diff --git a/docs/llama-stack-spec.html b/docs/llama-stack-spec.html deleted file mode 100644 index c4b9790ae..000000000 --- a/docs/llama-stack-spec.html +++ /dev/null @@ -1,6287 +0,0 @@ - - - - - - - OpenAPI specification - - - - - - - -
- - - diff --git a/docs/llama-stack-spec.yaml b/docs/llama-stack-spec.yaml deleted file mode 100644 index 171d7780c..000000000 --- a/docs/llama-stack-spec.yaml +++ /dev/null @@ -1,4010 +0,0 @@ -components: - responses: {} - schemas: - AgentConfig: - additionalProperties: false - properties: - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - instructions: - type: string - model: - type: string - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - sampling_params: - $ref: '#/components/schemas/SamplingParams' - tool_choice: - $ref: '#/components/schemas/ToolChoice' - tool_prompt_format: - $ref: '#/components/schemas/ToolPromptFormat' - tools: - items: - oneOf: - - $ref: '#/components/schemas/SearchToolDefinition' - - $ref: '#/components/schemas/WolframAlphaToolDefinition' - - $ref: '#/components/schemas/PhotogenToolDefinition' - - $ref: '#/components/schemas/CodeInterpreterToolDefinition' - - $ref: '#/components/schemas/FunctionCallToolDefinition' - - additionalProperties: false - properties: - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - max_chunks: - type: integer - max_tokens_in_context: - type: integer - memory_bank_configs: - items: - oneOf: - - additionalProperties: false - properties: - bank_id: - type: string - type: - const: vector - type: string - required: - - bank_id - - type - type: object - - additionalProperties: false - properties: - bank_id: - type: string - keys: - items: - type: string - type: array - type: - const: keyvalue - type: string - required: - - bank_id - - type - - keys - type: object - - additionalProperties: false - properties: - bank_id: - type: string - type: - const: keyword - type: string - required: - - bank_id - - type - type: object - - additionalProperties: false - properties: - bank_id: - type: string - entities: - items: - type: string - type: array - type: - const: graph - type: string - required: - - bank_id - - type - - entities - type: object - type: array - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - query_generator_config: - oneOf: - - additionalProperties: false - properties: - sep: - type: string - type: - const: default - type: string - required: - - type - - sep - type: object - - additionalProperties: false - properties: - model: - type: string - template: - type: string - type: - const: llm - type: string - required: - - type - - model - - template - type: object - - additionalProperties: false - properties: - type: - const: custom - type: string - required: - - type - type: object - type: - const: memory - type: string - required: - - type - - memory_bank_configs - - query_generator_config - - max_tokens_in_context - - max_chunks - type: object - type: array - required: - - model - - instructions - 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 - 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 - type: string - step_details: - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - step_type: - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - type: string - required: - - event_type - - step_type - - step_details - type: object - AgentTurnResponseStepProgressPayload: - additionalProperties: false - properties: - event_type: - const: step_progress - type: string - model_response_text_delta: - type: string - step_id: - type: string - step_type: - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - type: string - tool_call_delta: - $ref: '#/components/schemas/ToolCallDelta' - tool_response_text_delta: - type: string - required: - - event_type - - step_type - - step_id - type: object - AgentTurnResponseStepStartPayload: - additionalProperties: false - properties: - event_type: - const: 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 - type: object - AgentTurnResponseTurnCompletePayload: - additionalProperties: false - properties: - event_type: - const: turn_complete - type: string - turn: - $ref: '#/components/schemas/Turn' - required: - - event_type - - turn - type: object - AgentTurnResponseTurnStartPayload: - additionalProperties: false - properties: - event_type: - const: turn_start - type: string - turn_id: - type: string - required: - - event_type - - turn_id - type: object - Attachment: - additionalProperties: false - properties: - content: - oneOf: - - type: string - - items: - type: string - type: array - - $ref: '#/components/schemas/URL' - mime_type: - type: string - required: - - content - - mime_type - type: object - BatchChatCompletionRequest: - additionalProperties: false - properties: - logprobs: - additionalProperties: false - properties: - top_k: - type: integer - type: object - messages_batch: - items: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - 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: - oneOf: - - type: string - - items: - type: string - type: array - type: array - logprobs: - additionalProperties: false - properties: - top_k: - 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 - BuiltinShield: - enum: - - llama_guard - - code_scanner_guard - - third_party_shield - - injection_shield - - jailbreak_shield - type: string - BuiltinTool: - enum: - - brave_search - - wolfram_alpha - - photogen - - code_interpreter - type: string - CancelEvaluationJobRequest: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - CancelTrainingJobRequest: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - ChatCompletionRequest: - additionalProperties: false - properties: - logprobs: - additionalProperties: false - properties: - top_k: - type: integer - type: object - messages: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - type: array - model: - type: string - 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 - - 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: - oneOf: - - type: string - - $ref: '#/components/schemas/ToolCallDelta' - 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 - CodeInterpreterToolDefinition: - additionalProperties: false - properties: - enable_inline_code_execution: - type: boolean - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - remote_execution: - $ref: '#/components/schemas/RestAPIExecutionConfig' - type: - const: code_interpreter - type: string - required: - - type - - enable_inline_code_execution - type: object - CompletionMessage: - additionalProperties: false - properties: - content: - oneOf: - - type: string - - items: - type: string - type: array - role: - const: 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: - oneOf: - - type: string - - items: - type: string - type: array - logprobs: - additionalProperties: false - properties: - top_k: - type: integer - type: object - model: - type: string - sampling_params: - $ref: '#/components/schemas/SamplingParams' - stream: - type: boolean - required: - - model - - content - type: object - CompletionResponse: - additionalProperties: false - properties: - completion_message: - $ref: '#/components/schemas/CompletionMessage' - logprobs: - items: - $ref: '#/components/schemas/TokenLogProbs' - type: array - required: - - completion_message - 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 - CreateAgentRequest: - additionalProperties: false - properties: - agent_config: - $ref: '#/components/schemas/AgentConfig' - required: - - agent_config - type: object - CreateAgentSessionRequest: - additionalProperties: false - properties: - agent_id: - type: string - session_name: - type: string - required: - - agent_id - - session_name - type: object - CreateAgentTurnRequest: - additionalProperties: false - properties: - agent_id: - type: string - attachments: - items: - $ref: '#/components/schemas/Attachment' - type: array - messages: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - type: array - session_id: - type: string - stream: - type: boolean - required: - - agent_id - - session_id - - messages - type: object - CreateDatasetRequest: - additionalProperties: false - properties: - dataset: - $ref: '#/components/schemas/TrainEvalDataset' - uuid: - type: string - required: - - uuid - - dataset - type: object - CreateMemoryBankRequest: - additionalProperties: false - properties: - config: - oneOf: - - additionalProperties: false - properties: - chunk_size_in_tokens: - type: integer - embedding_model: - type: string - overlap_size_in_tokens: - type: integer - type: - const: vector - type: string - required: - - type - - embedding_model - - chunk_size_in_tokens - type: object - - additionalProperties: false - properties: - type: - const: keyvalue - type: string - required: - - type - type: object - - additionalProperties: false - properties: - type: - const: keyword - type: string - required: - - type - type: object - - additionalProperties: false - properties: - type: - const: graph - type: string - required: - - type - type: object - name: - type: string - url: - $ref: '#/components/schemas/URL' - required: - - name - - config - 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 - DeleteAgentsRequest: - additionalProperties: false - properties: - agent_id: - type: string - required: - - agent_id - type: object - DeleteAgentsSessionRequest: - additionalProperties: false - properties: - agent_id: - type: string - session_id: - type: string - required: - - agent_id - - session_id - type: object - DeleteDatasetRequest: - additionalProperties: false - properties: - dataset_uuid: - type: string - required: - - dataset_uuid - type: object - DeleteDocumentsRequest: - additionalProperties: false - properties: - bank_id: - type: string - document_ids: - items: - type: string - type: array - required: - - bank_id - - document_ids - type: object - DialogGenerations: - additionalProperties: false - properties: - dialog: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - type: array - sampled_generations: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - type: array - required: - - dialog - - sampled_generations - type: object - DoraFinetuningConfig: - 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 - rank: - type: integer - required: - - lora_attn_modules - - apply_lora_to_mlp - - apply_lora_to_output - - rank - - alpha - type: object - DropMemoryBankRequest: - additionalProperties: false - properties: - bank_id: - type: string - required: - - bank_id - type: object - EmbeddingsRequest: - additionalProperties: false - properties: - contents: - items: - oneOf: - - type: string - - items: - type: string - type: array - type: array - model: - type: string - required: - - model - - contents - type: object - EmbeddingsResponse: - additionalProperties: false - properties: - embeddings: - items: - items: - type: number - type: array - type: array - required: - - embeddings - type: object - EvaluateQuestionAnsweringRequest: - additionalProperties: false - properties: - metrics: - items: - enum: - - em - - f1 - type: string - type: array - required: - - metrics - type: object - EvaluateSummarizationRequest: - additionalProperties: false - properties: - metrics: - items: - enum: - - rouge - - bleu - type: string - type: array - required: - - metrics - type: object - EvaluateTextGenerationRequest: - additionalProperties: false - properties: - metrics: - items: - enum: - - perplexity - - rouge - - bleu - type: string - type: array - required: - - metrics - type: object - EvaluationJob: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - EvaluationJobArtifactsResponse: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - title: Artifacts of a evaluation job. - type: object - EvaluationJobLogStream: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - EvaluationJobStatusResponse: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - FinetuningAlgorithm: - enum: - - full - - lora - - qlora - - dora - type: string - FunctionCallToolDefinition: - additionalProperties: false - properties: - description: - type: string - function_name: - type: string - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - parameters: - additionalProperties: - $ref: '#/components/schemas/ToolParamDefinition' - type: object - remote_execution: - $ref: '#/components/schemas/RestAPIExecutionConfig' - type: - const: function_call - type: string - required: - - type - - function_name - - description - - parameters - type: object - GetAgentsSessionRequest: - additionalProperties: false - properties: - turn_ids: - items: - type: string - type: array - type: object - GetDocumentsRequest: - additionalProperties: false - properties: - document_ids: - items: - type: string - type: array - required: - - document_ids - 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 - type: string - turn_id: - type: string - required: - - turn_id - - step_id - - step_type - - model_response - type: object - InsertDocumentsRequest: - additionalProperties: false - properties: - bank_id: - type: string - documents: - items: - $ref: '#/components/schemas/MemoryBankDocument' - type: array - ttl_seconds: - type: integer - required: - - bank_id - - documents - type: object - LogEventRequest: - additionalProperties: false - properties: - event: - oneOf: - - $ref: '#/components/schemas/UnstructuredLogEvent' - - $ref: '#/components/schemas/MetricEvent' - - $ref: '#/components/schemas/StructuredLogEvent' - required: - - event - 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 - rank: - type: integer - required: - - lora_attn_modules - - apply_lora_to_mlp - - apply_lora_to_output - - rank - - alpha - type: object - MemoryBank: - additionalProperties: false - properties: - bank_id: - type: string - config: - oneOf: - - additionalProperties: false - properties: - chunk_size_in_tokens: - type: integer - embedding_model: - type: string - overlap_size_in_tokens: - type: integer - type: - const: vector - type: string - required: - - type - - embedding_model - - chunk_size_in_tokens - type: object - - additionalProperties: false - properties: - type: - const: keyvalue - type: string - required: - - type - type: object - - additionalProperties: false - properties: - type: - const: keyword - type: string - required: - - type - type: object - - additionalProperties: false - properties: - type: - const: graph - type: string - required: - - type - type: object - name: - type: string - url: - $ref: '#/components/schemas/URL' - required: - - bank_id - - name - - config - type: object - MemoryBankDocument: - additionalProperties: false - properties: - content: - oneOf: - - type: string - - items: - type: string - 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 - MemoryRetrievalStep: - additionalProperties: false - properties: - completed_at: - format: date-time - type: string - inserted_context: - oneOf: - - type: string - - items: - type: string - type: array - memory_bank_ids: - items: - type: string - type: array - started_at: - format: date-time - type: string - step_id: - type: string - step_type: - const: memory_retrieval - type: string - turn_id: - type: string - required: - - turn_id - - step_id - - step_type - - memory_bank_ids - - inserted_context - type: object - 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 - type: string - unit: - type: string - value: - oneOf: - - type: integer - - type: number - required: - - trace_id - - span_id - - timestamp - - type - - metric - - value - - unit - type: object - OnViolationAction: - enum: - - 0 - - 1 - - 2 - type: integer - OptimizerConfig: - additionalProperties: false - properties: - lr: - type: number - lr_min: - type: number - optimizer_type: - enum: - - adam - - adamw - - sgd - type: string - weight_decay: - type: number - required: - - optimizer_type - - lr - - lr_min - - weight_decay - type: object - PhotogenToolDefinition: - additionalProperties: false - properties: - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - remote_execution: - $ref: '#/components/schemas/RestAPIExecutionConfig' - type: - const: photogen - type: string - required: - - type - type: object - 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 - PostTrainingJobLogStream: - additionalProperties: false - properties: - job_uuid: - type: string - log_lines: - items: - type: string - type: array - required: - - job_uuid - - log_lines - title: Stream of logs from a finetuning job. - type: object - PostTrainingJobStatus: - enum: - - running - - completed - - failed - - scheduled - type: string - 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/PostTrainingJobStatus' - required: - - job_uuid - - status - - checkpoints - title: Status of a finetuning job. - type: object - PreferenceOptimizeRequest: - additionalProperties: false - properties: - algorithm: - $ref: '#/components/schemas/RLHFAlgorithm' - algorithm_config: - $ref: '#/components/schemas/DPOAlignmentConfig' - dataset: - $ref: '#/components/schemas/TrainEvalDataset' - finetuned_model: - $ref: '#/components/schemas/URL' - 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 - optimizer_config: - $ref: '#/components/schemas/OptimizerConfig' - training_config: - $ref: '#/components/schemas/TrainingConfig' - validation_dataset: - $ref: '#/components/schemas/TrainEvalDataset' - required: - - job_uuid - - finetuned_model - - dataset - - validation_dataset - - algorithm - - algorithm_config - - optimizer_config - - training_config - - hyperparam_search_config - - logger_config - type: object - QLoraFinetuningConfig: - 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 - rank: - type: integer - required: - - lora_attn_modules - - apply_lora_to_mlp - - apply_lora_to_output - - rank - - alpha - type: object - QueryDocumentsRequest: - additionalProperties: false - properties: - bank_id: - type: string - params: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - query: - oneOf: - - type: string - - items: - type: string - type: array - required: - - bank_id - - query - type: object - QueryDocumentsResponse: - additionalProperties: false - properties: - chunks: - items: - additionalProperties: false - properties: - content: - oneOf: - - type: string - - items: - type: string - type: array - document_id: - type: string - token_count: - type: integer - required: - - content - - token_count - - document_id - type: object - type: array - scores: - items: - type: number - type: array - required: - - chunks - - scores - type: object - RLHFAlgorithm: - enum: - - dpo - type: string - RestAPIExecutionConfig: - additionalProperties: false - properties: - body: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - headers: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - method: - $ref: '#/components/schemas/RestAPIMethod' - params: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - url: - $ref: '#/components/schemas/URL' - required: - - url - - method - type: object - RestAPIMethod: - enum: - - GET - - POST - - PUT - - DELETE - type: string - RewardScoreRequest: - additionalProperties: false - properties: - dialog_generations: - items: - $ref: '#/components/schemas/DialogGenerations' - type: array - model: - type: string - required: - - dialog_generations - - model - type: object - RewardScoringResponse: - additionalProperties: false - properties: - scored_generations: - items: - $ref: '#/components/schemas/ScoredDialogGenerations' - type: array - required: - - scored_generations - title: Response from the reward scoring. Batch of (prompt, response, score) - tuples that pass the threshold. - type: object - RunShieldResponse: - additionalProperties: false - properties: - responses: - items: - $ref: '#/components/schemas/ShieldResponse' - type: array - required: - - responses - type: object - RunShieldsRequest: - additionalProperties: false - properties: - messages: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - type: array - shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - required: - - messages - - shields - type: object - SamplingParams: - additionalProperties: false - properties: - max_tokens: - type: integer - repetition_penalty: - type: number - strategy: - $ref: '#/components/schemas/SamplingStrategy' - temperature: - type: number - top_k: - type: integer - top_p: - type: number - required: - - strategy - type: object - SamplingStrategy: - enum: - - greedy - - top_p - - top_k - type: string - ScoredDialogGenerations: - additionalProperties: false - properties: - dialog: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - type: array - scored_generations: - items: - $ref: '#/components/schemas/ScoredMessage' - type: array - required: - - dialog - - scored_generations - type: object - ScoredMessage: - additionalProperties: false - properties: - message: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - score: - type: number - required: - - message - - score - type: object - SearchToolDefinition: - additionalProperties: false - properties: - api_key: - type: string - engine: - enum: - - bing - - brave - type: string - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - remote_execution: - $ref: '#/components/schemas/RestAPIExecutionConfig' - type: - const: brave_search - type: string - required: - - type - - api_key - - engine - type: object - Session: - additionalProperties: false - properties: - memory_bank: - $ref: '#/components/schemas/MemoryBank' - 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 - ShieldCallStep: - additionalProperties: false - properties: - completed_at: - format: date-time - type: string - response: - $ref: '#/components/schemas/ShieldResponse' - started_at: - format: date-time - type: string - step_id: - type: string - step_type: - const: shield_call - type: string - turn_id: - type: string - required: - - turn_id - - step_id - - step_type - - response - type: object - ShieldDefinition: - additionalProperties: false - properties: - description: - type: string - execution_config: - $ref: '#/components/schemas/RestAPIExecutionConfig' - on_violation_action: - $ref: '#/components/schemas/OnViolationAction' - parameters: - additionalProperties: - $ref: '#/components/schemas/ToolParamDefinition' - type: object - shield_type: - oneOf: - - $ref: '#/components/schemas/BuiltinShield' - - type: string - required: - - shield_type - - on_violation_action - type: object - ShieldResponse: - additionalProperties: false - properties: - is_violation: - type: boolean - shield_type: - oneOf: - - $ref: '#/components/schemas/BuiltinShield' - - type: string - violation_return_message: - type: string - violation_type: - type: string - required: - - shield_type - - is_violation - type: object - SpanEndPayload: - additionalProperties: false - properties: - status: - $ref: '#/components/schemas/SpanStatus' - type: - const: 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 - type: string - required: - - type - - name - type: object - SpanStatus: - enum: - - ok - - error - type: string - StopReason: - enum: - - end_of_turn - - end_of_message - - out_of_tokens - type: string - 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 - type: string - required: - - trace_id - - span_id - - timestamp - - type - - payload - type: object - SupervisedFineTuneRequest: - additionalProperties: false - properties: - algorithm: - $ref: '#/components/schemas/FinetuningAlgorithm' - algorithm_config: - oneOf: - - $ref: '#/components/schemas/LoraFinetuningConfig' - - $ref: '#/components/schemas/QLoraFinetuningConfig' - - $ref: '#/components/schemas/DoraFinetuningConfig' - dataset: - $ref: '#/components/schemas/TrainEvalDataset' - 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 - optimizer_config: - $ref: '#/components/schemas/OptimizerConfig' - training_config: - $ref: '#/components/schemas/TrainingConfig' - validation_dataset: - $ref: '#/components/schemas/TrainEvalDataset' - required: - - job_uuid - - model - - dataset - - validation_dataset - - algorithm - - algorithm_config - - optimizer_config - - training_config - - hyperparam_search_config - - logger_config - type: object - SyntheticDataGenerateRequest: - additionalProperties: false - properties: - dialogs: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - 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: - $ref: '#/components/schemas/ScoredDialogGenerations' - 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: - oneOf: - - type: string - - items: - type: string - type: array - role: - const: system - type: string - required: - - role - - content - type: object - TokenLogProbs: - additionalProperties: false - properties: - logprobs_by_token: - additionalProperties: - type: number - type: object - required: - - logprobs_by_token - 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' - required: - - content - - parse_status - type: object - ToolCallParseStatus: - enum: - - started - - in_progress - - failure - - success - type: string - ToolChoice: - enum: - - auto - - required - type: string - 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 - 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 - ToolParamDefinition: - additionalProperties: false - properties: - description: - type: string - param_type: - type: string - required: - type: boolean - required: - - param_type - 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 - 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: - oneOf: - - type: string - - items: - type: string - type: array - 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: - oneOf: - - type: string - - items: - type: string - type: array - role: - const: ipython - type: string - tool_name: - oneOf: - - $ref: '#/components/schemas/BuiltinTool' - - type: string - required: - - role - - call_id - - tool_name - - content - 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 - TrainEvalDataset: - additionalProperties: false - properties: - columns: - additionalProperties: - $ref: '#/components/schemas/TrainEvalDatasetColumnType' - type: object - content_url: - $ref: '#/components/schemas/URL' - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - required: - - columns - - content_url - title: Dataset to be used for training or evaluating language models. - type: object - TrainEvalDatasetColumnType: - enum: - - dialog - - text - - media - - number - - json - type: string - TrainingConfig: - additionalProperties: false - properties: - batch_size: - type: integer - enable_activation_checkpointing: - type: boolean - fsdp_cpu_offload: - type: boolean - memory_efficient_fsdp_wrap: - type: boolean - n_epochs: - type: integer - n_iters: - type: integer - shuffle: - type: boolean - required: - - n_epochs - - batch_size - - shuffle - - n_iters - - enable_activation_checkpointing - - memory_efficient_fsdp_wrap - - fsdp_cpu_offload - 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: - $ref: '#/components/schemas/Attachment' - 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: - format: uri - pattern: ^(https?://|file://|data:) - type: string - 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 - type: string - required: - - trace_id - - span_id - - timestamp - - type - - message - - severity - type: object - UpdateDocumentsRequest: - additionalProperties: false - properties: - bank_id: - type: string - documents: - items: - $ref: '#/components/schemas/MemoryBankDocument' - type: array - required: - - bank_id - - documents - type: object - UserMessage: - additionalProperties: false - properties: - content: - oneOf: - - type: string - - items: - type: string - type: array - context: - oneOf: - - type: string - - items: - type: string - type: array - role: - const: user - type: string - required: - - role - - content - type: object - WolframAlphaToolDefinition: - additionalProperties: false - properties: - api_key: - type: string - input_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - output_shields: - items: - $ref: '#/components/schemas/ShieldDefinition' - type: array - remote_execution: - $ref: '#/components/schemas/RestAPIExecutionConfig' - type: - const: wolfram_alpha - type: string - required: - - type - - api_key - type: object -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. The specification is still in\ - \ draft and subject to change.\n Generated at 2024-09-20 13:32:23.841908" - title: '[DRAFT] Llama Stack Specification' - version: 0.0.1 -jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema -openapi: 3.1.0 -paths: - /agents/create: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - 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 - /agents/delete: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/DeleteAgentsRequest' - required: true - responses: - '200': - description: OK - tags: - - Agents - /agents/session/create: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - 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 - /agents/session/delete: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/DeleteAgentsSessionRequest' - required: true - responses: - '200': - description: OK - tags: - - Agents - /agents/session/get: - post: - parameters: - - in: query - name: agent_id - required: true - schema: - type: string - - in: query - 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-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/GetAgentsSessionRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Session' - description: OK - tags: - - Agents - /agents/step/get: - get: - parameters: - - in: query - name: agent_id - required: true - schema: - type: string - - in: query - name: turn_id - required: true - schema: - type: string - - in: query - 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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/AgentStepResponse' - description: OK - tags: - - Agents - /agents/turn/create: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentTurnRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/AgentTurnResponseStreamChunk' - description: OK - tags: - - Agents - /agents/turn/get: - get: - parameters: - - in: query - name: agent_id - required: true - schema: - type: string - - in: query - 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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Turn' - description: OK - tags: - - Agents - /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-ProviderData - 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 - /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-ProviderData - 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 - /datasets/create: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateDatasetRequest' - required: true - responses: - '200': - description: OK - tags: - - Datasets - /datasets/delete: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/DeleteDatasetRequest' - required: true - responses: - '200': - description: OK - tags: - - Datasets - /datasets/get: - get: - parameters: - - in: query - name: dataset_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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/TrainEvalDataset' - description: OK - tags: - - Datasets - /evaluate/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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluationJobArtifactsResponse' - description: OK - tags: - - Evaluations - /evaluate/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-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CancelEvaluationJobRequest' - required: true - responses: - '200': - description: OK - tags: - - Evaluations - /evaluate/job/logs: - 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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluationJobLogStream' - description: OK - tags: - - Evaluations - /evaluate/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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluationJobStatusResponse' - description: OK - tags: - - Evaluations - /evaluate/jobs: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/jsonl: - schema: - $ref: '#/components/schemas/EvaluationJob' - description: OK - tags: - - Evaluations - /evaluate/question_answering/: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateQuestionAnsweringRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluationJob' - description: OK - tags: - - Evaluations - /evaluate/summarization/: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateSummarizationRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluationJob' - description: OK - tags: - - Evaluations - /evaluate/text_generation/: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateTextGenerationRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluationJob' - description: OK - tags: - - Evaluations - /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-ProviderData - 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 - /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-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CompletionRequest' - required: true - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/CompletionResponse' - - $ref: '#/components/schemas/CompletionResponseStreamChunk' - description: Completion response. **OR** streamed completion response. - tags: - - Inference - /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-ProviderData - 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 - /memory_bank/documents/delete: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/DeleteDocumentsRequest' - required: true - responses: - '200': - description: OK - tags: - - Memory - /memory_bank/documents/get: - post: - parameters: - - in: query - name: bank_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-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/GetDocumentsRequest' - required: true - responses: - '200': - content: - application/jsonl: - schema: - $ref: '#/components/schemas/MemoryBankDocument' - description: OK - tags: - - Memory - /memory_bank/insert: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InsertDocumentsRequest' - required: true - responses: - '200': - description: OK - tags: - - Memory - /memory_bank/query: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryDocumentsRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/QueryDocumentsResponse' - description: OK - tags: - - Memory - /memory_bank/update: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/UpdateDocumentsRequest' - required: true - responses: - '200': - description: OK - tags: - - Memory - /memory_banks/create: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateMemoryBankRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/MemoryBank' - description: OK - tags: - - Memory - /memory_banks/drop: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/DropMemoryBankRequest' - required: true - responses: - '200': - content: - application/json: - schema: - type: string - description: OK - tags: - - Memory - /memory_banks/get: - get: - parameters: - - in: query - name: bank_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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/MemoryBank' - - type: 'null' - description: OK - tags: - - Memory - /memory_banks/list: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/jsonl: - schema: - $ref: '#/components/schemas/MemoryBank' - description: OK - tags: - - Memory - /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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJobArtifactsResponse' - description: OK - tags: - - PostTraining - /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-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CancelTrainingJobRequest' - required: true - responses: - '200': - description: OK - tags: - - PostTraining - /post_training/job/logs: - 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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJobLogStream' - description: OK - tags: - - PostTraining - /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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJobStatusResponse' - description: OK - tags: - - PostTraining - /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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/jsonl: - schema: - $ref: '#/components/schemas/PostTrainingJob' - description: OK - tags: - - PostTraining - /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-ProviderData - 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 - /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-ProviderData - 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 - /reward_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-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RewardScoreRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/RewardScoringResponse' - description: OK - tags: - - RewardScoring - /safety/run_shields: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RunShieldsRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/RunShieldResponse' - description: OK - tags: - - Safety - /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-ProviderData - 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 - /telemetry/get_trace: - get: - parameters: - - in: query - 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-ProviderData - required: false - schema: - type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Trace' - description: OK - tags: - - Telemetry - /telemetry/log_event: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-ProviderData - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/LogEventRequest' - required: true - responses: - '200': - description: OK - tags: - - Telemetry -security: -- Default: [] -servers: -- url: http://any-hosted-llama-stack.com -tags: -- name: BatchInference -- name: PostTraining -- name: Memory -- name: Evaluations -- name: Datasets -- name: SyntheticDataGeneration -- name: RewardScoring -- name: Agents -- name: Safety -- name: Inference -- name: Telemetry -- description: - name: BuiltinTool -- description: - name: CompletionMessage -- description: - name: SamplingParams -- description: - name: SamplingStrategy -- description: - name: StopReason -- description: - name: SystemMessage -- description: - name: ToolCall -- description: - name: ToolChoice -- description: - name: ToolDefinition -- description: - name: ToolParamDefinition -- 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: ToolResponseMessage -- description: - name: UserMessage -- description: - name: BatchChatCompletionRequest -- description: - name: BatchChatCompletionResponse -- description: - name: BatchCompletionRequest -- description: - name: BatchCompletionResponse -- description: - name: CancelEvaluationJobRequest -- description: - name: CancelTrainingJobRequest -- 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: - name: TokenLogProbs -- description: - name: ToolCallDelta -- description: - name: ToolCallParseStatus -- description: - name: CompletionRequest -- description: 'Completion response. - - - ' - name: CompletionResponse -- description: 'streamed completion response. - - - ' - name: CompletionResponseStreamChunk -- description: - name: AgentConfig -- description: - name: BuiltinShield -- description: - name: CodeInterpreterToolDefinition -- description: - name: FunctionCallToolDefinition -- description: - name: OnViolationAction -- description: - name: PhotogenToolDefinition -- description: - name: RestAPIExecutionConfig -- description: - name: RestAPIMethod -- description: - name: SearchToolDefinition -- description: - name: ShieldDefinition -- description: - name: URL -- description: - name: WolframAlphaToolDefinition -- description: - name: CreateAgentRequest -- description: - name: AgentCreateResponse -- description: - name: CreateAgentSessionRequest -- description: - name: AgentSessionCreateResponse -- description: - name: Attachment -- description: - name: CreateAgentTurnRequest -- description: 'Streamed agent execution response. - - - ' - name: AgentTurnResponseEvent -- description: - name: AgentTurnResponseStepCompletePayload -- description: - name: AgentTurnResponseStepProgressPayload -- description: - name: AgentTurnResponseStepStartPayload -- description: - name: AgentTurnResponseStreamChunk -- description: - name: AgentTurnResponseTurnCompletePayload -- description: - name: AgentTurnResponseTurnStartPayload -- description: - name: InferenceStep -- description: - name: MemoryRetrievalStep -- description: - name: ShieldCallStep -- description: - name: ShieldResponse -- description: - name: ToolExecutionStep -- description: - name: ToolResponse -- description: 'A single turn in an interaction with an Agentic System. - - - ' - name: Turn -- description: 'Dataset to be used for training or evaluating language models. - - - ' - name: TrainEvalDataset -- description: - name: TrainEvalDatasetColumnType -- description: - name: CreateDatasetRequest -- description: - name: CreateMemoryBankRequest -- description: - name: MemoryBank -- description: - name: DeleteAgentsRequest -- description: - name: DeleteAgentsSessionRequest -- description: - name: DeleteDatasetRequest -- description: - name: DeleteDocumentsRequest -- description: - name: DropMemoryBankRequest -- description: - name: EmbeddingsRequest -- description: - name: EmbeddingsResponse -- description: - name: EvaluateQuestionAnsweringRequest -- description: - name: EvaluationJob -- description: - name: EvaluateSummarizationRequest -- description: - name: EvaluateTextGenerationRequest -- description: - name: GetAgentsSessionRequest -- description: 'A single session of an interaction with an Agentic System. - - - ' - name: Session -- description: - name: AgentStepResponse -- description: - name: GetDocumentsRequest -- description: - name: MemoryBankDocument -- description: 'Artifacts of a evaluation job. - - - ' - name: EvaluationJobArtifactsResponse -- description: - name: EvaluationJobLogStream -- description: - name: EvaluationJobStatusResponse -- description: - name: Trace -- description: 'Checkpoint created during training runs - - - ' - name: Checkpoint -- description: 'Artifacts of a finetuning job. - - - ' - name: PostTrainingJobArtifactsResponse -- description: 'Stream of logs from a finetuning job. - - - ' - name: PostTrainingJobLogStream -- description: - name: PostTrainingJobStatus -- description: 'Status of a finetuning job. - - - ' - name: PostTrainingJobStatusResponse -- description: - name: PostTrainingJob -- description: - name: InsertDocumentsRequest -- description: - name: LogSeverity -- description: - name: MetricEvent -- description: - name: SpanEndPayload -- description: - name: SpanStartPayload -- description: - name: SpanStatus -- description: - name: StructuredLogEvent -- description: - name: UnstructuredLogEvent -- description: - name: LogEventRequest -- description: - name: DPOAlignmentConfig -- description: - name: OptimizerConfig -- description: - name: RLHFAlgorithm -- description: - name: TrainingConfig -- description: - name: PreferenceOptimizeRequest -- description: - name: QueryDocumentsRequest -- description: - name: QueryDocumentsResponse -- description: - name: DialogGenerations -- description: - name: RewardScoreRequest -- description: 'Response from the reward scoring. Batch of (prompt, response, score) - tuples that pass the threshold. - - - ' - name: RewardScoringResponse -- description: - name: ScoredDialogGenerations -- description: - name: ScoredMessage -- description: - name: RunShieldsRequest -- description: - name: RunShieldResponse -- description: - name: DoraFinetuningConfig -- description: - name: FinetuningAlgorithm -- description: - name: LoraFinetuningConfig -- description: - name: QLoraFinetuningConfig -- description: - name: SupervisedFineTuneRequest -- description: - name: SyntheticDataGenerateRequest -- description: 'Response from the synthetic data generation. Batch of (prompt, response, - score) tuples that pass the threshold. - - - ' - name: SyntheticDataGenerationResponse -- description: - name: UpdateDocumentsRequest -x-tagGroups: -- name: Operations - tags: - - Agents - - BatchInference - - Datasets - - Evaluations - - Inference - - Memory - - PostTraining - - RewardScoring - - Safety - - SyntheticDataGeneration - - Telemetry -- name: Types - tags: - - AgentConfig - - AgentCreateResponse - - AgentSessionCreateResponse - - AgentStepResponse - - AgentTurnResponseEvent - - AgentTurnResponseStepCompletePayload - - AgentTurnResponseStepProgressPayload - - AgentTurnResponseStepStartPayload - - AgentTurnResponseStreamChunk - - AgentTurnResponseTurnCompletePayload - - AgentTurnResponseTurnStartPayload - - Attachment - - BatchChatCompletionRequest - - BatchChatCompletionResponse - - BatchCompletionRequest - - BatchCompletionResponse - - BuiltinShield - - BuiltinTool - - CancelEvaluationJobRequest - - CancelTrainingJobRequest - - ChatCompletionRequest - - ChatCompletionResponse - - ChatCompletionResponseEvent - - ChatCompletionResponseEventType - - ChatCompletionResponseStreamChunk - - Checkpoint - - CodeInterpreterToolDefinition - - CompletionMessage - - CompletionRequest - - CompletionResponse - - CompletionResponseStreamChunk - - CreateAgentRequest - - CreateAgentSessionRequest - - CreateAgentTurnRequest - - CreateDatasetRequest - - CreateMemoryBankRequest - - DPOAlignmentConfig - - DeleteAgentsRequest - - DeleteAgentsSessionRequest - - DeleteDatasetRequest - - DeleteDocumentsRequest - - DialogGenerations - - DoraFinetuningConfig - - DropMemoryBankRequest - - EmbeddingsRequest - - EmbeddingsResponse - - EvaluateQuestionAnsweringRequest - - EvaluateSummarizationRequest - - EvaluateTextGenerationRequest - - EvaluationJob - - EvaluationJobArtifactsResponse - - EvaluationJobLogStream - - EvaluationJobStatusResponse - - FinetuningAlgorithm - - FunctionCallToolDefinition - - GetAgentsSessionRequest - - GetDocumentsRequest - - InferenceStep - - InsertDocumentsRequest - - LogEventRequest - - LogSeverity - - LoraFinetuningConfig - - MemoryBank - - MemoryBankDocument - - MemoryRetrievalStep - - MetricEvent - - OnViolationAction - - OptimizerConfig - - PhotogenToolDefinition - - PostTrainingJob - - PostTrainingJobArtifactsResponse - - PostTrainingJobLogStream - - PostTrainingJobStatus - - PostTrainingJobStatusResponse - - PreferenceOptimizeRequest - - QLoraFinetuningConfig - - QueryDocumentsRequest - - QueryDocumentsResponse - - RLHFAlgorithm - - RestAPIExecutionConfig - - RestAPIMethod - - RewardScoreRequest - - RewardScoringResponse - - RunShieldResponse - - RunShieldsRequest - - SamplingParams - - SamplingStrategy - - ScoredDialogGenerations - - ScoredMessage - - SearchToolDefinition - - Session - - ShieldCallStep - - ShieldDefinition - - ShieldResponse - - SpanEndPayload - - SpanStartPayload - - SpanStatus - - StopReason - - StructuredLogEvent - - SupervisedFineTuneRequest - - SyntheticDataGenerateRequest - - SyntheticDataGenerationResponse - - SystemMessage - - TokenLogProbs - - ToolCall - - ToolCallDelta - - ToolCallParseStatus - - ToolChoice - - ToolDefinition - - ToolExecutionStep - - ToolParamDefinition - - ToolPromptFormat - - ToolResponse - - ToolResponseMessage - - Trace - - TrainEvalDataset - - TrainEvalDatasetColumnType - - TrainingConfig - - Turn - - URL - - UnstructuredLogEvent - - UpdateDocumentsRequest - - UserMessage - - WolframAlphaToolDefinition