - description: name: ListModelsResponse - description: name: ListPostTrainingJobsResponse - description: name: ListProvidersResponse - description: name: ListRoutesResponse - description: name: ListScoringFunctionsResponse - description: name: ListShieldsResponse - description: name: ListToolGroupsResponse - description: name: ListToolsResponse - description: name: ListVectorDBsResponse - description: name: LogEventRequest - description: name: LogSeverity - description: name: LoraFinetuningConfig - description: name: MemoryRetrievalStep - description: name: Message - description: name: MetricEvent - description: name: Model - description: name: ModelCandidate - description: name: ModelType - name: Models - description: name: NumberType - description: name: ObjectType - description: name: OptimizerConfig - description: name: OptimizerType - description: name: PaginatedRowsResult - description: name: ParamType - name: PostTraining (Coming Soon) - description: name: PostTrainingJob - description: 'Artifacts of a finetuning job. ' name: PostTrainingJobArtifactsResponse - description: 'Status of a finetuning job. ' name: PostTrainingJobStatusResponse - description: name: PreferenceOptimizeRequest - description: name: ProviderInfo - description: name: QATFinetuningConfig - description: name: QueryChunksRequest - description: name: QueryChunksResponse - description: name: QueryCondition - description: name: QueryConditionOp - description: name: QueryRequest - description: name: QuerySpanTreeResponse - description: name: QuerySpansResponse - description: name: QueryTracesResponse - description: name: RAGDocument - description: name: RAGQueryConfig - description: name: RAGQueryGeneratorConfig - description: name: RAGQueryResult - description: name: RegexParserScoringFnParams - description: name: RegisterDatasetRequest - description: name: RegisterEvalTaskRequest - description: name: RegisterModelRequest - description: name: RegisterScoringFunctionRequest - description: name: RegisterShieldRequest - description: name: RegisterToolGroupRequest - description: name: RegisterVectorDbRequest - description: name: ResponseFormat - description: name: RouteInfo - description: name: RunEvalRequest - description: name: RunShieldRequest - description: name: RunShieldResponse - name: Safety - description: name: SafetyViolation - description: name: SamplingParams - description: name: SaveSpansToDatasetRequest - description: name: ScoreBatchRequest - description: name: ScoreBatchResponse - description: name: ScoreRequest - description: name: ScoreResponse - name: Scoring - description: name: ScoringFn - name: ScoringFunctions - description: name: ScoringResult - description: 'A single session of an interaction with an Agentic System. ' name: Session - description: 'A safety shield resource that can be used to check content ' name: Shield - description: name: ShieldCallStep - name: Shields - description: name: Span - description: name: SpanEndPayload - description: name: SpanStartPayload - description: name: SpanStatus - description: name: SpanWithStatus - description: name: StopReason - description: name: StringType - description: name: StructuredLogEvent - description: name: SupervisedFineTuneRequest - description: name: SyntheticDataGenerateRequest - name: SyntheticDataGeneration (Coming Soon) - description: 'Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold. ' name: SyntheticDataGenerationResponse - description: name: SystemMessage - name: Telemetry - description: name: TextContentItem - description: name: TextDelta - description: name: TokenLogProbs - description: name: Tool - description: name: ToolCall - description: name: ToolCallDelta - description: name: ToolCallParseStatus - description: name: ToolChoice - description: name: ToolDef - description: name: ToolDefinition - description: name: ToolExecutionStep - description: name: ToolGroup - name: ToolGroups - description: name: ToolHost - description: name: ToolInvocationResult - description: name: ToolParamDefinition - description: name: ToolParameter - description: "This Enum refers to the prompt format for calling custom / zero shot\ \ tools\n\n`json` --\n Refers to the json format for calling tools.\n The\ \ json format takes the form like\n {\n \"type\": \"function\",\n \ \ \"function\" : {\n \"name\": \"function_name\",\n \ \ \"description\": \"function_description\",\n \"parameters\": {...}\n\ \ }\n }\n\n`function_tag` --\n This is an example of how you could\ \ define\n your own user defined format for making tool calls.\n The function_tag\ \ format looks like this,\n (parameters)\n\ \nThe detailed prompts for each of these formats are added to llama cli\n\n" name: ToolPromptFormat - description: name: ToolResponse - description: name: ToolResponseMessage - name: ToolRuntime - description: name: TopKSamplingStrategy - description: name: TopPSamplingStrategy - description: name: Trace - description: name: TrainingConfig - description: 'A single turn in an interaction with an Agentic System. ' name: Turn - description: name: URL - description: name: UnionType - description: name: UnstructuredLogEvent - description: name: UserMessage - description: name: VectorDB - name: VectorDBs - name: VectorIO - description: name: VersionInfo - description: name: ViolationLevel x-tagGroups: - name: Operations tags: - Agents - BatchInference (Coming Soon) - DatasetIO - Datasets - Eval - EvalTasks - Inference - Inspect - Models - PostTraining (Coming Soon) - Safety - Scoring - ScoringFunctions - Shields - SyntheticDataGeneration (Coming Soon) - Telemetry - ToolGroups - ToolRuntime - VectorDBs - VectorIO - name: Types tags: - AgentCandidate - AgentConfig - AgentCreateResponse - AgentSessionCreateResponse - AgentStepResponse - AgentTool - AgentTurnInputType - AgentTurnResponseEvent - AgentTurnResponseStepCompletePayload - AgentTurnResponseStepProgressPayload - AgentTurnResponseStepStartPayload - AgentTurnResponseStreamChunk - AgentTurnResponseTurnCompletePayload - AgentTurnResponseTurnStartPayload - AggregationFunctionType - AppEvalTaskConfig - AppendRowsRequest - ArrayType - BasicScoringFnParams - BatchChatCompletionRequest - BatchChatCompletionResponse - BatchCompletionRequest - BatchCompletionResponse - BenchmarkEvalTaskConfig - BooleanType - BuiltinTool - CancelTrainingJobRequest - ChatCompletionInputType - ChatCompletionRequest - ChatCompletionResponse - ChatCompletionResponseEvent - ChatCompletionResponseEventType - ChatCompletionResponseStreamChunk - Checkpoint - CompletionInputType - CompletionMessage - CompletionRequest - CompletionResponse - CompletionResponseStreamChunk - ContentDelta - CreateAgentRequest - CreateAgentSessionRequest - CreateAgentTurnRequest - DPOAlignmentConfig - DataConfig - Dataset - DatasetFormat - DefaultRAGQueryGeneratorConfig - EfficiencyConfig - EmbeddingsRequest - EmbeddingsResponse - EvalTask - EvaluateResponse - EvaluateRowsRequest - GreedySamplingStrategy - HealthInfo - ImageContentItem - ImageDelta - InferenceStep - InsertChunksRequest - InsertRequest - InterleavedContent - InterleavedContentItem - InvokeToolRequest - Job - JobStatus - JsonType - LLMAsJudgeScoringFnParams - LLMRAGQueryGeneratorConfig - ListDatasetsResponse - ListEvalTasksResponse - ListModelsResponse - ListPostTrainingJobsResponse - ListProvidersResponse - ListRoutesResponse - ListScoringFunctionsResponse - ListShieldsResponse - ListToolGroupsResponse - ListToolsResponse - ListVectorDBsResponse - LogEventRequest - LogSeverity - LoraFinetuningConfig - MemoryRetrievalStep - Message - MetricEvent - Model - ModelCandidate - ModelType - NumberType - ObjectType - OptimizerConfig - OptimizerType - PaginatedRowsResult - ParamType - PostTrainingJob - PostTrainingJobArtifactsResponse - PostTrainingJobStatusResponse - PreferenceOptimizeRequest - ProviderInfo - QATFinetuningConfig - QueryChunksRequest - QueryChunksResponse - QueryCondition - QueryConditionOp - QueryRequest - QuerySpanTreeResponse - QuerySpansResponse - QueryTracesResponse - RAGDocument - RAGQueryConfig - RAGQueryGeneratorConfig - RAGQueryResult - RegexParserScoringFnParams - RegisterDatasetRequest - RegisterEvalTaskRequest - RegisterModelRequest - RegisterScoringFunctionRequest - RegisterShieldRequest - RegisterToolGroupRequest - RegisterVectorDbRequest - ResponseFormat - RouteInfo - RunEvalRequest - RunShieldRequest - RunShieldResponse - SafetyViolation - SamplingParams - SaveSpansToDatasetRequest - ScoreBatchRequest - ScoreBatchResponse - ScoreRequest - ScoreResponse - ScoringFn - ScoringResult - Session - Shield - ShieldCallStep - Span - SpanEndPayload - SpanStartPayload - SpanStatus - SpanWithStatus - StopReason - StringType - StructuredLogEvent - SupervisedFineTuneRequest - SyntheticDataGenerateRequest - SyntheticDataGenerationResponse - SystemMessage - TextContentItem - TextDelta - TokenLogProbs - Tool - ToolCall - ToolCallDelta - ToolCallParseStatus - ToolChoice - ToolDef - ToolDefinition - ToolExecutionStep - ToolGroup - ToolHost - ToolInvocationResult - ToolParamDefinition - ToolParameter - ToolPromptFormat - ToolResponse - ToolResponseMessage - TopKSamplingStrategy - TopPSamplingStrategy - Trace - TrainingConfig - Turn - URL - UnionType - UnstructuredLogEvent - UserMessage - VectorDB - VersionInfo - ViolationLevel