diff --git a/docs/_static/css/my_theme.css b/docs/_static/css/my_theme.css deleted file mode 100644 index 7dcd97c9b..000000000 --- a/docs/_static/css/my_theme.css +++ /dev/null @@ -1,136 +0,0 @@ -@import url("theme.css"); - -/* Horizontal Navigation Bar */ -.horizontal-nav { - background-color: #ffffff; - border-bottom: 1px solid #e5e5e5; - padding: 0; - position: fixed; - top: 0; - left: 0; - right: 0; - z-index: 1050; - height: 50px; - box-shadow: 0 2px 4px rgba(0,0,0,0.1); -} - -[data-theme="dark"] .horizontal-nav { - background-color: #1a1a1a; - border-bottom: 1px solid #333; -} - -.horizontal-nav .nav-container { - max-width: 1200px; - margin: 0 auto; - display: flex; - align-items: center; - justify-content: space-between; - padding: 0 20px; - height: 100%; -} - -.horizontal-nav .nav-brand { - font-size: 18px; - font-weight: 600; - color: #333; - text-decoration: none; -} - -[data-theme="dark"] .horizontal-nav .nav-brand { - color: #fff; -} - -.horizontal-nav .nav-links { - display: flex; - align-items: center; - gap: 30px; - list-style: none; - margin: 0; - padding: 0; -} - -.horizontal-nav .nav-links a { - color: #666; - text-decoration: none; - font-size: 14px; - font-weight: 500; - padding: 8px 12px; - border-radius: 6px; - transition: all 0.2s ease; -} - -.horizontal-nav .nav-links a:hover, -.horizontal-nav .nav-links a.active { - color: #333; - background-color: #f5f5f5; -} - -.horizontal-nav .nav-links a.active { - font-weight: 600; -} - -[data-theme="dark"] .horizontal-nav .nav-links a { - color: #ccc; -} - -[data-theme="dark"] .horizontal-nav .nav-links a:hover, -[data-theme="dark"] .horizontal-nav .nav-links a.active { - color: #fff; - background-color: #333; -} - -.horizontal-nav .nav-links .github-link { - display: flex; - align-items: center; - gap: 6px; -} - -.horizontal-nav .nav-links .github-icon { - width: 16px; - height: 16px; - fill: currentColor; -} - -/* Adjust main content to account for fixed nav */ -.wy-nav-side { - top: 50px; - height: calc(100vh - 50px); -} - -.wy-nav-content-wrap { - margin-top: 50px; -} - -.wy-nav-content { - max-width: 90%; -} - -.wy-nav-side { - /* background: linear-gradient(45deg, #2980B9, #16A085); */ - background: linear-gradient(90deg, #332735, #1b263c); -} - -.wy-side-nav-search { - background-color: transparent !important; -} - -.hide-title h1 { - display: none; -} - -h2, h3, h4 { - font-weight: normal; -} -html[data-theme="dark"] .rst-content div[class^="highlight"] { - background-color: #0b0b0b; -} -pre { - white-space: pre-wrap !important; - word-break: break-all; -} - -[data-theme="dark"] .mermaid { - background-color: #f4f4f6 !important; - border-radius: 6px; - padding: 0.5em; - } diff --git a/docs/_static/js/detect_theme.js b/docs/_static/js/detect_theme.js deleted file mode 100644 index 712565ef7..000000000 --- a/docs/_static/js/detect_theme.js +++ /dev/null @@ -1,32 +0,0 @@ -document.addEventListener("DOMContentLoaded", function () { - const prefersDark = window.matchMedia("(prefers-color-scheme: dark)").matches; - const htmlElement = document.documentElement; - - // Check if theme is saved in localStorage - const savedTheme = localStorage.getItem("sphinx-rtd-theme"); - - if (savedTheme) { - // Use the saved theme preference - htmlElement.setAttribute("data-theme", savedTheme); - document.body.classList.toggle("dark", savedTheme === "dark"); - } else { - // Fall back to system preference - const theme = prefersDark ? "dark" : "light"; - htmlElement.setAttribute("data-theme", theme); - document.body.classList.toggle("dark", theme === "dark"); - // Save initial preference - localStorage.setItem("sphinx-rtd-theme", theme); - } - - // Listen for theme changes from the existing toggle - const observer = new MutationObserver(function(mutations) { - mutations.forEach(function(mutation) { - if (mutation.attributeName === "data-theme") { - const currentTheme = htmlElement.getAttribute("data-theme"); - localStorage.setItem("sphinx-rtd-theme", currentTheme); - } - }); - }); - - observer.observe(htmlElement, { attributes: true }); -}); diff --git a/docs/_static/js/horizontal_nav.js b/docs/_static/js/horizontal_nav.js deleted file mode 100644 index c2384f9d5..000000000 --- a/docs/_static/js/horizontal_nav.js +++ /dev/null @@ -1,44 +0,0 @@ -// Horizontal Navigation Bar for Llama Stack Documentation -document.addEventListener('DOMContentLoaded', function() { - // Create the horizontal navigation HTML - const navHTML = ` - - `; - - // Insert the navigation at the beginning of the body - document.body.insertAdjacentHTML('afterbegin', navHTML); - - // Update navigation links based on current page - updateActiveNav(); -}); - -function updateActiveNav() { - const currentPath = window.location.pathname; - const navLinks = document.querySelectorAll('.horizontal-nav .nav-links a'); - - navLinks.forEach(link => { - // Remove any existing active classes - link.classList.remove('active'); - - // Add active class based on current path - if (currentPath === '/' && link.getAttribute('href') === '/') { - link.classList.add('active'); - } else if (currentPath.includes('/references/api_reference/') && link.getAttribute('href').includes('api_reference')) { - link.classList.add('active'); - } - }); -} diff --git a/docs/_static/js/keyboard_shortcuts.js b/docs/_static/js/keyboard_shortcuts.js deleted file mode 100644 index 81d0b7c65..000000000 --- a/docs/_static/js/keyboard_shortcuts.js +++ /dev/null @@ -1,14 +0,0 @@ -document.addEventListener('keydown', function(event) { - // command+K or ctrl+K - if ((event.metaKey || event.ctrlKey) && event.key === 'k') { - event.preventDefault(); - document.querySelector('.search-input, .search-field, input[name="q"]').focus(); - } - - // forward slash - if (event.key === '/' && - !event.target.matches('input, textarea, select')) { - event.preventDefault(); - document.querySelector('.search-input, .search-field, input[name="q"]').focus(); - } -}); diff --git a/docs/_static/llama-stack-logo.png b/docs/_static/llama-stack-logo.png deleted file mode 100644 index 1899a0fc7..000000000 Binary files a/docs/_static/llama-stack-logo.png and /dev/null differ diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html deleted file mode 100644 index 9ddb070d7..000000000 --- a/docs/_static/llama-stack-spec.html +++ /dev/null @@ -1,18124 +0,0 @@ - - - - - - - OpenAPI specification - - - - - - - - - - - - - diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml deleted file mode 100644 index 94dc5c0f9..000000000 --- a/docs/_static/llama-stack-spec.yaml +++ /dev/null @@ -1,13450 +0,0 @@ -openapi: 3.1.0 -info: - title: Llama Stack Specification - version: v1 - description: >- - This is the specification of the Llama Stack that provides - a set of endpoints and their corresponding interfaces that are - tailored to - best leverage Llama Models. -servers: - - url: http://any-hosted-llama-stack.com -paths: - /v1/datasetio/append-rows/{dataset_id}: - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - DatasetIO - description: Append rows to a dataset. - parameters: - - name: dataset_id - in: path - description: >- - The ID of the dataset to append the rows to. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/AppendRowsRequest' - required: true - /v1/inference/batch-chat-completion: - post: - responses: - '200': - description: >- - A BatchChatCompletionResponse with the full completions. - content: - application/json: - schema: - $ref: '#/components/schemas/BatchChatCompletionResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Generate chat completions for a batch of messages using the specified model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/BatchChatCompletionRequest' - required: true - /v1/inference/batch-completion: - post: - responses: - '200': - description: >- - A BatchCompletionResponse with the full completions. - content: - application/json: - schema: - $ref: '#/components/schemas/BatchCompletionResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Generate completions for a batch of content using the specified model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/BatchCompletionRequest' - required: true - /v1/post-training/job/cancel: - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - PostTraining (Coming Soon) - description: Cancel a training job. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CancelTrainingJobRequest' - required: true - /v1/inference/chat-completion: - post: - responses: - '200': - description: >- - If stream=False, returns a ChatCompletionResponse with the full completion. - If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk. - content: - application/json: - schema: - $ref: '#/components/schemas/ChatCompletionResponse' - text/event-stream: - schema: - $ref: '#/components/schemas/ChatCompletionResponseStreamChunk' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - BatchInference (Coming Soon) - description: >- - Generate a chat completion for the given messages using the specified model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ChatCompletionRequest' - required: true - /v1/inference/completion: - post: - responses: - '200': - description: >- - If stream=False, returns a CompletionResponse with the full completion. - If stream=True, returns an SSE event stream of CompletionResponseStreamChunk. - content: - application/json: - schema: - $ref: '#/components/schemas/CompletionResponse' - text/event-stream: - schema: - $ref: '#/components/schemas/CompletionResponseStreamChunk' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - BatchInference (Coming Soon) - description: >- - Generate a completion for the given content using the specified model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CompletionRequest' - required: true - /v1/agents: - get: - responses: - '200': - description: A PaginatedResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/PaginatedResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: List all agents. - parameters: - - name: start_index - in: query - description: The index to start the pagination from. - required: false - schema: - type: integer - - name: limit - in: query - description: The number of agents to return. - required: false - schema: - type: integer - post: - responses: - '200': - description: >- - An AgentCreateResponse with the agent ID. - content: - application/json: - schema: - $ref: '#/components/schemas/AgentCreateResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: >- - Create an agent with the given configuration. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentRequest' - required: true - /v1/agents/{agent_id}/session: - post: - responses: - '200': - description: An AgentSessionCreateResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/AgentSessionCreateResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Create a new session for an agent. - parameters: - - name: agent_id - in: path - description: >- - The ID of the agent to create the session for. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentSessionRequest' - required: true - /v1/agents/{agent_id}/session/{session_id}/turn: - post: - responses: - '200': - description: >- - If stream=False, returns a Turn object. If stream=True, returns an SSE - event stream of AgentTurnResponseStreamChunk. - content: - application/json: - schema: - $ref: '#/components/schemas/Turn' - text/event-stream: - schema: - $ref: '#/components/schemas/AgentTurnResponseStreamChunk' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Create a new turn for an agent. - parameters: - - name: agent_id - in: path - description: >- - The ID of the agent to create the turn for. - required: true - schema: - type: string - - name: session_id - in: path - description: >- - The ID of the session to create the turn for. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentTurnRequest' - required: true - /v1/openai/v1/responses: - get: - responses: - '200': - description: A ListOpenAIResponseObject. - content: - application/json: - schema: - $ref: '#/components/schemas/ListOpenAIResponseObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: List all OpenAI responses. - parameters: - - name: after - in: query - description: The ID of the last response to return. - required: false - schema: - type: string - - name: limit - in: query - description: The number of responses to return. - required: false - schema: - type: integer - - name: model - in: query - description: The model to filter responses by. - required: false - schema: - type: string - - name: order - in: query - description: >- - The order to sort responses by when sorted by created_at ('asc' or 'desc'). - required: false - schema: - $ref: '#/components/schemas/Order' - post: - responses: - '200': - description: An OpenAIResponseObject. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIResponseObject' - text/event-stream: - schema: - $ref: '#/components/schemas/OpenAIResponseObjectStream' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Create a new OpenAI response. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateOpenaiResponseRequest' - required: true - /v1/prompts: - get: - responses: - '200': - description: >- - A ListPromptsResponse containing all prompts. - content: - application/json: - schema: - $ref: '#/components/schemas/ListPromptsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: List all prompts. - parameters: [] - post: - responses: - '200': - description: The created Prompt resource. - content: - application/json: - schema: - $ref: '#/components/schemas/Prompt' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: Create a new prompt. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreatePromptRequest' - required: true - /v1/agents/{agent_id}: - get: - responses: - '200': - description: An Agent of the agent. - content: - application/json: - schema: - $ref: '#/components/schemas/Agent' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Describe an agent by its ID. - parameters: - - name: agent_id - in: path - description: ID of the agent. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: >- - Delete an agent by its ID and its associated sessions and turns. - parameters: - - name: agent_id - in: path - description: The ID of the agent to delete. - required: true - schema: - type: string - /v1/agents/{agent_id}/session/{session_id}: - get: - responses: - '200': - description: A Session. - content: - application/json: - schema: - $ref: '#/components/schemas/Session' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Retrieve an agent session by its ID. - parameters: - - name: session_id - in: path - description: The ID of the session to get. - required: true - schema: - type: string - - name: agent_id - in: path - description: >- - The ID of the agent to get the session for. - required: true - schema: - type: string - - name: turn_ids - in: query - description: >- - (Optional) List of turn IDs to filter the session by. - required: false - schema: - type: array - items: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: >- - Delete an agent session by its ID and its associated turns. - parameters: - - name: session_id - in: path - description: The ID of the session to delete. - required: true - schema: - type: string - - name: agent_id - in: path - description: >- - The ID of the agent to delete the session for. - required: true - schema: - type: string - /v1/openai/v1/responses/{response_id}: - get: - responses: - '200': - description: An OpenAIResponseObject. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIResponseObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Retrieve an OpenAI response by its ID. - parameters: - - name: response_id - in: path - description: >- - The ID of the OpenAI response to retrieve. - required: true - schema: - type: string - delete: - responses: - '200': - description: An OpenAIDeleteResponseObject - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIDeleteResponseObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Delete an OpenAI response by its ID. - parameters: - - name: response_id - in: path - description: The ID of the OpenAI response to delete. - required: true - schema: - type: string - /v1/prompts/{prompt_id}: - get: - responses: - '200': - description: A Prompt resource. - content: - application/json: - schema: - $ref: '#/components/schemas/Prompt' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: >- - Get a prompt by its identifier and optional version. - parameters: - - name: prompt_id - in: path - description: The identifier of the prompt to get. - required: true - schema: - type: string - - name: version - in: query - description: >- - The version of the prompt to get (defaults to latest). - required: false - schema: - type: integer - post: - responses: - '200': - description: >- - The updated Prompt resource with incremented version. - content: - application/json: - schema: - $ref: '#/components/schemas/Prompt' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: >- - Update an existing prompt (increments version). - parameters: - - name: prompt_id - in: path - description: The identifier of the prompt to update. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/UpdatePromptRequest' - required: true - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: Delete a prompt. - parameters: - - name: prompt_id - in: path - description: The identifier of the prompt to delete. - required: true - schema: - type: string - /v1/inference/embeddings: - post: - responses: - '200': - description: >- - An array of embeddings, one for each content. Each embedding is a list - of floats. The dimensionality of the embedding is model-specific; you - can check model metadata using /models/{model_id}. - content: - application/json: - schema: - $ref: '#/components/schemas/EmbeddingsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Generate embeddings for content pieces using the specified model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EmbeddingsRequest' - required: true - /v1/eval/benchmarks/{benchmark_id}/evaluations: - post: - responses: - '200': - description: >- - EvaluateResponse object containing generations and scores. - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Eval - description: Evaluate a list of rows on a benchmark. - parameters: - - name: benchmark_id - in: path - description: >- - The ID of the benchmark to run the evaluation on. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateRowsRequest' - required: true - /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}: - get: - responses: - '200': - description: An AgentStepResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/AgentStepResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Retrieve an agent step by its ID. - parameters: - - name: agent_id - in: path - description: The ID of the agent to get the step for. - required: true - schema: - type: string - - name: session_id - in: path - description: >- - The ID of the session to get the step for. - required: true - schema: - type: string - - name: turn_id - in: path - description: The ID of the turn to get the step for. - required: true - schema: - type: string - - name: step_id - in: path - description: The ID of the step to get. - required: true - schema: - type: string - /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}: - get: - responses: - '200': - description: A Turn. - content: - application/json: - schema: - $ref: '#/components/schemas/Turn' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: Retrieve an agent turn by its ID. - parameters: - - name: agent_id - in: path - description: The ID of the agent to get the turn for. - required: true - schema: - type: string - - name: session_id - in: path - description: >- - The ID of the session to get the turn for. - required: true - schema: - type: string - - name: turn_id - in: path - description: The ID of the turn to get. - required: true - schema: - type: string - /v1/eval/benchmarks/{benchmark_id}: - get: - responses: - '200': - description: A Benchmark. - content: - application/json: - schema: - $ref: '#/components/schemas/Benchmark' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Benchmarks - description: Get a benchmark by its ID. - parameters: - - name: benchmark_id - in: path - description: The ID of the benchmark to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Benchmarks - description: Unregister a benchmark. - parameters: - - name: benchmark_id - in: path - description: The ID of the benchmark to unregister. - required: true - schema: - type: string - /v1/openai/v1/chat/completions/{completion_id}: - get: - responses: - '200': - description: A OpenAICompletionWithInputMessages. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAICompletionWithInputMessages' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: Describe a chat completion by its ID. - parameters: - - name: completion_id - in: path - description: ID of the chat completion. - required: true - schema: - type: string - /v1/datasets/{dataset_id}: - get: - responses: - '200': - description: A Dataset. - content: - application/json: - schema: - $ref: '#/components/schemas/Dataset' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Datasets - description: Get a dataset by its ID. - parameters: - - name: dataset_id - in: path - description: The ID of the dataset to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Datasets - description: Unregister a dataset by its ID. - parameters: - - name: dataset_id - in: path - description: The ID of the dataset to unregister. - required: true - schema: - type: string - /v1/models/{model_id}: - get: - responses: - '200': - description: A Model. - content: - application/json: - schema: - $ref: '#/components/schemas/Model' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Models - description: Get a model by its identifier. - parameters: - - name: model_id - in: path - description: The identifier of the model to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Models - description: Unregister a model. - parameters: - - name: model_id - in: path - description: >- - The identifier of the model to unregister. - required: true - schema: - type: string - /v1/scoring-functions/{scoring_fn_id}: - get: - responses: - '200': - description: A ScoringFn. - content: - application/json: - schema: - $ref: '#/components/schemas/ScoringFn' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ScoringFunctions - description: Get a scoring function by its ID. - parameters: - - name: scoring_fn_id - in: path - description: The ID of the scoring function to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ScoringFunctions - description: Unregister a scoring function. - parameters: - - name: scoring_fn_id - in: path - description: >- - The ID of the scoring function to unregister. - required: true - schema: - type: string - /v1/shields/{identifier}: - get: - responses: - '200': - description: A Shield. - content: - application/json: - schema: - $ref: '#/components/schemas/Shield' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Shields - description: Get a shield by its identifier. - parameters: - - name: identifier - in: path - description: The identifier of the shield to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Shields - description: Unregister a shield. - parameters: - - name: identifier - in: path - description: >- - The identifier of the shield to unregister. - required: true - schema: - type: string - /v1/telemetry/traces/{trace_id}/spans/{span_id}: - get: - responses: - '200': - description: A Span. - content: - application/json: - schema: - $ref: '#/components/schemas/Span' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Get a span by its ID. - parameters: - - name: trace_id - in: path - description: >- - The ID of the trace to get the span from. - required: true - schema: - type: string - - name: span_id - in: path - description: The ID of the span to get. - required: true - schema: - type: string - /v1/telemetry/spans/{span_id}/tree: - post: - responses: - '200': - description: A QuerySpanTreeResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/QuerySpanTreeResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Get a span tree by its ID. - parameters: - - name: span_id - in: path - description: The ID of the span to get the tree from. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/GetSpanTreeRequest' - required: true - /v1/tools/{tool_name}: - get: - responses: - '200': - description: A Tool. - content: - application/json: - schema: - $ref: '#/components/schemas/Tool' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolGroups - description: Get a tool by its name. - parameters: - - name: tool_name - in: path - description: The name of the tool to get. - required: true - schema: - type: string - /v1/toolgroups/{toolgroup_id}: - get: - responses: - '200': - description: A ToolGroup. - content: - application/json: - schema: - $ref: '#/components/schemas/ToolGroup' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolGroups - description: Get a tool group by its ID. - parameters: - - name: toolgroup_id - in: path - description: The ID of the tool group to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolGroups - description: Unregister a tool group. - parameters: - - name: toolgroup_id - in: path - description: The ID of the tool group to unregister. - required: true - schema: - type: string - /v1/telemetry/traces/{trace_id}: - get: - responses: - '200': - description: A Trace. - content: - application/json: - schema: - $ref: '#/components/schemas/Trace' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Get a trace by its ID. - parameters: - - name: trace_id - in: path - description: The ID of the trace to get. - required: true - schema: - type: string - /v1/post-training/job/artifacts: - get: - responses: - '200': - description: A PostTrainingJobArtifactsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJobArtifactsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - PostTraining (Coming Soon) - description: Get the artifacts of a training job. - parameters: - - name: job_uuid - in: query - description: >- - The UUID of the job to get the artifacts of. - required: true - schema: - type: string - /v1/post-training/job/status: - get: - responses: - '200': - description: A PostTrainingJobStatusResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJobStatusResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - PostTraining (Coming Soon) - description: Get the status of a training job. - parameters: - - name: job_uuid - in: query - description: >- - The UUID of the job to get the status of. - required: true - schema: - type: string - /v1/post-training/jobs: - get: - responses: - '200': - description: A ListPostTrainingJobsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListPostTrainingJobsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - PostTraining (Coming Soon) - description: Get all training jobs. - parameters: [] - /v1/vector-dbs/{vector_db_id}: - get: - responses: - '200': - description: A VectorDB. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorDB' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorDBs - description: Get a vector database by its identifier. - parameters: - - name: vector_db_id - in: path - description: >- - The identifier of the vector database to get. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorDBs - description: Unregister a vector database. - parameters: - - name: vector_db_id - in: path - description: >- - The identifier of the vector database to unregister. - required: true - schema: - type: string - /v1/health: - get: - responses: - '200': - description: >- - Health information indicating if the service is operational. - content: - application/json: - schema: - $ref: '#/components/schemas/HealthInfo' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inspect - description: >- - Get the current health status of the service. - parameters: [] - /v1/tool-runtime/rag-tool/insert: - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolRuntime - description: >- - Index documents so they can be used by the RAG system. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InsertRequest' - required: true - /v1/vector-io/insert: - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Insert chunks into a vector database. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InsertChunksRequest' - required: true - /v1/providers/{provider_id}: - get: - responses: - '200': - description: >- - A ProviderInfo object containing the provider's details. - content: - application/json: - schema: - $ref: '#/components/schemas/ProviderInfo' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Providers - description: >- - Get detailed information about a specific provider. - parameters: - - name: provider_id - in: path - description: The ID of the provider to inspect. - required: true - schema: - type: string - /v1/tool-runtime/invoke: - post: - responses: - '200': - description: A ToolInvocationResult. - content: - application/json: - schema: - $ref: '#/components/schemas/ToolInvocationResult' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolRuntime - description: Run a tool with the given arguments. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InvokeToolRequest' - required: true - /v1/datasetio/iterrows/{dataset_id}: - get: - responses: - '200': - description: A PaginatedResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/PaginatedResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - DatasetIO - description: >- - Get a paginated list of rows from a dataset. - - Uses offset-based pagination where: - - - start_index: The starting index (0-based). If None, starts from beginning. - - - limit: Number of items to return. If None or -1, returns all items. - - - The response includes: - - - data: List of items for the current page. - - - has_more: Whether there are more items available after this set. - parameters: - - name: dataset_id - in: path - description: >- - The ID of the dataset to get the rows from. - required: true - schema: - type: string - - name: start_index - in: query - description: >- - Index into dataset for the first row to get. Get all rows if None. - required: false - schema: - type: integer - - name: limit - in: query - description: The number of rows to get. - required: false - schema: - type: integer - /v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}: - get: - responses: - '200': - description: The status of the evaluation job. - content: - application/json: - schema: - $ref: '#/components/schemas/Job' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Eval - description: Get the status of a job. - parameters: - - name: benchmark_id - in: path - description: >- - The ID of the benchmark to run the evaluation on. - required: true - schema: - type: string - - name: job_id - in: path - description: The ID of the job to get the status of. - required: true - schema: - type: string - delete: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Eval - description: Cancel a job. - parameters: - - name: benchmark_id - in: path - description: >- - The ID of the benchmark to run the evaluation on. - required: true - schema: - type: string - - name: job_id - in: path - description: The ID of the job to cancel. - required: true - schema: - type: string - /v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result: - get: - responses: - '200': - description: The result of the job. - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Eval - description: Get the result of a job. - parameters: - - name: benchmark_id - in: path - description: >- - The ID of the benchmark to run the evaluation on. - required: true - schema: - type: string - - name: job_id - in: path - description: The ID of the job to get the result of. - required: true - schema: - type: string - /v1/agents/{agent_id}/sessions: - get: - responses: - '200': - description: A PaginatedResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/PaginatedResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: List all session(s) of a given agent. - parameters: - - name: agent_id - in: path - description: >- - The ID of the agent to list sessions for. - required: true - schema: - type: string - - name: start_index - in: query - description: The index to start the pagination from. - required: false - schema: - type: integer - - name: limit - in: query - description: The number of sessions to return. - required: false - schema: - type: integer - /v1/eval/benchmarks: - get: - responses: - '200': - description: A ListBenchmarksResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListBenchmarksResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Benchmarks - description: List all benchmarks. - parameters: [] - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Benchmarks - description: Register a benchmark. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterBenchmarkRequest' - required: true - /v1/openai/v1/chat/completions: - get: - responses: - '200': - description: A ListOpenAIChatCompletionResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListOpenAIChatCompletionResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: List all chat completions. - parameters: - - name: after - in: query - description: >- - The ID of the last chat completion to return. - required: false - schema: - type: string - - name: limit - in: query - description: >- - The maximum number of chat completions to return. - required: false - schema: - type: integer - - name: model - in: query - description: The model to filter by. - required: false - schema: - type: string - - name: order - in: query - description: >- - The order to sort the chat completions by: "asc" or "desc". Defaults to - "desc". - required: false - schema: - $ref: '#/components/schemas/Order' - post: - responses: - '200': - description: An OpenAIChatCompletion. - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/OpenAIChatCompletion' - - $ref: '#/components/schemas/OpenAIChatCompletionChunk' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Generate an OpenAI-compatible chat completion for the given messages using - the specified model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiChatCompletionRequest' - required: true - /v1/datasets: - get: - responses: - '200': - description: A ListDatasetsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListDatasetsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Datasets - description: List all datasets. - parameters: [] - post: - responses: - '200': - description: A Dataset. - content: - application/json: - schema: - $ref: '#/components/schemas/Dataset' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Datasets - description: Register a new dataset. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterDatasetRequest' - required: true - /v1/models: - get: - responses: - '200': - description: A ListModelsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListModelsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Models - description: List all models. - parameters: [] - post: - responses: - '200': - description: A Model. - content: - application/json: - schema: - $ref: '#/components/schemas/Model' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Models - description: Register a model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterModelRequest' - required: true - /v1/openai/v1/responses/{response_id}/input_items: - get: - responses: - '200': - description: An ListOpenAIResponseInputItem. - content: - application/json: - schema: - $ref: '#/components/schemas/ListOpenAIResponseInputItem' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: >- - List input items for a given OpenAI response. - parameters: - - name: response_id - in: path - description: >- - The ID of the response to retrieve input items for. - required: true - schema: - type: string - - name: after - in: query - description: >- - An item ID to list items after, used for pagination. - required: false - schema: - type: string - - name: before - in: query - description: >- - An item ID to list items before, used for pagination. - required: false - schema: - type: string - - name: include - in: query - description: >- - Additional fields to include in the response. - required: false - schema: - type: array - items: - type: string - - name: limit - in: query - description: >- - A limit on the number of objects to be returned. Limit can range between - 1 and 100, and the default is 20. - required: false - schema: - type: integer - - name: order - in: query - description: >- - The order to return the input items in. Default is desc. - required: false - schema: - $ref: '#/components/schemas/Order' - /v1/prompts/{prompt_id}/versions: - get: - responses: - '200': - description: >- - A ListPromptsResponse containing all versions of the prompt. - content: - application/json: - schema: - $ref: '#/components/schemas/ListPromptsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: List all versions of a specific prompt. - parameters: - - name: prompt_id - in: path - description: >- - The identifier of the prompt to list versions for. - required: true - schema: - type: string - /v1/providers: - get: - responses: - '200': - description: >- - A ListProvidersResponse containing information about all providers. - content: - application/json: - schema: - $ref: '#/components/schemas/ListProvidersResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Providers - description: List all available providers. - parameters: [] - /v1/inspect/routes: - get: - responses: - '200': - description: >- - Response containing information about all available routes. - content: - application/json: - schema: - $ref: '#/components/schemas/ListRoutesResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inspect - description: >- - List all available API routes with their methods and implementing providers. - parameters: [] - /v1/tool-runtime/list-tools: - get: - responses: - '200': - description: A ListToolDefsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListToolDefsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolRuntime - description: List all tools in the runtime. - parameters: - - name: tool_group_id - in: query - description: >- - The ID of the tool group to list tools for. - required: false - schema: - type: string - - name: mcp_endpoint - in: query - description: >- - The MCP endpoint to use for the tool group. - required: false - schema: - $ref: '#/components/schemas/URL' - /v1/scoring-functions: - get: - responses: - '200': - description: A ListScoringFunctionsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListScoringFunctionsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ScoringFunctions - description: List all scoring functions. - parameters: [] - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ScoringFunctions - description: Register a scoring function. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterScoringFunctionRequest' - required: true - /v1/shields: - get: - responses: - '200': - description: A ListShieldsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListShieldsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Shields - description: List all shields. - parameters: [] - post: - responses: - '200': - description: A Shield. - content: - application/json: - schema: - $ref: '#/components/schemas/Shield' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Shields - description: Register a shield. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterShieldRequest' - required: true - /v1/toolgroups: - get: - responses: - '200': - description: A ListToolGroupsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListToolGroupsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolGroups - description: List tool groups with optional provider. - parameters: [] - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolGroups - description: Register a tool group. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterToolGroupRequest' - required: true - /v1/tools: - get: - responses: - '200': - description: A ListToolsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListToolsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolGroups - description: List tools with optional tool group. - parameters: - - name: toolgroup_id - in: query - description: >- - The ID of the tool group to list tools for. - required: false - schema: - type: string - /v1/vector-dbs: - get: - responses: - '200': - description: A ListVectorDBsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ListVectorDBsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorDBs - description: List all vector databases. - parameters: [] - post: - responses: - '200': - description: A VectorDB. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorDB' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorDBs - description: Register a vector database. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterVectorDbRequest' - required: true - /v1/telemetry/events: - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Log an event. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/LogEventRequest' - required: true - /v1/openai/v1/vector_stores/{vector_store_id}/files: - get: - responses: - '200': - description: >- - A VectorStoreListFilesResponse containing the list of files. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreListFilesResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: List files in a vector store. - parameters: - - name: vector_store_id - in: path - description: >- - The ID of the vector store to list files from. - required: true - schema: - type: string - - name: limit - in: query - description: >- - (Optional) A limit on the number of objects to be returned. Limit can - range between 1 and 100, and the default is 20. - required: false - schema: - type: integer - - name: order - in: query - description: >- - (Optional) Sort order by the `created_at` timestamp of the objects. `asc` - for ascending order and `desc` for descending order. - required: false - schema: - type: string - - name: after - in: query - description: >- - (Optional) A cursor for use in pagination. `after` is an object ID that - defines your place in the list. - required: false - schema: - type: string - - name: before - in: query - description: >- - (Optional) A cursor for use in pagination. `before` is an object ID that - defines your place in the list. - required: false - schema: - type: string - - name: filter - in: query - description: >- - (Optional) Filter by file status to only return files with the specified - status. - required: false - schema: - $ref: '#/components/schemas/VectorStoreFileStatus' - post: - responses: - '200': - description: >- - A VectorStoreFileObject representing the attached file. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreFileObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Attach a file to a vector store. - parameters: - - name: vector_store_id - in: path - description: >- - The ID of the vector store to attach the file to. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiAttachFileToVectorStoreRequest' - required: true - /v1/openai/v1/completions: - post: - responses: - '200': - description: An OpenAICompletion. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAICompletion' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Generate an OpenAI-compatible completion for the given prompt using the specified - model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiCompletionRequest' - required: true - /v1/openai/v1/vector_stores: - get: - responses: - '200': - description: >- - A VectorStoreListResponse containing the list of vector stores. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreListResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Returns a list of vector stores. - parameters: - - name: limit - in: query - description: >- - A limit on the number of objects to be returned. Limit can range between - 1 and 100, and the default is 20. - required: false - schema: - type: integer - - name: order - in: query - description: >- - Sort order by the `created_at` timestamp of the objects. `asc` for ascending - order and `desc` for descending order. - required: false - schema: - type: string - - name: after - in: query - description: >- - A cursor for use in pagination. `after` is an object ID that defines your - place in the list. - required: false - schema: - type: string - - name: before - in: query - description: >- - A cursor for use in pagination. `before` is an object ID that defines - your place in the list. - required: false - schema: - type: string - post: - responses: - '200': - description: >- - A VectorStoreObject representing the created vector store. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Creates a vector store. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiCreateVectorStoreRequest' - required: true - /v1/openai/v1/files/{file_id}: - get: - responses: - '200': - description: >- - An OpenAIFileObject containing file information. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIFileObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Files - description: >- - Returns information about a specific file. - parameters: - - name: file_id - in: path - description: >- - The ID of the file to use for this request. - required: true - schema: - type: string - delete: - responses: - '200': - description: >- - An OpenAIFileDeleteResponse indicating successful deletion. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIFileDeleteResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Files - description: Delete a file. - parameters: - - name: file_id - in: path - description: >- - The ID of the file to use for this request. - required: true - schema: - type: string - /v1/openai/v1/vector_stores/{vector_store_id}: - get: - responses: - '200': - description: >- - A VectorStoreObject representing the vector store. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Retrieves a vector store. - parameters: - - name: vector_store_id - in: path - description: The ID of the vector store to retrieve. - required: true - schema: - type: string - post: - responses: - '200': - description: >- - A VectorStoreObject representing the updated vector store. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Updates a vector store. - parameters: - - name: vector_store_id - in: path - description: The ID of the vector store to update. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiUpdateVectorStoreRequest' - required: true - delete: - responses: - '200': - description: >- - A VectorStoreDeleteResponse indicating the deletion status. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreDeleteResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Delete a vector store. - parameters: - - name: vector_store_id - in: path - description: The ID of the vector store to delete. - required: true - schema: - type: string - /v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}: - get: - responses: - '200': - description: >- - A VectorStoreFileObject representing the file. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreFileObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Retrieves a vector store file. - parameters: - - name: vector_store_id - in: path - description: >- - The ID of the vector store containing the file to retrieve. - required: true - schema: - type: string - - name: file_id - in: path - description: The ID of the file to retrieve. - required: true - schema: - type: string - post: - responses: - '200': - description: >- - A VectorStoreFileObject representing the updated file. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreFileObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Updates a vector store file. - parameters: - - name: vector_store_id - in: path - description: >- - The ID of the vector store containing the file to update. - required: true - schema: - type: string - - name: file_id - in: path - description: The ID of the file to update. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiUpdateVectorStoreFileRequest' - required: true - delete: - responses: - '200': - description: >- - A VectorStoreFileDeleteResponse indicating the deletion status. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreFileDeleteResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Delete a vector store file. - parameters: - - name: vector_store_id - in: path - description: >- - The ID of the vector store containing the file to delete. - required: true - schema: - type: string - - name: file_id - in: path - description: The ID of the file to delete. - required: true - schema: - type: string - /v1/openai/v1/embeddings: - post: - responses: - '200': - description: >- - An OpenAIEmbeddingsResponse containing the embeddings. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIEmbeddingsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Generate OpenAI-compatible embeddings for the given input using the specified - model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiEmbeddingsRequest' - required: true - /v1/openai/v1/files: - get: - responses: - '200': - description: >- - An ListOpenAIFileResponse containing the list of files. - content: - application/json: - schema: - $ref: '#/components/schemas/ListOpenAIFileResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Files - description: >- - Returns a list of files that belong to the user's organization. - parameters: - - name: after - in: query - description: >- - A cursor for use in pagination. `after` is an object ID that defines your - place in the list. For instance, if you make a list request and receive - 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo - in order to fetch the next page of the list. - required: false - schema: - type: string - - name: limit - in: query - description: >- - A limit on the number of objects to be returned. Limit can range between - 1 and 10,000, and the default is 10,000. - required: false - schema: - type: integer - - name: order - in: query - description: >- - Sort order by the `created_at` timestamp of the objects. `asc` for ascending - order and `desc` for descending order. - required: false - schema: - $ref: '#/components/schemas/Order' - - name: purpose - in: query - description: >- - Only return files with the given purpose. - required: false - schema: - $ref: '#/components/schemas/OpenAIFilePurpose' - post: - responses: - '200': - description: >- - An OpenAIFileObject representing the uploaded file. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIFileObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Files - description: >- - Upload a file that can be used across various endpoints. - - The file upload should be a multipart form request with: - - - file: The File object (not file name) to be uploaded. - - - purpose: The intended purpose of the uploaded file. - - - expires_after: Optional form values describing expiration for the file. - Expected expires_after[anchor] = "created_at", expires_after[seconds] = . - Seconds must be between 3600 and 2592000 (1 hour to 30 days). - parameters: [] - requestBody: - content: - multipart/form-data: - schema: - type: object - properties: - file: - type: string - format: binary - purpose: - $ref: '#/components/schemas/OpenAIFilePurpose' - expires_after_anchor: - oneOf: - - type: string - - type: 'null' - expires_after_seconds: - oneOf: - - type: integer - - type: 'null' - required: - - file - - purpose - - expires_after_anchor - - expires_after_seconds - required: true - /v1/openai/v1/models: - get: - responses: - '200': - description: A OpenAIListModelsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/OpenAIListModelsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Models - description: List models using the OpenAI API. - parameters: [] - /v1/openai/v1/files/{file_id}/content: - get: - responses: - '200': - description: >- - The raw file content as a binary response. - content: - application/json: - schema: - $ref: '#/components/schemas/Response' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Files - description: >- - Returns the contents of the specified file. - parameters: - - name: file_id - in: path - description: >- - The ID of the file to use for this request. - required: true - schema: - type: string - /v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content: - get: - responses: - '200': - description: >- - A list of InterleavedContent representing the file contents. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreFileContentsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: >- - Retrieves the contents of a vector store file. - parameters: - - name: vector_store_id - in: path - description: >- - The ID of the vector store containing the file to retrieve. - required: true - schema: - type: string - - name: file_id - in: path - description: The ID of the file to retrieve. - required: true - schema: - type: string - /v1/openai/v1/vector_stores/{vector_store_id}/search: - post: - responses: - '200': - description: >- - A VectorStoreSearchResponse containing the search results. - content: - application/json: - schema: - $ref: '#/components/schemas/VectorStoreSearchResponsePage' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: >- - Search for chunks in a vector store. - - Searches a vector store for relevant chunks based on a query and optional - file attribute filters. - parameters: - - name: vector_store_id - in: path - description: The ID of the vector store to search. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/OpenaiSearchVectorStoreRequest' - required: true - /v1/post-training/preference-optimize: - post: - responses: - '200': - description: A PostTrainingJob. - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJob' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - PostTraining (Coming Soon) - description: Run preference optimization of a model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/PreferenceOptimizeRequest' - required: true - /v1/tool-runtime/rag-tool/query: - post: - responses: - '200': - description: >- - RAGQueryResult containing the retrieved content and metadata - content: - application/json: - schema: - $ref: '#/components/schemas/RAGQueryResult' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - ToolRuntime - description: >- - Query the RAG system for context; typically invoked by the agent. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryRequest' - required: true - /v1/vector-io/query: - post: - responses: - '200': - description: A QueryChunksResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/QueryChunksResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - VectorIO - description: Query chunks from a vector database. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryChunksRequest' - required: true - /v1/telemetry/metrics/{metric_name}: - post: - responses: - '200': - description: A QueryMetricsResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/QueryMetricsResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Query metrics. - parameters: - - name: metric_name - in: path - description: The name of the metric to query. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryMetricsRequest' - required: true - /v1/telemetry/spans: - post: - responses: - '200': - description: A QuerySpansResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/QuerySpansResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Query spans. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QuerySpansRequest' - required: true - /v1/telemetry/traces: - post: - responses: - '200': - description: A QueryTracesResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/QueryTracesResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Query traces. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryTracesRequest' - required: true - /v1/inference/rerank: - post: - responses: - '200': - description: >- - RerankResponse with indices sorted by relevance score (descending). - content: - application/json: - schema: - $ref: '#/components/schemas/RerankResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inference - description: >- - Rerank a list of documents based on their relevance to a query. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RerankRequest' - required: true - /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume: - post: - responses: - '200': - description: >- - A Turn object if stream is False, otherwise an AsyncIterator of AgentTurnResponseStreamChunk - objects. - content: - application/json: - schema: - $ref: '#/components/schemas/Turn' - text/event-stream: - schema: - $ref: '#/components/schemas/AgentTurnResponseStreamChunk' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Agents - description: >- - Resume an agent turn with executed tool call responses. - - When a Turn has the status `awaiting_input` due to pending input from client - side tool calls, this endpoint can be used to submit the outputs from the - tool calls once they are ready. - parameters: - - name: agent_id - in: path - description: The ID of the agent to resume. - required: true - schema: - type: string - - name: session_id - in: path - description: The ID of the session to resume. - required: true - schema: - type: string - - name: turn_id - in: path - description: The ID of the turn to resume. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ResumeAgentTurnRequest' - required: true - /v1/eval/benchmarks/{benchmark_id}/jobs: - post: - responses: - '200': - description: >- - The job that was created to run the evaluation. - content: - application/json: - schema: - $ref: '#/components/schemas/Job' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Eval - description: Run an evaluation on a benchmark. - parameters: - - name: benchmark_id - in: path - description: >- - The ID of the benchmark to run the evaluation on. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RunEvalRequest' - required: true - /v1/openai/v1/moderations: - post: - responses: - '200': - description: A moderation object. - content: - application/json: - schema: - $ref: '#/components/schemas/ModerationObject' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Safety - description: >- - Classifies if text and/or image inputs are potentially harmful. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RunModerationRequest' - required: true - /v1/safety/run-shield: - post: - responses: - '200': - description: A RunShieldResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/RunShieldResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Safety - description: Run a shield. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RunShieldRequest' - required: true - /v1/telemetry/spans/export: - post: - responses: - '200': - description: OK - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Telemetry - description: Save spans to a dataset. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SaveSpansToDatasetRequest' - required: true - /v1/scoring/score: - post: - responses: - '200': - description: >- - A ScoreResponse object containing rows and aggregated results. - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Scoring - description: Score a list of rows. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreRequest' - required: true - /v1/scoring/score-batch: - post: - responses: - '200': - description: A ScoreBatchResponse. - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreBatchResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Scoring - description: Score a batch of rows. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreBatchRequest' - required: true - /v1/prompts/{prompt_id}/set-default-version: - post: - responses: - '200': - description: >- - The prompt with the specified version now set as default. - content: - application/json: - schema: - $ref: '#/components/schemas/Prompt' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Prompts - description: >- - Set which version of a prompt should be the default in get_prompt (latest). - parameters: - - name: prompt_id - in: path - description: The identifier of the prompt. - required: true - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SetDefaultVersionRequest' - required: true - /v1/post-training/supervised-fine-tune: - post: - responses: - '200': - description: A PostTrainingJob. - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJob' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - PostTraining (Coming Soon) - description: Run supervised fine-tuning of a model. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SupervisedFineTuneRequest' - required: true - /v1/synthetic-data-generation/generate: - post: - responses: - '200': - description: >- - Response containing filtered synthetic data samples and optional statistics - content: - application/json: - schema: - $ref: '#/components/schemas/SyntheticDataGenerationResponse' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - SyntheticDataGeneration (Coming Soon) - description: >- - Generate synthetic data based on input dialogs and apply filtering. - parameters: [] - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SyntheticDataGenerateRequest' - required: true - /v1/version: - get: - responses: - '200': - description: >- - Version information containing the service version number. - content: - application/json: - schema: - $ref: '#/components/schemas/VersionInfo' - '400': - $ref: '#/components/responses/BadRequest400' - '429': - $ref: >- - #/components/responses/TooManyRequests429 - '500': - $ref: >- - #/components/responses/InternalServerError500 - default: - $ref: '#/components/responses/DefaultError' - tags: - - Inspect - description: Get the version of the service. - parameters: [] -jsonSchemaDialect: >- - https://json-schema.org/draft/2020-12/schema -components: - schemas: - Error: - type: object - properties: - status: - type: integer - description: HTTP status code - title: - type: string - description: >- - Error title, a short summary of the error which is invariant for an error - type - detail: - type: string - description: >- - Error detail, a longer human-readable description of the error - instance: - type: string - description: >- - (Optional) A URL which can be used to retrieve more information about - the specific occurrence of the error - additionalProperties: false - required: - - status - - title - - detail - title: Error - description: >- - Error response from the API. Roughly follows RFC 7807. - AppendRowsRequest: - type: object - properties: - rows: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The rows to append to the dataset. - additionalProperties: false - required: - - rows - title: AppendRowsRequest - CompletionMessage: - type: object - properties: - role: - type: string - const: assistant - default: assistant - description: >- - Must be "assistant" to identify this as the model's response - content: - $ref: '#/components/schemas/InterleavedContent' - description: The content of the model's response - stop_reason: - type: string - enum: - - end_of_turn - - end_of_message - - out_of_tokens - description: >- - Reason why the model stopped generating. Options are: - `StopReason.end_of_turn`: - The model finished generating the entire response. - `StopReason.end_of_message`: - The model finished generating but generated a partial response -- usually, - a tool call. The user may call the tool and continue the conversation - with the tool's response. - `StopReason.out_of_tokens`: The model ran - out of token budget. - tool_calls: - type: array - items: - $ref: '#/components/schemas/ToolCall' - description: >- - List of tool calls. Each tool call is a ToolCall object. - additionalProperties: false - required: - - role - - content - - stop_reason - title: CompletionMessage - description: >- - A message containing the model's (assistant) response in a chat conversation. - GrammarResponseFormat: - type: object - properties: - type: - type: string - enum: - - json_schema - - grammar - description: >- - Must be "grammar" to identify this format type - const: grammar - default: grammar - bnf: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The BNF grammar specification the response should conform to - additionalProperties: false - required: - - type - - bnf - title: GrammarResponseFormat - description: >- - Configuration for grammar-guided response generation. - GreedySamplingStrategy: - type: object - properties: - type: - type: string - const: greedy - default: greedy - description: >- - Must be "greedy" to identify this sampling strategy - additionalProperties: false - required: - - type - title: GreedySamplingStrategy - description: >- - Greedy sampling strategy that selects the highest probability token at each - step. - ImageContentItem: - type: object - properties: - type: - type: string - const: image - default: image - description: >- - Discriminator type of the content item. Always "image" - image: - type: object - properties: - url: - $ref: '#/components/schemas/URL' - description: >- - A URL of the image or data URL in the format of data:image/{type};base64,{data}. - Note that URL could have length limits. - data: - type: string - contentEncoding: base64 - description: base64 encoded image data as string - additionalProperties: false - description: >- - Image as a base64 encoded string or an URL - additionalProperties: false - required: - - type - - image - title: ImageContentItem - description: A image content item - InterleavedContent: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - type: array - items: - $ref: '#/components/schemas/InterleavedContentItem' - InterleavedContentItem: - oneOf: - - $ref: '#/components/schemas/ImageContentItem' - - $ref: '#/components/schemas/TextContentItem' - discriminator: - propertyName: type - mapping: - image: '#/components/schemas/ImageContentItem' - text: '#/components/schemas/TextContentItem' - JsonSchemaResponseFormat: - type: object - properties: - type: - type: string - enum: - - json_schema - - grammar - description: >- - Must be "json_schema" to identify this format type - const: json_schema - default: json_schema - json_schema: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The JSON schema the response should conform to. In a Python SDK, this - is often a `pydantic` model. - additionalProperties: false - required: - - type - - json_schema - title: JsonSchemaResponseFormat - description: >- - Configuration for JSON schema-guided response generation. - Message: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - discriminator: - propertyName: role - mapping: - user: '#/components/schemas/UserMessage' - system: '#/components/schemas/SystemMessage' - tool: '#/components/schemas/ToolResponseMessage' - assistant: '#/components/schemas/CompletionMessage' - ResponseFormat: - oneOf: - - $ref: '#/components/schemas/JsonSchemaResponseFormat' - - $ref: '#/components/schemas/GrammarResponseFormat' - discriminator: - propertyName: type - mapping: - json_schema: '#/components/schemas/JsonSchemaResponseFormat' - grammar: '#/components/schemas/GrammarResponseFormat' - SamplingParams: - type: object - properties: - strategy: - $ref: '#/components/schemas/SamplingStrategy' - description: The sampling strategy. - max_tokens: - type: integer - default: 0 - description: >- - The maximum number of tokens that can be generated in the completion. - The token count of your prompt plus max_tokens cannot exceed the model's - context length. - repetition_penalty: - type: number - default: 1.0 - description: >- - Number between -2.0 and 2.0. Positive values penalize new tokens based - on whether they appear in the text so far, increasing the model's likelihood - to talk about new topics. - stop: - type: array - items: - type: string - description: >- - Up to 4 sequences where the API will stop generating further tokens. The - returned text will not contain the stop sequence. - additionalProperties: false - required: - - strategy - title: SamplingParams - description: Sampling parameters. - SamplingStrategy: - oneOf: - - $ref: '#/components/schemas/GreedySamplingStrategy' - - $ref: '#/components/schemas/TopPSamplingStrategy' - - $ref: '#/components/schemas/TopKSamplingStrategy' - discriminator: - propertyName: type - mapping: - greedy: '#/components/schemas/GreedySamplingStrategy' - top_p: '#/components/schemas/TopPSamplingStrategy' - top_k: '#/components/schemas/TopKSamplingStrategy' - SystemMessage: - type: object - properties: - role: - type: string - const: system - default: system - description: >- - Must be "system" to identify this as a system message - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - The content of the "system prompt". If multiple system messages are provided, - they are concatenated. The underlying Llama Stack code may also add other - system messages (for example, for formatting tool definitions). - additionalProperties: false - required: - - role - - content - title: SystemMessage - description: >- - A system message providing instructions or context to the model. - TextContentItem: - type: object - properties: - type: - type: string - const: text - default: text - description: >- - Discriminator type of the content item. Always "text" - text: - type: string - description: Text content - additionalProperties: false - required: - - type - - text - title: TextContentItem - description: A text content item - ToolCall: - type: object - properties: - call_id: - type: string - tool_name: - oneOf: - - type: string - enum: - - brave_search - - wolfram_alpha - - photogen - - code_interpreter - title: BuiltinTool - - type: string - arguments: - oneOf: - - type: string - - type: object - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - - type: array - items: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - - type: object - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - arguments_json: - type: string - additionalProperties: false - required: - - call_id - - tool_name - - arguments - title: ToolCall - ToolConfig: - type: object - properties: - tool_choice: - oneOf: - - type: string - enum: - - auto - - required - - none - title: ToolChoice - description: >- - Whether tool use is required or automatic. This is a hint to the model - which may not be followed. It depends on the Instruction Following - capabilities of the model. - - type: string - default: auto - description: >- - (Optional) Whether tool use is automatic, required, or none. Can also - specify a tool name to use a specific tool. Defaults to ToolChoice.auto. - tool_prompt_format: - type: string - enum: - - json - - function_tag - - python_list - description: >- - (Optional) Instructs the model how to format tool calls. By default, Llama - Stack will attempt to use a format that is best adapted to the model. - - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a - tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python - syntax -- a list of function calls. - system_message_behavior: - type: string - enum: - - append - - replace - description: >- - (Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: - Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: - Replaces the default system prompt with the provided system message. The - system message can include the string '{{function_definitions}}' to indicate - where the function definitions should be inserted. - default: append - additionalProperties: false - title: ToolConfig - description: Configuration for tool use. - ToolDefinition: - type: object - properties: - tool_name: - oneOf: - - type: string - enum: - - brave_search - - wolfram_alpha - - photogen - - code_interpreter - title: BuiltinTool - - type: string - description: - type: string - parameters: - type: object - additionalProperties: - $ref: '#/components/schemas/ToolParamDefinition' - additionalProperties: false - required: - - tool_name - title: ToolDefinition - ToolParamDefinition: - type: object - properties: - param_type: - type: string - description: - type: string - required: - type: boolean - default: true - default: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - additionalProperties: false - required: - - param_type - title: ToolParamDefinition - ToolResponseMessage: - type: object - properties: - role: - type: string - const: tool - default: tool - description: >- - Must be "tool" to identify this as a tool response - call_id: - type: string - description: >- - Unique identifier for the tool call this response is for - content: - $ref: '#/components/schemas/InterleavedContent' - description: The response content from the tool - additionalProperties: false - required: - - role - - call_id - - content - title: ToolResponseMessage - description: >- - A message representing the result of a tool invocation. - TopKSamplingStrategy: - type: object - properties: - type: - type: string - const: top_k - default: top_k - description: >- - Must be "top_k" to identify this sampling strategy - top_k: - type: integer - description: >- - Number of top tokens to consider for sampling. Must be at least 1 - additionalProperties: false - required: - - type - - top_k - title: TopKSamplingStrategy - description: >- - Top-k sampling strategy that restricts sampling to the k most likely tokens. - TopPSamplingStrategy: - type: object - properties: - type: - type: string - const: top_p - default: top_p - description: >- - Must be "top_p" to identify this sampling strategy - temperature: - type: number - description: >- - Controls randomness in sampling. Higher values increase randomness - top_p: - type: number - default: 0.95 - description: >- - Cumulative probability threshold for nucleus sampling. Defaults to 0.95 - additionalProperties: false - required: - - type - title: TopPSamplingStrategy - description: >- - Top-p (nucleus) sampling strategy that samples from the smallest set of tokens - with cumulative probability >= p. - URL: - type: object - properties: - uri: - type: string - description: The URL string pointing to the resource - additionalProperties: false - required: - - uri - title: URL - description: A URL reference to external content. - UserMessage: - type: object - properties: - role: - type: string - const: user - default: user - description: >- - Must be "user" to identify this as a user message - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - The content of the message, which can include text and other media - context: - $ref: '#/components/schemas/InterleavedContent' - description: >- - (Optional) This field is used internally by Llama Stack to pass RAG context. - This field may be removed in the API in the future. - additionalProperties: false - required: - - role - - content - title: UserMessage - description: >- - A message from the user in a chat conversation. - BatchChatCompletionRequest: - type: object - properties: - model_id: - type: string - description: >- - The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint. - messages_batch: - type: array - items: - type: array - items: - $ref: '#/components/schemas/Message' - description: >- - The messages to generate completions for. - sampling_params: - $ref: '#/components/schemas/SamplingParams' - description: >- - (Optional) Parameters to control the sampling strategy. - tools: - type: array - items: - $ref: '#/components/schemas/ToolDefinition' - description: >- - (Optional) List of tool definitions available to the model. - tool_config: - $ref: '#/components/schemas/ToolConfig' - description: (Optional) Configuration for tool use. - response_format: - $ref: '#/components/schemas/ResponseFormat' - description: >- - (Optional) Grammar specification for guided (structured) decoding. - logprobs: - type: object - properties: - top_k: - type: integer - default: 0 - description: >- - How many tokens (for each position) to return log probabilities for. - additionalProperties: false - description: >- - (Optional) If specified, log probabilities for each token position will - be returned. - additionalProperties: false - required: - - model_id - - messages_batch - title: BatchChatCompletionRequest - BatchChatCompletionResponse: - type: object - properties: - batch: - type: array - items: - $ref: '#/components/schemas/ChatCompletionResponse' - description: >- - List of chat completion responses, one for each conversation in the batch - additionalProperties: false - required: - - batch - title: BatchChatCompletionResponse - description: >- - Response from a batch chat completion request. - ChatCompletionResponse: - type: object - properties: - metrics: - type: array - items: - $ref: '#/components/schemas/MetricInResponse' - description: >- - (Optional) List of metrics associated with the API response - completion_message: - $ref: '#/components/schemas/CompletionMessage' - description: The complete response message - logprobs: - type: array - items: - $ref: '#/components/schemas/TokenLogProbs' - description: >- - Optional log probabilities for generated tokens - additionalProperties: false - required: - - completion_message - title: ChatCompletionResponse - description: Response from a chat completion request. - MetricInResponse: - type: object - properties: - metric: - type: string - description: The name of the metric - value: - oneOf: - - type: integer - - type: number - description: The numeric value of the metric - unit: - type: string - description: >- - (Optional) The unit of measurement for the metric value - additionalProperties: false - required: - - metric - - value - title: MetricInResponse - description: >- - A metric value included in API responses. - TokenLogProbs: - type: object - properties: - logprobs_by_token: - type: object - additionalProperties: - type: number - description: >- - Dictionary mapping tokens to their log probabilities - additionalProperties: false - required: - - logprobs_by_token - title: TokenLogProbs - description: Log probabilities for generated tokens. - BatchCompletionRequest: - type: object - properties: - model_id: - type: string - description: >- - The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint. - content_batch: - type: array - items: - $ref: '#/components/schemas/InterleavedContent' - description: The content to generate completions for. - sampling_params: - $ref: '#/components/schemas/SamplingParams' - description: >- - (Optional) Parameters to control the sampling strategy. - response_format: - $ref: '#/components/schemas/ResponseFormat' - description: >- - (Optional) Grammar specification for guided (structured) decoding. - logprobs: - type: object - properties: - top_k: - type: integer - default: 0 - description: >- - How many tokens (for each position) to return log probabilities for. - additionalProperties: false - description: >- - (Optional) If specified, log probabilities for each token position will - be returned. - additionalProperties: false - required: - - model_id - - content_batch - title: BatchCompletionRequest - BatchCompletionResponse: - type: object - properties: - batch: - type: array - items: - $ref: '#/components/schemas/CompletionResponse' - description: >- - List of completion responses, one for each input in the batch - additionalProperties: false - required: - - batch - title: BatchCompletionResponse - description: >- - Response from a batch completion request. - CompletionResponse: - type: object - properties: - metrics: - type: array - items: - $ref: '#/components/schemas/MetricInResponse' - description: >- - (Optional) List of metrics associated with the API response - content: - type: string - description: The generated completion text - stop_reason: - type: string - enum: - - end_of_turn - - end_of_message - - out_of_tokens - description: Reason why generation stopped - logprobs: - type: array - items: - $ref: '#/components/schemas/TokenLogProbs' - description: >- - Optional log probabilities for generated tokens - additionalProperties: false - required: - - content - - stop_reason - title: CompletionResponse - description: Response from a completion request. - CancelTrainingJobRequest: - type: object - properties: - job_uuid: - type: string - description: The UUID of the job to cancel. - additionalProperties: false - required: - - job_uuid - title: CancelTrainingJobRequest - ChatCompletionRequest: - type: object - properties: - model_id: - type: string - description: >- - The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint. - messages: - type: array - items: - $ref: '#/components/schemas/Message' - description: List of messages in the conversation. - sampling_params: - $ref: '#/components/schemas/SamplingParams' - description: >- - Parameters to control the sampling strategy. - tools: - type: array - items: - $ref: '#/components/schemas/ToolDefinition' - description: >- - (Optional) List of tool definitions available to the model. - tool_choice: - type: string - enum: - - auto - - required - - none - description: >- - (Optional) Whether tool use is required or automatic. Defaults to ToolChoice.auto. - .. deprecated:: Use tool_config instead. - tool_prompt_format: - type: string - enum: - - json - - function_tag - - python_list - description: >- - (Optional) Instructs the model how to format tool calls. By default, Llama - Stack will attempt to use a format that is best adapted to the model. - - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a - tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python - syntax -- a list of function calls. .. deprecated:: Use tool_config instead. - response_format: - $ref: '#/components/schemas/ResponseFormat' - description: >- - (Optional) Grammar specification for guided (structured) decoding. There - are two options: - `ResponseFormat.json_schema`: The grammar is a JSON - schema. Most providers support this format. - `ResponseFormat.grammar`: - The grammar is a BNF grammar. This format is more flexible, but not all - providers support it. - stream: - type: boolean - description: >- - (Optional) If True, generate an SSE event stream of the response. Defaults - to False. - logprobs: - type: object - properties: - top_k: - type: integer - default: 0 - description: >- - How many tokens (for each position) to return log probabilities for. - additionalProperties: false - description: >- - (Optional) If specified, log probabilities for each token position will - be returned. - tool_config: - $ref: '#/components/schemas/ToolConfig' - description: (Optional) Configuration for tool use. - additionalProperties: false - required: - - model_id - - messages - title: ChatCompletionRequest - ChatCompletionResponseEvent: - type: object - properties: - event_type: - type: string - enum: - - start - - complete - - progress - description: Type of the event - delta: - $ref: '#/components/schemas/ContentDelta' - description: >- - Content generated since last event. This can be one or more tokens, or - a tool call. - logprobs: - type: array - items: - $ref: '#/components/schemas/TokenLogProbs' - description: >- - Optional log probabilities for generated tokens - stop_reason: - type: string - enum: - - end_of_turn - - end_of_message - - out_of_tokens - description: >- - Optional reason why generation stopped, if complete - additionalProperties: false - required: - - event_type - - delta - title: ChatCompletionResponseEvent - description: >- - An event during chat completion generation. - ChatCompletionResponseStreamChunk: - type: object - properties: - metrics: - type: array - items: - $ref: '#/components/schemas/MetricInResponse' - description: >- - (Optional) List of metrics associated with the API response - event: - $ref: '#/components/schemas/ChatCompletionResponseEvent' - description: The event containing the new content - additionalProperties: false - required: - - event - title: ChatCompletionResponseStreamChunk - description: >- - A chunk of a streamed chat completion response. - ContentDelta: - oneOf: - - $ref: '#/components/schemas/TextDelta' - - $ref: '#/components/schemas/ImageDelta' - - $ref: '#/components/schemas/ToolCallDelta' - discriminator: - propertyName: type - mapping: - text: '#/components/schemas/TextDelta' - image: '#/components/schemas/ImageDelta' - tool_call: '#/components/schemas/ToolCallDelta' - ImageDelta: - type: object - properties: - type: - type: string - const: image - default: image - description: >- - Discriminator type of the delta. Always "image" - image: - type: string - contentEncoding: base64 - description: The incremental image data as bytes - additionalProperties: false - required: - - type - - image - title: ImageDelta - description: >- - An image content delta for streaming responses. - TextDelta: - type: object - properties: - type: - type: string - const: text - default: text - description: >- - Discriminator type of the delta. Always "text" - text: - type: string - description: The incremental text content - additionalProperties: false - required: - - type - - text - title: TextDelta - description: >- - A text content delta for streaming responses. - ToolCallDelta: - type: object - properties: - type: - type: string - const: tool_call - default: tool_call - description: >- - Discriminator type of the delta. Always "tool_call" - tool_call: - oneOf: - - type: string - - $ref: '#/components/schemas/ToolCall' - description: >- - Either an in-progress tool call string or the final parsed tool call - parse_status: - type: string - enum: - - started - - in_progress - - failed - - succeeded - description: Current parsing status of the tool call - additionalProperties: false - required: - - type - - tool_call - - parse_status - title: ToolCallDelta - description: >- - A tool call content delta for streaming responses. - CompletionRequest: - type: object - properties: - model_id: - type: string - description: >- - The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint. - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - The content to generate a completion for. - sampling_params: - $ref: '#/components/schemas/SamplingParams' - description: >- - (Optional) Parameters to control the sampling strategy. - response_format: - $ref: '#/components/schemas/ResponseFormat' - description: >- - (Optional) Grammar specification for guided (structured) decoding. - stream: - type: boolean - description: >- - (Optional) If True, generate an SSE event stream of the response. Defaults - to False. - logprobs: - type: object - properties: - top_k: - type: integer - default: 0 - description: >- - How many tokens (for each position) to return log probabilities for. - additionalProperties: false - description: >- - (Optional) If specified, log probabilities for each token position will - be returned. - additionalProperties: false - required: - - model_id - - content - title: CompletionRequest - CompletionResponseStreamChunk: - type: object - properties: - metrics: - type: array - items: - $ref: '#/components/schemas/MetricInResponse' - description: >- - (Optional) List of metrics associated with the API response - delta: - type: string - description: >- - New content generated since last chunk. This can be one or more tokens. - stop_reason: - type: string - enum: - - end_of_turn - - end_of_message - - out_of_tokens - description: >- - Optional reason why generation stopped, if complete - logprobs: - type: array - items: - $ref: '#/components/schemas/TokenLogProbs' - description: >- - Optional log probabilities for generated tokens - additionalProperties: false - required: - - delta - title: CompletionResponseStreamChunk - description: >- - A chunk of a streamed completion response. - AgentConfig: - type: object - properties: - sampling_params: - $ref: '#/components/schemas/SamplingParams' - input_shields: - type: array - items: - type: string - output_shields: - type: array - items: - type: string - toolgroups: - type: array - items: - $ref: '#/components/schemas/AgentTool' - client_tools: - type: array - items: - $ref: '#/components/schemas/ToolDef' - tool_choice: - type: string - enum: - - auto - - required - - none - title: ToolChoice - description: >- - Whether tool use is required or automatic. This is a hint to the model - which may not be followed. It depends on the Instruction Following capabilities - of the model. - deprecated: true - tool_prompt_format: - type: string - enum: - - json - - function_tag - - python_list - title: ToolPromptFormat - description: >- - Prompt format for calling custom / zero shot tools. - deprecated: true - tool_config: - $ref: '#/components/schemas/ToolConfig' - max_infer_iters: - type: integer - default: 10 - model: - type: string - description: >- - The model identifier to use for the agent - instructions: - type: string - description: The system instructions for the agent - name: - type: string - description: >- - Optional name for the agent, used in telemetry and identification - enable_session_persistence: - type: boolean - default: false - description: >- - Optional flag indicating whether session data has to be persisted - response_format: - $ref: '#/components/schemas/ResponseFormat' - description: Optional response format configuration - additionalProperties: false - required: - - model - - instructions - title: AgentConfig - description: Configuration for an agent. - AgentTool: - oneOf: - - type: string - - type: object - properties: - name: - type: string - args: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - additionalProperties: false - required: - - name - - args - title: AgentToolGroupWithArgs - ToolDef: - type: object - properties: - name: - type: string - description: Name of the tool - description: - type: string - description: >- - (Optional) Human-readable description of what the tool does - parameters: - type: array - items: - $ref: '#/components/schemas/ToolParameter' - description: >- - (Optional) List of parameters this tool accepts - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional metadata about the tool - additionalProperties: false - required: - - name - title: ToolDef - description: >- - Tool definition used in runtime contexts. - ToolParameter: - type: object - properties: - name: - type: string - description: Name of the parameter - parameter_type: - type: string - description: >- - Type of the parameter (e.g., string, integer) - description: - type: string - description: >- - Human-readable description of what the parameter does - required: - type: boolean - default: true - description: >- - Whether this parameter is required for tool invocation - default: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Default value for the parameter if not provided - additionalProperties: false - required: - - name - - parameter_type - - description - - required - title: ToolParameter - description: Parameter definition for a tool. - CreateAgentRequest: - type: object - properties: - agent_config: - $ref: '#/components/schemas/AgentConfig' - description: The configuration for the agent. - additionalProperties: false - required: - - agent_config - title: CreateAgentRequest - AgentCreateResponse: - type: object - properties: - agent_id: - type: string - description: Unique identifier for the created agent - additionalProperties: false - required: - - agent_id - title: AgentCreateResponse - description: >- - Response returned when creating a new agent. - CreateAgentSessionRequest: - type: object - properties: - session_name: - type: string - description: The name of the session to create. - additionalProperties: false - required: - - session_name - title: CreateAgentSessionRequest - AgentSessionCreateResponse: - type: object - properties: - session_id: - type: string - description: >- - Unique identifier for the created session - additionalProperties: false - required: - - session_id - title: AgentSessionCreateResponse - description: >- - Response returned when creating a new agent session. - CreateAgentTurnRequest: - type: object - properties: - messages: - type: array - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - description: List of messages to start the turn with. - stream: - type: boolean - description: >- - (Optional) If True, generate an SSE event stream of the response. Defaults - to False. - documents: - type: array - items: - type: object - properties: - content: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - type: array - items: - $ref: '#/components/schemas/InterleavedContentItem' - - $ref: '#/components/schemas/URL' - description: The content of the document. - mime_type: - type: string - description: The MIME type of the document. - additionalProperties: false - required: - - content - - mime_type - title: Document - description: A document to be used by an agent. - description: >- - (Optional) List of documents to create the turn with. - toolgroups: - type: array - items: - $ref: '#/components/schemas/AgentTool' - description: >- - (Optional) List of toolgroups to create the turn with, will be used in - addition to the agent's config toolgroups for the request. - tool_config: - $ref: '#/components/schemas/ToolConfig' - description: >- - (Optional) The tool configuration to create the turn with, will be used - to override the agent's tool_config. - additionalProperties: false - required: - - messages - title: CreateAgentTurnRequest - InferenceStep: - type: object - properties: - turn_id: - type: string - description: The ID of the turn. - step_id: - type: string - description: The ID of the step. - started_at: - type: string - format: date-time - description: The time the step started. - completed_at: - type: string - format: date-time - description: The time the step completed. - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - title: StepType - description: Type of the step in an agent turn. - const: inference - default: inference - model_response: - $ref: '#/components/schemas/CompletionMessage' - description: The response from the LLM. - additionalProperties: false - required: - - turn_id - - step_id - - step_type - - model_response - title: InferenceStep - description: An inference step in an agent turn. - MemoryRetrievalStep: - type: object - properties: - turn_id: - type: string - description: The ID of the turn. - step_id: - type: string - description: The ID of the step. - started_at: - type: string - format: date-time - description: The time the step started. - completed_at: - type: string - format: date-time - description: The time the step completed. - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - title: StepType - description: Type of the step in an agent turn. - const: memory_retrieval - default: memory_retrieval - vector_db_ids: - type: string - description: >- - The IDs of the vector databases to retrieve context from. - inserted_context: - $ref: '#/components/schemas/InterleavedContent' - description: >- - The context retrieved from the vector databases. - additionalProperties: false - required: - - turn_id - - step_id - - step_type - - vector_db_ids - - inserted_context - title: MemoryRetrievalStep - description: >- - A memory retrieval step in an agent turn. - SafetyViolation: - type: object - properties: - violation_level: - $ref: '#/components/schemas/ViolationLevel' - description: Severity level of the violation - user_message: - type: string - description: >- - (Optional) Message to convey to the user about the violation - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Additional metadata including specific violation codes for debugging and - telemetry - additionalProperties: false - required: - - violation_level - - metadata - title: SafetyViolation - description: >- - Details of a safety violation detected by content moderation. - ShieldCallStep: - type: object - properties: - turn_id: - type: string - description: The ID of the turn. - step_id: - type: string - description: The ID of the step. - started_at: - type: string - format: date-time - description: The time the step started. - completed_at: - type: string - format: date-time - description: The time the step completed. - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - title: StepType - description: Type of the step in an agent turn. - const: shield_call - default: shield_call - violation: - $ref: '#/components/schemas/SafetyViolation' - description: The violation from the shield call. - additionalProperties: false - required: - - turn_id - - step_id - - step_type - title: ShieldCallStep - description: A shield call step in an agent turn. - ToolExecutionStep: - type: object - properties: - turn_id: - type: string - description: The ID of the turn. - step_id: - type: string - description: The ID of the step. - started_at: - type: string - format: date-time - description: The time the step started. - completed_at: - type: string - format: date-time - description: The time the step completed. - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - title: StepType - description: Type of the step in an agent turn. - const: tool_execution - default: tool_execution - tool_calls: - type: array - items: - $ref: '#/components/schemas/ToolCall' - description: The tool calls to execute. - tool_responses: - type: array - items: - $ref: '#/components/schemas/ToolResponse' - description: The tool responses from the tool calls. - additionalProperties: false - required: - - turn_id - - step_id - - step_type - - tool_calls - - tool_responses - title: ToolExecutionStep - description: A tool execution step in an agent turn. - ToolResponse: - type: object - properties: - call_id: - type: string - description: >- - Unique identifier for the tool call this response is for - tool_name: - oneOf: - - type: string - enum: - - brave_search - - wolfram_alpha - - photogen - - code_interpreter - title: BuiltinTool - - type: string - description: Name of the tool that was invoked - content: - $ref: '#/components/schemas/InterleavedContent' - description: The response content from the tool - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional metadata about the tool response - additionalProperties: false - required: - - call_id - - tool_name - - content - title: ToolResponse - description: Response from a tool invocation. - Turn: - type: object - properties: - turn_id: - type: string - description: >- - Unique identifier for the turn within a session - session_id: - type: string - description: >- - Unique identifier for the conversation session - input_messages: - type: array - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - description: >- - List of messages that initiated this turn - steps: - type: array - items: - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - discriminator: - propertyName: step_type - mapping: - inference: '#/components/schemas/InferenceStep' - tool_execution: '#/components/schemas/ToolExecutionStep' - shield_call: '#/components/schemas/ShieldCallStep' - memory_retrieval: '#/components/schemas/MemoryRetrievalStep' - description: >- - Ordered list of processing steps executed during this turn - output_message: - $ref: '#/components/schemas/CompletionMessage' - description: >- - The model's generated response containing content and metadata - output_attachments: - type: array - items: - type: object - properties: - content: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - type: array - items: - $ref: '#/components/schemas/InterleavedContentItem' - - $ref: '#/components/schemas/URL' - description: The content of the attachment. - mime_type: - type: string - description: The MIME type of the attachment. - additionalProperties: false - required: - - content - - mime_type - title: Attachment - description: An attachment to an agent turn. - description: >- - (Optional) Files or media attached to the agent's response - started_at: - type: string - format: date-time - description: Timestamp when the turn began - completed_at: - type: string - format: date-time - description: >- - (Optional) Timestamp when the turn finished, if completed - additionalProperties: false - required: - - turn_id - - session_id - - input_messages - - steps - - output_message - - started_at - title: Turn - description: >- - A single turn in an interaction with an Agentic System. - ViolationLevel: - type: string - enum: - - info - - warn - - error - title: ViolationLevel - description: Severity level of a safety violation. - AgentTurnResponseEvent: - type: object - properties: - payload: - $ref: '#/components/schemas/AgentTurnResponseEventPayload' - description: >- - Event-specific payload containing event data - additionalProperties: false - required: - - payload - title: AgentTurnResponseEvent - description: >- - An event in an agent turn response stream. - AgentTurnResponseEventPayload: - oneOf: - - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload' - - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload' - - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload' - - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload' - - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload' - - $ref: '#/components/schemas/AgentTurnResponseTurnAwaitingInputPayload' - discriminator: - propertyName: event_type - mapping: - step_start: '#/components/schemas/AgentTurnResponseStepStartPayload' - step_progress: '#/components/schemas/AgentTurnResponseStepProgressPayload' - step_complete: '#/components/schemas/AgentTurnResponseStepCompletePayload' - turn_start: '#/components/schemas/AgentTurnResponseTurnStartPayload' - turn_complete: '#/components/schemas/AgentTurnResponseTurnCompletePayload' - turn_awaiting_input: '#/components/schemas/AgentTurnResponseTurnAwaitingInputPayload' - AgentTurnResponseStepCompletePayload: - type: object - properties: - event_type: - type: string - enum: - - step_start - - step_complete - - step_progress - - turn_start - - turn_complete - - turn_awaiting_input - const: step_complete - default: step_complete - description: Type of event being reported - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - description: Type of step being executed - step_id: - type: string - description: >- - Unique identifier for the step within a turn - step_details: - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - discriminator: - propertyName: step_type - mapping: - inference: '#/components/schemas/InferenceStep' - tool_execution: '#/components/schemas/ToolExecutionStep' - shield_call: '#/components/schemas/ShieldCallStep' - memory_retrieval: '#/components/schemas/MemoryRetrievalStep' - description: Complete details of the executed step - additionalProperties: false - required: - - event_type - - step_type - - step_id - - step_details - title: AgentTurnResponseStepCompletePayload - description: >- - Payload for step completion events in agent turn responses. - AgentTurnResponseStepProgressPayload: - type: object - properties: - event_type: - type: string - enum: - - step_start - - step_complete - - step_progress - - turn_start - - turn_complete - - turn_awaiting_input - const: step_progress - default: step_progress - description: Type of event being reported - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - description: Type of step being executed - step_id: - type: string - description: >- - Unique identifier for the step within a turn - delta: - $ref: '#/components/schemas/ContentDelta' - description: >- - Incremental content changes during step execution - additionalProperties: false - required: - - event_type - - step_type - - step_id - - delta - title: AgentTurnResponseStepProgressPayload - description: >- - Payload for step progress events in agent turn responses. - AgentTurnResponseStepStartPayload: - type: object - properties: - event_type: - type: string - enum: - - step_start - - step_complete - - step_progress - - turn_start - - turn_complete - - turn_awaiting_input - const: step_start - default: step_start - description: Type of event being reported - step_type: - type: string - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - description: Type of step being executed - step_id: - type: string - description: >- - Unique identifier for the step within a turn - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional metadata for the step - additionalProperties: false - required: - - event_type - - step_type - - step_id - title: AgentTurnResponseStepStartPayload - description: >- - Payload for step start events in agent turn responses. - AgentTurnResponseStreamChunk: - type: object - properties: - event: - $ref: '#/components/schemas/AgentTurnResponseEvent' - description: >- - Individual event in the agent turn response stream - additionalProperties: false - required: - - event - title: AgentTurnResponseStreamChunk - description: Streamed agent turn completion response. - "AgentTurnResponseTurnAwaitingInputPayload": - type: object - properties: - event_type: - type: string - enum: - - step_start - - step_complete - - step_progress - - turn_start - - turn_complete - - turn_awaiting_input - const: turn_awaiting_input - default: turn_awaiting_input - description: Type of event being reported - turn: - $ref: '#/components/schemas/Turn' - description: >- - Turn data when waiting for external tool responses - additionalProperties: false - required: - - event_type - - turn - title: >- - AgentTurnResponseTurnAwaitingInputPayload - description: >- - Payload for turn awaiting input events in agent turn responses. - AgentTurnResponseTurnCompletePayload: - type: object - properties: - event_type: - type: string - enum: - - step_start - - step_complete - - step_progress - - turn_start - - turn_complete - - turn_awaiting_input - const: turn_complete - default: turn_complete - description: Type of event being reported - turn: - $ref: '#/components/schemas/Turn' - description: >- - Complete turn data including all steps and results - additionalProperties: false - required: - - event_type - - turn - title: AgentTurnResponseTurnCompletePayload - description: >- - Payload for turn completion events in agent turn responses. - AgentTurnResponseTurnStartPayload: - type: object - properties: - event_type: - type: string - enum: - - step_start - - step_complete - - step_progress - - turn_start - - turn_complete - - turn_awaiting_input - const: turn_start - default: turn_start - description: Type of event being reported - turn_id: - type: string - description: >- - Unique identifier for the turn within a session - additionalProperties: false - required: - - event_type - - turn_id - title: AgentTurnResponseTurnStartPayload - description: >- - Payload for turn start events in agent turn responses. - OpenAIResponseAnnotationCitation: - type: object - properties: - type: - type: string - const: url_citation - default: url_citation - description: >- - Annotation type identifier, always "url_citation" - end_index: - type: integer - description: >- - End position of the citation span in the content - start_index: - type: integer - description: >- - Start position of the citation span in the content - title: - type: string - description: Title of the referenced web resource - url: - type: string - description: URL of the referenced web resource - additionalProperties: false - required: - - type - - end_index - - start_index - - title - - url - title: OpenAIResponseAnnotationCitation - description: >- - URL citation annotation for referencing external web resources. - "OpenAIResponseAnnotationContainerFileCitation": - type: object - properties: - type: - type: string - const: container_file_citation - default: container_file_citation - container_id: - type: string - end_index: - type: integer - file_id: - type: string - filename: - type: string - start_index: - type: integer - additionalProperties: false - required: - - type - - container_id - - end_index - - file_id - - filename - - start_index - title: >- - OpenAIResponseAnnotationContainerFileCitation - OpenAIResponseAnnotationFileCitation: - type: object - properties: - type: - type: string - const: file_citation - default: file_citation - description: >- - Annotation type identifier, always "file_citation" - file_id: - type: string - description: Unique identifier of the referenced file - filename: - type: string - description: Name of the referenced file - index: - type: integer - description: >- - Position index of the citation within the content - additionalProperties: false - required: - - type - - file_id - - filename - - index - title: OpenAIResponseAnnotationFileCitation - description: >- - File citation annotation for referencing specific files in response content. - OpenAIResponseAnnotationFilePath: - type: object - properties: - type: - type: string - const: file_path - default: file_path - file_id: - type: string - index: - type: integer - additionalProperties: false - required: - - type - - file_id - - index - title: OpenAIResponseAnnotationFilePath - OpenAIResponseAnnotations: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseAnnotationFileCitation' - - $ref: '#/components/schemas/OpenAIResponseAnnotationCitation' - - $ref: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' - - $ref: '#/components/schemas/OpenAIResponseAnnotationFilePath' - discriminator: - propertyName: type - mapping: - file_citation: '#/components/schemas/OpenAIResponseAnnotationFileCitation' - url_citation: '#/components/schemas/OpenAIResponseAnnotationCitation' - container_file_citation: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation' - file_path: '#/components/schemas/OpenAIResponseAnnotationFilePath' - OpenAIResponseInput: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' - - $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput' - - $ref: '#/components/schemas/OpenAIResponseMessage' - "OpenAIResponseInputFunctionToolCallOutput": - type: object - properties: - call_id: - type: string - output: - type: string - type: - type: string - const: function_call_output - default: function_call_output - id: - type: string - status: - type: string - additionalProperties: false - required: - - call_id - - output - - type - title: >- - OpenAIResponseInputFunctionToolCallOutput - description: >- - This represents the output of a function call that gets passed back to the - model. - OpenAIResponseInputMessageContent: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseInputMessageContentText' - - $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage' - discriminator: - propertyName: type - mapping: - input_text: '#/components/schemas/OpenAIResponseInputMessageContentText' - input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage' - OpenAIResponseInputMessageContentImage: - type: object - properties: - detail: - oneOf: - - type: string - const: low - - type: string - const: high - - type: string - const: auto - default: auto - description: >- - Level of detail for image processing, can be "low", "high", or "auto" - type: - type: string - const: input_image - default: input_image - description: >- - Content type identifier, always "input_image" - image_url: - type: string - description: (Optional) URL of the image content - additionalProperties: false - required: - - detail - - type - title: OpenAIResponseInputMessageContentImage - description: >- - Image content for input messages in OpenAI response format. - OpenAIResponseInputMessageContentText: - type: object - properties: - text: - type: string - description: The text content of the input message - type: - type: string - const: input_text - default: input_text - description: >- - Content type identifier, always "input_text" - additionalProperties: false - required: - - text - - type - title: OpenAIResponseInputMessageContentText - description: >- - Text content for input messages in OpenAI response format. - OpenAIResponseInputTool: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch' - - $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch' - - $ref: '#/components/schemas/OpenAIResponseInputToolFunction' - - $ref: '#/components/schemas/OpenAIResponseInputToolMCP' - discriminator: - propertyName: type - mapping: - web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch' - file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch' - function: '#/components/schemas/OpenAIResponseInputToolFunction' - mcp: '#/components/schemas/OpenAIResponseInputToolMCP' - OpenAIResponseInputToolFileSearch: - type: object - properties: - type: - type: string - const: file_search - default: file_search - description: >- - Tool type identifier, always "file_search" - vector_store_ids: - type: array - items: - type: string - description: >- - List of vector store identifiers to search within - filters: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional filters to apply to the search - max_num_results: - type: integer - default: 10 - description: >- - (Optional) Maximum number of search results to return (1-50) - ranking_options: - type: object - properties: - ranker: - type: string - description: >- - (Optional) Name of the ranking algorithm to use - score_threshold: - type: number - default: 0.0 - description: >- - (Optional) Minimum relevance score threshold for results - additionalProperties: false - description: >- - (Optional) Options for ranking and scoring search results - additionalProperties: false - required: - - type - - vector_store_ids - title: OpenAIResponseInputToolFileSearch - description: >- - File search tool configuration for OpenAI response inputs. - OpenAIResponseInputToolFunction: - type: object - properties: - type: - type: string - const: function - default: function - description: Tool type identifier, always "function" - name: - type: string - description: Name of the function that can be called - description: - type: string - description: >- - (Optional) Description of what the function does - parameters: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) JSON schema defining the function's parameters - strict: - type: boolean - description: >- - (Optional) Whether to enforce strict parameter validation - additionalProperties: false - required: - - type - - name - title: OpenAIResponseInputToolFunction - description: >- - Function tool configuration for OpenAI response inputs. - OpenAIResponseInputToolMCP: - type: object - properties: - type: - type: string - const: mcp - default: mcp - description: Tool type identifier, always "mcp" - server_label: - type: string - description: Label to identify this MCP server - server_url: - type: string - description: URL endpoint of the MCP server - headers: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) HTTP headers to include when connecting to the server - require_approval: - oneOf: - - type: string - const: always - - type: string - const: never - - type: object - properties: - always: - type: array - items: - type: string - description: >- - (Optional) List of tool names that always require approval - never: - type: array - items: - type: string - description: >- - (Optional) List of tool names that never require approval - additionalProperties: false - title: ApprovalFilter - description: >- - Filter configuration for MCP tool approval requirements. - default: never - description: >- - Approval requirement for tool calls ("always", "never", or filter) - allowed_tools: - oneOf: - - type: array - items: - type: string - - type: object - properties: - tool_names: - type: array - items: - type: string - description: >- - (Optional) List of specific tool names that are allowed - additionalProperties: false - title: AllowedToolsFilter - description: >- - Filter configuration for restricting which MCP tools can be used. - description: >- - (Optional) Restriction on which tools can be used from this server - additionalProperties: false - required: - - type - - server_label - - server_url - - require_approval - title: OpenAIResponseInputToolMCP - description: >- - Model Context Protocol (MCP) tool configuration for OpenAI response inputs. - OpenAIResponseInputToolWebSearch: - type: object - properties: - type: - oneOf: - - type: string - const: web_search - - type: string - const: web_search_preview - - type: string - const: web_search_preview_2025_03_11 - default: web_search - description: Web search tool type variant to use - search_context_size: - type: string - default: medium - description: >- - (Optional) Size of search context, must be "low", "medium", or "high" - additionalProperties: false - required: - - type - title: OpenAIResponseInputToolWebSearch - description: >- - Web search tool configuration for OpenAI response inputs. - OpenAIResponseMessage: - type: object - properties: - content: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIResponseInputMessageContent' - - type: array - items: - $ref: '#/components/schemas/OpenAIResponseOutputMessageContent' - role: - oneOf: - - type: string - const: system - - type: string - const: developer - - type: string - const: user - - type: string - const: assistant - type: - type: string - const: message - default: message - id: - type: string - status: - type: string - additionalProperties: false - required: - - content - - role - - type - title: OpenAIResponseMessage - description: >- - Corresponds to the various Message types in the Responses API. They are all - under one type because the Responses API gives them all the same "type" value, - and there is no way to tell them apart in certain scenarios. - OpenAIResponseOutputMessageContent: - type: object - properties: - text: - type: string - type: - type: string - const: output_text - default: output_text - annotations: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseAnnotations' - additionalProperties: false - required: - - text - - type - - annotations - title: >- - OpenAIResponseOutputMessageContentOutputText - "OpenAIResponseOutputMessageFileSearchToolCall": - type: object - properties: - id: - type: string - description: Unique identifier for this tool call - queries: - type: array - items: - type: string - description: List of search queries executed - status: - type: string - description: >- - Current status of the file search operation - type: - type: string - const: file_search_call - default: file_search_call - description: >- - Tool call type identifier, always "file_search_call" - results: - type: array - items: - type: object - properties: - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Key-value attributes associated with the file - file_id: - type: string - description: >- - Unique identifier of the file containing the result - filename: - type: string - description: Name of the file containing the result - score: - type: number - description: >- - Relevance score for this search result (between 0 and 1) - text: - type: string - description: Text content of the search result - additionalProperties: false - required: - - attributes - - file_id - - filename - - score - - text - title: >- - OpenAIResponseOutputMessageFileSearchToolCallResults - description: >- - Search results returned by the file search operation. - description: >- - (Optional) Search results returned by the file search operation - additionalProperties: false - required: - - id - - queries - - status - - type - title: >- - OpenAIResponseOutputMessageFileSearchToolCall - description: >- - File search tool call output message for OpenAI responses. - "OpenAIResponseOutputMessageFunctionToolCall": - type: object - properties: - call_id: - type: string - description: Unique identifier for the function call - name: - type: string - description: Name of the function being called - arguments: - type: string - description: >- - JSON string containing the function arguments - type: - type: string - const: function_call - default: function_call - description: >- - Tool call type identifier, always "function_call" - id: - type: string - description: >- - (Optional) Additional identifier for the tool call - status: - type: string - description: >- - (Optional) Current status of the function call execution - additionalProperties: false - required: - - call_id - - name - - arguments - - type - title: >- - OpenAIResponseOutputMessageFunctionToolCall - description: >- - Function tool call output message for OpenAI responses. - "OpenAIResponseOutputMessageWebSearchToolCall": - type: object - properties: - id: - type: string - description: Unique identifier for this tool call - status: - type: string - description: >- - Current status of the web search operation - type: - type: string - const: web_search_call - default: web_search_call - description: >- - Tool call type identifier, always "web_search_call" - additionalProperties: false - required: - - id - - status - - type - title: >- - OpenAIResponseOutputMessageWebSearchToolCall - description: >- - Web search tool call output message for OpenAI responses. - OpenAIResponseText: - type: object - properties: - format: - type: object - properties: - type: - oneOf: - - type: string - const: text - - type: string - const: json_schema - - type: string - const: json_object - description: >- - Must be "text", "json_schema", or "json_object" to identify the format - type - name: - type: string - description: >- - The name of the response format. Only used for json_schema. - schema: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The JSON schema the response should conform to. In a Python SDK, this - is often a `pydantic` model. Only used for json_schema. - description: - type: string - description: >- - (Optional) A description of the response format. Only used for json_schema. - strict: - type: boolean - description: >- - (Optional) Whether to strictly enforce the JSON schema. If true, the - response must match the schema exactly. Only used for json_schema. - additionalProperties: false - required: - - type - description: >- - (Optional) Text format configuration specifying output format requirements - additionalProperties: false - title: OpenAIResponseText - description: >- - Text response configuration for OpenAI responses. - CreateOpenaiResponseRequest: - type: object - properties: - input: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIResponseInput' - description: Input message(s) to create the response. - model: - type: string - description: The underlying LLM used for completions. - instructions: - type: string - previous_response_id: - type: string - description: >- - (Optional) if specified, the new response will be a continuation of the - previous response. This can be used to easily fork-off new responses from - existing responses. - store: - type: boolean - stream: - type: boolean - temperature: - type: number - text: - $ref: '#/components/schemas/OpenAIResponseText' - tools: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseInputTool' - include: - type: array - items: - type: string - description: >- - (Optional) Additional fields to include in the response. - max_infer_iters: - type: integer - additionalProperties: false - required: - - input - - model - title: CreateOpenaiResponseRequest - OpenAIResponseError: - type: object - properties: - code: - type: string - description: >- - Error code identifying the type of failure - message: - type: string - description: >- - Human-readable error message describing the failure - additionalProperties: false - required: - - code - - message - title: OpenAIResponseError - description: >- - Error details for failed OpenAI response requests. - OpenAIResponseObject: - type: object - properties: - created_at: - type: integer - description: >- - Unix timestamp when the response was created - error: - $ref: '#/components/schemas/OpenAIResponseError' - description: >- - (Optional) Error details if the response generation failed - id: - type: string - description: Unique identifier for this response - model: - type: string - description: Model identifier used for generation - object: - type: string - const: response - default: response - description: >- - Object type identifier, always "response" - output: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseOutput' - description: >- - List of generated output items (messages, tool calls, etc.) - parallel_tool_calls: - type: boolean - default: false - description: >- - Whether tool calls can be executed in parallel - previous_response_id: - type: string - description: >- - (Optional) ID of the previous response in a conversation - status: - type: string - description: >- - Current status of the response generation - temperature: - type: number - description: >- - (Optional) Sampling temperature used for generation - text: - $ref: '#/components/schemas/OpenAIResponseText' - description: >- - Text formatting configuration for the response - top_p: - type: number - description: >- - (Optional) Nucleus sampling parameter used for generation - truncation: - type: string - description: >- - (Optional) Truncation strategy applied to the response - user: - type: string - description: >- - (Optional) User identifier associated with the request - additionalProperties: false - required: - - created_at - - id - - model - - object - - output - - parallel_tool_calls - - status - - text - title: OpenAIResponseObject - description: >- - Complete OpenAI response object containing generation results and metadata. - OpenAIResponseOutput: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseMessage' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' - - $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' - discriminator: - propertyName: type - mapping: - message: '#/components/schemas/OpenAIResponseMessage' - web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall' - file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall' - function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall' - mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall' - mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools' - OpenAIResponseOutputMessageMCPCall: - type: object - properties: - id: - type: string - description: Unique identifier for this MCP call - type: - type: string - const: mcp_call - default: mcp_call - description: >- - Tool call type identifier, always "mcp_call" - arguments: - type: string - description: >- - JSON string containing the MCP call arguments - name: - type: string - description: Name of the MCP method being called - server_label: - type: string - description: >- - Label identifying the MCP server handling the call - error: - type: string - description: >- - (Optional) Error message if the MCP call failed - output: - type: string - description: >- - (Optional) Output result from the successful MCP call - additionalProperties: false - required: - - id - - type - - arguments - - name - - server_label - title: OpenAIResponseOutputMessageMCPCall - description: >- - Model Context Protocol (MCP) call output message for OpenAI responses. - OpenAIResponseOutputMessageMCPListTools: - type: object - properties: - id: - type: string - description: >- - Unique identifier for this MCP list tools operation - type: - type: string - const: mcp_list_tools - default: mcp_list_tools - description: >- - Tool call type identifier, always "mcp_list_tools" - server_label: - type: string - description: >- - Label identifying the MCP server providing the tools - tools: - type: array - items: - type: object - properties: - input_schema: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - JSON schema defining the tool's input parameters - name: - type: string - description: Name of the tool - description: - type: string - description: >- - (Optional) Description of what the tool does - additionalProperties: false - required: - - input_schema - - name - title: MCPListToolsTool - description: >- - Tool definition returned by MCP list tools operation. - description: >- - List of available tools provided by the MCP server - additionalProperties: false - required: - - id - - type - - server_label - - tools - title: OpenAIResponseOutputMessageMCPListTools - description: >- - MCP list tools output message containing available tools from an MCP server. - OpenAIResponseContentPart: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseContentPartOutputText' - - $ref: '#/components/schemas/OpenAIResponseContentPartRefusal' - discriminator: - propertyName: type - mapping: - output_text: '#/components/schemas/OpenAIResponseContentPartOutputText' - refusal: '#/components/schemas/OpenAIResponseContentPartRefusal' - OpenAIResponseContentPartOutputText: - type: object - properties: - type: - type: string - const: output_text - default: output_text - text: - type: string - additionalProperties: false - required: - - type - - text - title: OpenAIResponseContentPartOutputText - OpenAIResponseContentPartRefusal: - type: object - properties: - type: - type: string - const: refusal - default: refusal - refusal: - type: string - additionalProperties: false - required: - - type - - refusal - title: OpenAIResponseContentPartRefusal - OpenAIResponseObjectStream: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemAdded' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemDone' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDelta' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDone' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallInProgress' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallSearching' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallCompleted' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsInProgress' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsFailed' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsCompleted' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDone' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone' - - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted' - discriminator: - propertyName: type - mapping: - response.created: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated' - response.output_item.added: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemAdded' - response.output_item.done: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemDone' - response.output_text.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDelta' - response.output_text.done: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDone' - response.function_call_arguments.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta' - response.function_call_arguments.done: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone' - response.web_search_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallInProgress' - response.web_search_call.searching: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallSearching' - response.web_search_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallCompleted' - response.mcp_list_tools.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsInProgress' - response.mcp_list_tools.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsFailed' - response.mcp_list_tools.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsCompleted' - response.mcp_call.arguments.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta' - response.mcp_call.arguments.done: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDone' - response.mcp_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress' - response.mcp_call.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed' - response.mcp_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted' - response.content_part.added: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded' - response.content_part.done: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone' - response.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted' - "OpenAIResponseObjectStreamResponseCompleted": - type: object - properties: - response: - $ref: '#/components/schemas/OpenAIResponseObject' - description: The completed response object - type: - type: string - const: response.completed - default: response.completed - description: >- - Event type identifier, always "response.completed" - additionalProperties: false - required: - - response - - type - title: >- - OpenAIResponseObjectStreamResponseCompleted - description: >- - Streaming event indicating a response has been completed. - "OpenAIResponseObjectStreamResponseContentPartAdded": - type: object - properties: - response_id: - type: string - description: >- - Unique identifier of the response containing this content - item_id: - type: string - description: >- - Unique identifier of the output item containing this content part - part: - $ref: '#/components/schemas/OpenAIResponseContentPart' - description: The content part that was added - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.content_part.added - default: response.content_part.added - description: >- - Event type identifier, always "response.content_part.added" - additionalProperties: false - required: - - response_id - - item_id - - part - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseContentPartAdded - description: >- - Streaming event for when a new content part is added to a response item. - "OpenAIResponseObjectStreamResponseContentPartDone": - type: object - properties: - response_id: - type: string - description: >- - Unique identifier of the response containing this content - item_id: - type: string - description: >- - Unique identifier of the output item containing this content part - part: - $ref: '#/components/schemas/OpenAIResponseContentPart' - description: The completed content part - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.content_part.done - default: response.content_part.done - description: >- - Event type identifier, always "response.content_part.done" - additionalProperties: false - required: - - response_id - - item_id - - part - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseContentPartDone - description: >- - Streaming event for when a content part is completed. - "OpenAIResponseObjectStreamResponseCreated": - type: object - properties: - response: - $ref: '#/components/schemas/OpenAIResponseObject' - description: The newly created response object - type: - type: string - const: response.created - default: response.created - description: >- - Event type identifier, always "response.created" - additionalProperties: false - required: - - response - - type - title: >- - OpenAIResponseObjectStreamResponseCreated - description: >- - Streaming event indicating a new response has been created. - "OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta": - type: object - properties: - delta: - type: string - description: >- - Incremental function call arguments being added - item_id: - type: string - description: >- - Unique identifier of the function call being updated - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.function_call_arguments.delta - default: response.function_call_arguments.delta - description: >- - Event type identifier, always "response.function_call_arguments.delta" - additionalProperties: false - required: - - delta - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta - description: >- - Streaming event for incremental function call argument updates. - "OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone": - type: object - properties: - arguments: - type: string - description: >- - Final complete arguments JSON string for the function call - item_id: - type: string - description: >- - Unique identifier of the completed function call - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.function_call_arguments.done - default: response.function_call_arguments.done - description: >- - Event type identifier, always "response.function_call_arguments.done" - additionalProperties: false - required: - - arguments - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone - description: >- - Streaming event for when function call arguments are completed. - "OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta": - type: object - properties: - delta: - type: string - item_id: - type: string - output_index: - type: integer - sequence_number: - type: integer - type: - type: string - const: response.mcp_call.arguments.delta - default: response.mcp_call.arguments.delta - additionalProperties: false - required: - - delta - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta - "OpenAIResponseObjectStreamResponseMcpCallArgumentsDone": - type: object - properties: - arguments: - type: string - item_id: - type: string - output_index: - type: integer - sequence_number: - type: integer - type: - type: string - const: response.mcp_call.arguments.done - default: response.mcp_call.arguments.done - additionalProperties: false - required: - - arguments - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpCallArgumentsDone - "OpenAIResponseObjectStreamResponseMcpCallCompleted": - type: object - properties: - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.mcp_call.completed - default: response.mcp_call.completed - description: >- - Event type identifier, always "response.mcp_call.completed" - additionalProperties: false - required: - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpCallCompleted - description: Streaming event for completed MCP calls. - "OpenAIResponseObjectStreamResponseMcpCallFailed": - type: object - properties: - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.mcp_call.failed - default: response.mcp_call.failed - description: >- - Event type identifier, always "response.mcp_call.failed" - additionalProperties: false - required: - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpCallFailed - description: Streaming event for failed MCP calls. - "OpenAIResponseObjectStreamResponseMcpCallInProgress": - type: object - properties: - item_id: - type: string - description: Unique identifier of the MCP call - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.mcp_call.in_progress - default: response.mcp_call.in_progress - description: >- - Event type identifier, always "response.mcp_call.in_progress" - additionalProperties: false - required: - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpCallInProgress - description: >- - Streaming event for MCP calls in progress. - "OpenAIResponseObjectStreamResponseMcpListToolsCompleted": - type: object - properties: - sequence_number: - type: integer - type: - type: string - const: response.mcp_list_tools.completed - default: response.mcp_list_tools.completed - additionalProperties: false - required: - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpListToolsCompleted - "OpenAIResponseObjectStreamResponseMcpListToolsFailed": - type: object - properties: - sequence_number: - type: integer - type: - type: string - const: response.mcp_list_tools.failed - default: response.mcp_list_tools.failed - additionalProperties: false - required: - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpListToolsFailed - "OpenAIResponseObjectStreamResponseMcpListToolsInProgress": - type: object - properties: - sequence_number: - type: integer - type: - type: string - const: response.mcp_list_tools.in_progress - default: response.mcp_list_tools.in_progress - additionalProperties: false - required: - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseMcpListToolsInProgress - "OpenAIResponseObjectStreamResponseOutputItemAdded": - type: object - properties: - response_id: - type: string - description: >- - Unique identifier of the response containing this output - item: - $ref: '#/components/schemas/OpenAIResponseOutput' - description: >- - The output item that was added (message, tool call, etc.) - output_index: - type: integer - description: >- - Index position of this item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.output_item.added - default: response.output_item.added - description: >- - Event type identifier, always "response.output_item.added" - additionalProperties: false - required: - - response_id - - item - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseOutputItemAdded - description: >- - Streaming event for when a new output item is added to the response. - "OpenAIResponseObjectStreamResponseOutputItemDone": - type: object - properties: - response_id: - type: string - description: >- - Unique identifier of the response containing this output - item: - $ref: '#/components/schemas/OpenAIResponseOutput' - description: >- - The completed output item (message, tool call, etc.) - output_index: - type: integer - description: >- - Index position of this item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.output_item.done - default: response.output_item.done - description: >- - Event type identifier, always "response.output_item.done" - additionalProperties: false - required: - - response_id - - item - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseOutputItemDone - description: >- - Streaming event for when an output item is completed. - "OpenAIResponseObjectStreamResponseOutputTextDelta": - type: object - properties: - content_index: - type: integer - description: Index position within the text content - delta: - type: string - description: Incremental text content being added - item_id: - type: string - description: >- - Unique identifier of the output item being updated - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.output_text.delta - default: response.output_text.delta - description: >- - Event type identifier, always "response.output_text.delta" - additionalProperties: false - required: - - content_index - - delta - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseOutputTextDelta - description: >- - Streaming event for incremental text content updates. - "OpenAIResponseObjectStreamResponseOutputTextDone": - type: object - properties: - content_index: - type: integer - description: Index position within the text content - text: - type: string - description: >- - Final complete text content of the output item - item_id: - type: string - description: >- - Unique identifier of the completed output item - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.output_text.done - default: response.output_text.done - description: >- - Event type identifier, always "response.output_text.done" - additionalProperties: false - required: - - content_index - - text - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseOutputTextDone - description: >- - Streaming event for when text output is completed. - "OpenAIResponseObjectStreamResponseWebSearchCallCompleted": - type: object - properties: - item_id: - type: string - description: >- - Unique identifier of the completed web search call - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.web_search_call.completed - default: response.web_search_call.completed - description: >- - Event type identifier, always "response.web_search_call.completed" - additionalProperties: false - required: - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseWebSearchCallCompleted - description: >- - Streaming event for completed web search calls. - "OpenAIResponseObjectStreamResponseWebSearchCallInProgress": - type: object - properties: - item_id: - type: string - description: Unique identifier of the web search call - output_index: - type: integer - description: >- - Index position of the item in the output list - sequence_number: - type: integer - description: >- - Sequential number for ordering streaming events - type: - type: string - const: response.web_search_call.in_progress - default: response.web_search_call.in_progress - description: >- - Event type identifier, always "response.web_search_call.in_progress" - additionalProperties: false - required: - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseWebSearchCallInProgress - description: >- - Streaming event for web search calls in progress. - "OpenAIResponseObjectStreamResponseWebSearchCallSearching": - type: object - properties: - item_id: - type: string - output_index: - type: integer - sequence_number: - type: integer - type: - type: string - const: response.web_search_call.searching - default: response.web_search_call.searching - additionalProperties: false - required: - - item_id - - output_index - - sequence_number - - type - title: >- - OpenAIResponseObjectStreamResponseWebSearchCallSearching - CreatePromptRequest: - type: object - properties: - prompt: - type: string - description: >- - The prompt text content with variable placeholders. - variables: - type: array - items: - type: string - description: >- - List of variable names that can be used in the prompt template. - additionalProperties: false - required: - - prompt - title: CreatePromptRequest - Prompt: - type: object - properties: - prompt: - type: string - description: >- - The system prompt text with variable placeholders. Variables are only - supported when using the Responses API. - version: - type: integer - description: >- - Version (integer starting at 1, incremented on save) - prompt_id: - type: string - description: >- - Unique identifier formatted as 'pmpt_<48-digit-hash>' - variables: - type: array - items: - type: string - description: >- - List of prompt variable names that can be used in the prompt template - is_default: - type: boolean - default: false - description: >- - Boolean indicating whether this version is the default version for this - prompt - additionalProperties: false - required: - - version - - prompt_id - - variables - - is_default - title: Prompt - description: >- - A prompt resource representing a stored OpenAI Compatible prompt template - in Llama Stack. - OpenAIDeleteResponseObject: - type: object - properties: - id: - type: string - description: >- - Unique identifier of the deleted response - object: - type: string - const: response - default: response - description: >- - Object type identifier, always "response" - deleted: - type: boolean - default: true - description: Deletion confirmation flag, always True - additionalProperties: false - required: - - id - - object - - deleted - title: OpenAIDeleteResponseObject - description: >- - Response object confirming deletion of an OpenAI response. - EmbeddingsRequest: - type: object - properties: - model_id: - type: string - description: >- - The identifier of the model to use. The model must be an embedding model - registered with Llama Stack and available via the /models endpoint. - contents: - oneOf: - - type: array - items: - type: string - - type: array - items: - $ref: '#/components/schemas/InterleavedContentItem' - description: >- - List of contents to generate embeddings for. Each content can be a string - or an InterleavedContentItem (and hence can be multimodal). The behavior - depends on the model and provider. Some models may only support text. - text_truncation: - type: string - enum: - - none - - start - - end - description: >- - (Optional) Config for how to truncate text for embedding when text is - longer than the model's max sequence length. - output_dimension: - type: integer - description: >- - (Optional) Output dimensionality for the embeddings. Only supported by - Matryoshka models. - task_type: - type: string - enum: - - query - - document - description: >- - (Optional) How is the embedding being used? This is only supported by - asymmetric embedding models. - additionalProperties: false - required: - - model_id - - contents - title: EmbeddingsRequest - EmbeddingsResponse: - type: object - properties: - embeddings: - type: array - items: - type: array - items: - type: number - description: >- - List of embedding vectors, one per input content. Each embedding is a - list of floats. The dimensionality of the embedding is model-specific; - you can check model metadata using /models/{model_id} - additionalProperties: false - required: - - embeddings - title: EmbeddingsResponse - description: >- - Response containing generated embeddings. - AgentCandidate: - type: object - properties: - type: - type: string - const: agent - default: agent - config: - $ref: '#/components/schemas/AgentConfig' - description: >- - The configuration for the agent candidate. - additionalProperties: false - required: - - type - - config - title: AgentCandidate - description: An agent candidate for evaluation. - AggregationFunctionType: - type: string - enum: - - average - - weighted_average - - median - - categorical_count - - accuracy - title: AggregationFunctionType - description: >- - Types of aggregation functions for scoring results. - BasicScoringFnParams: - type: object - properties: - type: - $ref: '#/components/schemas/ScoringFnParamsType' - const: basic - default: basic - description: >- - The type of scoring function parameters, always basic - aggregation_functions: - type: array - items: - $ref: '#/components/schemas/AggregationFunctionType' - description: >- - Aggregation functions to apply to the scores of each row - additionalProperties: false - required: - - type - - aggregation_functions - title: BasicScoringFnParams - description: >- - Parameters for basic scoring function configuration. - BenchmarkConfig: - type: object - properties: - eval_candidate: - $ref: '#/components/schemas/EvalCandidate' - description: The candidate to evaluate. - scoring_params: - type: object - additionalProperties: - $ref: '#/components/schemas/ScoringFnParams' - description: >- - Map between scoring function id and parameters for each scoring function - you want to run - num_examples: - type: integer - description: >- - (Optional) The number of examples to evaluate. If not provided, all examples - in the dataset will be evaluated - additionalProperties: false - required: - - eval_candidate - - scoring_params - title: BenchmarkConfig - description: >- - A benchmark configuration for evaluation. - EvalCandidate: - oneOf: - - $ref: '#/components/schemas/ModelCandidate' - - $ref: '#/components/schemas/AgentCandidate' - discriminator: - propertyName: type - mapping: - model: '#/components/schemas/ModelCandidate' - agent: '#/components/schemas/AgentCandidate' - LLMAsJudgeScoringFnParams: - type: object - properties: - type: - $ref: '#/components/schemas/ScoringFnParamsType' - const: llm_as_judge - default: llm_as_judge - description: >- - The type of scoring function parameters, always llm_as_judge - judge_model: - type: string - description: >- - Identifier of the LLM model to use as a judge for scoring - prompt_template: - type: string - description: >- - (Optional) Custom prompt template for the judge model - judge_score_regexes: - type: array - items: - type: string - description: >- - Regexes to extract the answer from generated response - aggregation_functions: - type: array - items: - $ref: '#/components/schemas/AggregationFunctionType' - description: >- - Aggregation functions to apply to the scores of each row - additionalProperties: false - required: - - type - - judge_model - - judge_score_regexes - - aggregation_functions - title: LLMAsJudgeScoringFnParams - description: >- - Parameters for LLM-as-judge scoring function configuration. - ModelCandidate: - type: object - properties: - type: - type: string - const: model - default: model - model: - type: string - description: The model ID to evaluate. - sampling_params: - $ref: '#/components/schemas/SamplingParams' - description: The sampling parameters for the model. - system_message: - $ref: '#/components/schemas/SystemMessage' - description: >- - (Optional) The system message providing instructions or context to the - model. - additionalProperties: false - required: - - type - - model - - sampling_params - title: ModelCandidate - description: A model candidate for evaluation. - RegexParserScoringFnParams: - type: object - properties: - type: - $ref: '#/components/schemas/ScoringFnParamsType' - const: regex_parser - default: regex_parser - description: >- - The type of scoring function parameters, always regex_parser - parsing_regexes: - type: array - items: - type: string - description: >- - Regex to extract the answer from generated response - aggregation_functions: - type: array - items: - $ref: '#/components/schemas/AggregationFunctionType' - description: >- - Aggregation functions to apply to the scores of each row - additionalProperties: false - required: - - type - - parsing_regexes - - aggregation_functions - title: RegexParserScoringFnParams - description: >- - Parameters for regex parser scoring function configuration. - ScoringFnParams: - oneOf: - - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - - $ref: '#/components/schemas/RegexParserScoringFnParams' - - $ref: '#/components/schemas/BasicScoringFnParams' - discriminator: - propertyName: type - mapping: - llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' - regex_parser: '#/components/schemas/RegexParserScoringFnParams' - basic: '#/components/schemas/BasicScoringFnParams' - ScoringFnParamsType: - type: string - enum: - - llm_as_judge - - regex_parser - - basic - title: ScoringFnParamsType - description: >- - Types of scoring function parameter configurations. - EvaluateRowsRequest: - type: object - properties: - input_rows: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The rows to evaluate. - scoring_functions: - type: array - items: - type: string - description: >- - The scoring functions to use for the evaluation. - benchmark_config: - $ref: '#/components/schemas/BenchmarkConfig' - description: The configuration for the benchmark. - additionalProperties: false - required: - - input_rows - - scoring_functions - - benchmark_config - title: EvaluateRowsRequest - EvaluateResponse: - type: object - properties: - generations: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The generations from the evaluation. - scores: - type: object - additionalProperties: - $ref: '#/components/schemas/ScoringResult' - description: The scores from the evaluation. - additionalProperties: false - required: - - generations - - scores - title: EvaluateResponse - description: The response from an evaluation. - ScoringResult: - type: object - properties: - score_rows: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The scoring result for each row. Each row is a map of column name to value. - aggregated_results: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Map of metric name to aggregated value - additionalProperties: false - required: - - score_rows - - aggregated_results - title: ScoringResult - description: A scoring result for a single row. - Agent: - type: object - properties: - agent_id: - type: string - description: Unique identifier for the agent - agent_config: - $ref: '#/components/schemas/AgentConfig' - description: Configuration settings for the agent - created_at: - type: string - format: date-time - description: Timestamp when the agent was created - additionalProperties: false - required: - - agent_id - - agent_config - - created_at - title: Agent - description: >- - An agent instance with configuration and metadata. - Session: - type: object - properties: - session_id: - type: string - description: >- - Unique identifier for the conversation session - session_name: - type: string - description: Human-readable name for the session - turns: - type: array - items: - $ref: '#/components/schemas/Turn' - description: >- - List of all turns that have occurred in this session - started_at: - type: string - format: date-time - description: Timestamp when the session was created - additionalProperties: false - required: - - session_id - - session_name - - turns - - started_at - title: Session - description: >- - A single session of an interaction with an Agentic System. - AgentStepResponse: - type: object - properties: - step: - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - discriminator: - propertyName: step_type - mapping: - inference: '#/components/schemas/InferenceStep' - tool_execution: '#/components/schemas/ToolExecutionStep' - shield_call: '#/components/schemas/ShieldCallStep' - memory_retrieval: '#/components/schemas/MemoryRetrievalStep' - description: >- - The complete step data and execution details - additionalProperties: false - required: - - step - title: AgentStepResponse - description: >- - Response containing details of a specific agent step. - Benchmark: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: benchmark - default: benchmark - description: The resource type, always benchmark - dataset_id: - type: string - description: >- - Identifier of the dataset to use for the benchmark evaluation - scoring_functions: - type: array - items: - type: string - description: >- - List of scoring function identifiers to apply during evaluation - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Metadata for this evaluation task - additionalProperties: false - required: - - identifier - - provider_id - - type - - dataset_id - - scoring_functions - - metadata - title: Benchmark - description: >- - A benchmark resource for evaluating model performance. - OpenAIAssistantMessageParam: - type: object - properties: - role: - type: string - const: assistant - default: assistant - description: >- - Must be "assistant" to identify this as the model's response - content: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - description: The content of the model's response - name: - type: string - description: >- - (Optional) The name of the assistant message participant. - tool_calls: - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionToolCall' - description: >- - List of tool calls. Each tool call is an OpenAIChatCompletionToolCall - object. - additionalProperties: false - required: - - role - title: OpenAIAssistantMessageParam - description: >- - A message containing the model's (assistant) response in an OpenAI-compatible - chat completion request. - "OpenAIChatCompletionContentPartImageParam": - type: object - properties: - type: - type: string - const: image_url - default: image_url - description: >- - Must be "image_url" to identify this as image content - image_url: - $ref: '#/components/schemas/OpenAIImageURL' - description: >- - Image URL specification and processing details - additionalProperties: false - required: - - type - - image_url - title: >- - OpenAIChatCompletionContentPartImageParam - description: >- - Image content part for OpenAI-compatible chat completion messages. - OpenAIChatCompletionContentPartParam: - oneOf: - - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' - - $ref: '#/components/schemas/OpenAIFile' - discriminator: - propertyName: type - mapping: - text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' - file: '#/components/schemas/OpenAIFile' - OpenAIChatCompletionContentPartTextParam: - type: object - properties: - type: - type: string - const: text - default: text - description: >- - Must be "text" to identify this as text content - text: - type: string - description: The text content of the message - additionalProperties: false - required: - - type - - text - title: OpenAIChatCompletionContentPartTextParam - description: >- - Text content part for OpenAI-compatible chat completion messages. - OpenAIChatCompletionToolCall: - type: object - properties: - index: - type: integer - description: >- - (Optional) Index of the tool call in the list - id: - type: string - description: >- - (Optional) Unique identifier for the tool call - type: - type: string - const: function - default: function - description: >- - Must be "function" to identify this as a function call - function: - $ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction' - description: (Optional) Function call details - additionalProperties: false - required: - - type - title: OpenAIChatCompletionToolCall - description: >- - Tool call specification for OpenAI-compatible chat completion responses. - OpenAIChatCompletionToolCallFunction: - type: object - properties: - name: - type: string - description: (Optional) Name of the function to call - arguments: - type: string - description: >- - (Optional) Arguments to pass to the function as a JSON string - additionalProperties: false - title: OpenAIChatCompletionToolCallFunction - description: >- - Function call details for OpenAI-compatible tool calls. - OpenAIChoice: - type: object - properties: - message: - $ref: '#/components/schemas/OpenAIMessageParam' - description: The message from the model - finish_reason: - type: string - description: The reason the model stopped generating - index: - type: integer - description: The index of the choice - logprobs: - $ref: '#/components/schemas/OpenAIChoiceLogprobs' - description: >- - (Optional) The log probabilities for the tokens in the message - additionalProperties: false - required: - - message - - finish_reason - - index - title: OpenAIChoice - description: >- - A choice from an OpenAI-compatible chat completion response. - OpenAIChoiceLogprobs: - type: object - properties: - content: - type: array - items: - $ref: '#/components/schemas/OpenAITokenLogProb' - description: >- - (Optional) The log probabilities for the tokens in the message - refusal: - type: array - items: - $ref: '#/components/schemas/OpenAITokenLogProb' - description: >- - (Optional) The log probabilities for the tokens in the message - additionalProperties: false - title: OpenAIChoiceLogprobs - description: >- - The log probabilities for the tokens in the message from an OpenAI-compatible - chat completion response. - OpenAIDeveloperMessageParam: - type: object - properties: - role: - type: string - const: developer - default: developer - description: >- - Must be "developer" to identify this as a developer message - content: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - description: The content of the developer message - name: - type: string - description: >- - (Optional) The name of the developer message participant. - additionalProperties: false - required: - - role - - content - title: OpenAIDeveloperMessageParam - description: >- - A message from the developer in an OpenAI-compatible chat completion request. - OpenAIFile: - type: object - properties: - type: - type: string - const: file - default: file - file: - $ref: '#/components/schemas/OpenAIFileFile' - additionalProperties: false - required: - - type - - file - title: OpenAIFile - OpenAIFileFile: - type: object - properties: - file_data: - type: string - file_id: - type: string - filename: - type: string - additionalProperties: false - title: OpenAIFileFile - OpenAIImageURL: - type: object - properties: - url: - type: string - description: >- - URL of the image to include in the message - detail: - type: string - description: >- - (Optional) Level of detail for image processing. Can be "low", "high", - or "auto" - additionalProperties: false - required: - - url - title: OpenAIImageURL - description: >- - Image URL specification for OpenAI-compatible chat completion messages. - OpenAIMessageParam: - oneOf: - - $ref: '#/components/schemas/OpenAIUserMessageParam' - - $ref: '#/components/schemas/OpenAISystemMessageParam' - - $ref: '#/components/schemas/OpenAIAssistantMessageParam' - - $ref: '#/components/schemas/OpenAIToolMessageParam' - - $ref: '#/components/schemas/OpenAIDeveloperMessageParam' - discriminator: - propertyName: role - mapping: - user: '#/components/schemas/OpenAIUserMessageParam' - system: '#/components/schemas/OpenAISystemMessageParam' - assistant: '#/components/schemas/OpenAIAssistantMessageParam' - tool: '#/components/schemas/OpenAIToolMessageParam' - developer: '#/components/schemas/OpenAIDeveloperMessageParam' - OpenAISystemMessageParam: - type: object - properties: - role: - type: string - const: system - default: system - description: >- - Must be "system" to identify this as a system message - content: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - description: >- - The content of the "system prompt". If multiple system messages are provided, - they are concatenated. The underlying Llama Stack code may also add other - system messages (for example, for formatting tool definitions). - name: - type: string - description: >- - (Optional) The name of the system message participant. - additionalProperties: false - required: - - role - - content - title: OpenAISystemMessageParam - description: >- - A system message providing instructions or context to the model. - OpenAITokenLogProb: - type: object - properties: - token: - type: string - bytes: - type: array - items: - type: integer - logprob: - type: number - top_logprobs: - type: array - items: - $ref: '#/components/schemas/OpenAITopLogProb' - additionalProperties: false - required: - - token - - logprob - - top_logprobs - title: OpenAITokenLogProb - description: >- - The log probability for a token from an OpenAI-compatible chat completion - response. - OpenAIToolMessageParam: - type: object - properties: - role: - type: string - const: tool - default: tool - description: >- - Must be "tool" to identify this as a tool response - tool_call_id: - type: string - description: >- - Unique identifier for the tool call this response is for - content: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - description: The response content from the tool - additionalProperties: false - required: - - role - - tool_call_id - - content - title: OpenAIToolMessageParam - description: >- - A message representing the result of a tool invocation in an OpenAI-compatible - chat completion request. - OpenAITopLogProb: - type: object - properties: - token: - type: string - bytes: - type: array - items: - type: integer - logprob: - type: number - additionalProperties: false - required: - - token - - logprob - title: OpenAITopLogProb - description: >- - The top log probability for a token from an OpenAI-compatible chat completion - response. - OpenAIUserMessageParam: - type: object - properties: - role: - type: string - const: user - default: user - description: >- - Must be "user" to identify this as a user message - content: - oneOf: - - type: string - - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam' - description: >- - The content of the message, which can include text and other media - name: - type: string - description: >- - (Optional) The name of the user message participant. - additionalProperties: false - required: - - role - - content - title: OpenAIUserMessageParam - description: >- - A message from the user in an OpenAI-compatible chat completion request. - OpenAICompletionWithInputMessages: - type: object - properties: - id: - type: string - description: The ID of the chat completion - choices: - type: array - items: - $ref: '#/components/schemas/OpenAIChoice' - description: List of choices - object: - type: string - const: chat.completion - default: chat.completion - description: >- - The object type, which will be "chat.completion" - created: - type: integer - description: >- - The Unix timestamp in seconds when the chat completion was created - model: - type: string - description: >- - The model that was used to generate the chat completion - input_messages: - type: array - items: - $ref: '#/components/schemas/OpenAIMessageParam' - additionalProperties: false - required: - - id - - choices - - object - - created - - model - - input_messages - title: OpenAICompletionWithInputMessages - DataSource: - oneOf: - - $ref: '#/components/schemas/URIDataSource' - - $ref: '#/components/schemas/RowsDataSource' - discriminator: - propertyName: type - mapping: - uri: '#/components/schemas/URIDataSource' - rows: '#/components/schemas/RowsDataSource' - Dataset: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: dataset - default: dataset - description: >- - Type of resource, always 'dataset' for datasets - purpose: - type: string - enum: - - post-training/messages - - eval/question-answer - - eval/messages-answer - description: >- - Purpose of the dataset indicating its intended use - source: - $ref: '#/components/schemas/DataSource' - description: >- - Data source configuration for the dataset - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Additional metadata for the dataset - additionalProperties: false - required: - - identifier - - provider_id - - type - - purpose - - source - - metadata - title: Dataset - description: >- - Dataset resource for storing and accessing training or evaluation data. - RowsDataSource: - type: object - properties: - type: - type: string - const: rows - default: rows - rows: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The dataset is stored in rows. E.g. - [ {"messages": [{"role": "user", - "content": "Hello, world!"}, {"role": "assistant", "content": "Hello, - world!"}]} ] - additionalProperties: false - required: - - type - - rows - title: RowsDataSource - description: A dataset stored in rows. - URIDataSource: - type: object - properties: - type: - type: string - const: uri - default: uri - uri: - type: string - description: >- - The dataset can be obtained from a URI. E.g. - "https://mywebsite.com/mydata.jsonl" - - "lsfs://mydata.jsonl" - "data:csv;base64,{base64_content}" - additionalProperties: false - required: - - type - - uri - title: URIDataSource - description: >- - A dataset that can be obtained from a URI. - Model: - type: object - properties: - identifier: - type: string - description: >- - Unique identifier for this resource in llama stack - provider_resource_id: - type: string - description: >- - Unique identifier for this resource in the provider - provider_id: - type: string - description: >- - ID of the provider that owns this resource - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: model - default: model - description: >- - The resource type, always 'model' for model resources - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Any additional metadata for this model - model_type: - $ref: '#/components/schemas/ModelType' - default: llm - description: >- - The type of model (LLM or embedding model) - additionalProperties: false - required: - - identifier - - provider_id - - type - - metadata - - model_type - title: Model - description: >- - A model resource representing an AI model registered in Llama Stack. - ModelType: - type: string - enum: - - llm - - embedding - title: ModelType - description: >- - Enumeration of supported model types in Llama Stack. - AgentTurnInputType: - type: object - properties: - type: - type: string - const: agent_turn_input - default: agent_turn_input - description: >- - Discriminator type. Always "agent_turn_input" - additionalProperties: false - required: - - type - title: AgentTurnInputType - description: Parameter type for agent turn input. - ArrayType: - type: object - properties: - type: - type: string - const: array - default: array - description: Discriminator type. Always "array" - additionalProperties: false - required: - - type - title: ArrayType - description: Parameter type for array values. - BooleanType: - type: object - properties: - type: - type: string - const: boolean - default: boolean - description: Discriminator type. Always "boolean" - additionalProperties: false - required: - - type - title: BooleanType - description: Parameter type for boolean values. - ChatCompletionInputType: - type: object - properties: - type: - type: string - const: chat_completion_input - default: chat_completion_input - description: >- - Discriminator type. Always "chat_completion_input" - additionalProperties: false - required: - - type - title: ChatCompletionInputType - description: >- - Parameter type for chat completion input. - CompletionInputType: - type: object - properties: - type: - type: string - const: completion_input - default: completion_input - description: >- - Discriminator type. Always "completion_input" - additionalProperties: false - required: - - type - title: CompletionInputType - description: Parameter type for completion input. - JsonType: - type: object - properties: - type: - type: string - const: json - default: json - description: Discriminator type. Always "json" - additionalProperties: false - required: - - type - title: JsonType - description: Parameter type for JSON values. - NumberType: - type: object - properties: - type: - type: string - const: number - default: number - description: Discriminator type. Always "number" - additionalProperties: false - required: - - type - title: NumberType - description: Parameter type for numeric values. - ObjectType: - type: object - properties: - type: - type: string - const: object - default: object - description: Discriminator type. Always "object" - additionalProperties: false - required: - - type - title: ObjectType - description: Parameter type for object values. - ParamType: - oneOf: - - $ref: '#/components/schemas/StringType' - - $ref: '#/components/schemas/NumberType' - - $ref: '#/components/schemas/BooleanType' - - $ref: '#/components/schemas/ArrayType' - - $ref: '#/components/schemas/ObjectType' - - $ref: '#/components/schemas/JsonType' - - $ref: '#/components/schemas/UnionType' - - $ref: '#/components/schemas/ChatCompletionInputType' - - $ref: '#/components/schemas/CompletionInputType' - - $ref: '#/components/schemas/AgentTurnInputType' - discriminator: - propertyName: type - mapping: - string: '#/components/schemas/StringType' - number: '#/components/schemas/NumberType' - boolean: '#/components/schemas/BooleanType' - array: '#/components/schemas/ArrayType' - object: '#/components/schemas/ObjectType' - json: '#/components/schemas/JsonType' - union: '#/components/schemas/UnionType' - chat_completion_input: '#/components/schemas/ChatCompletionInputType' - completion_input: '#/components/schemas/CompletionInputType' - agent_turn_input: '#/components/schemas/AgentTurnInputType' - ScoringFn: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: scoring_function - default: scoring_function - description: >- - The resource type, always scoring_function - description: - type: string - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - return_type: - $ref: '#/components/schemas/ParamType' - params: - $ref: '#/components/schemas/ScoringFnParams' - additionalProperties: false - required: - - identifier - - provider_id - - type - - metadata - - return_type - title: ScoringFn - description: >- - A scoring function resource for evaluating model outputs. - StringType: - type: object - properties: - type: - type: string - const: string - default: string - description: Discriminator type. Always "string" - additionalProperties: false - required: - - type - title: StringType - description: Parameter type for string values. - UnionType: - type: object - properties: - type: - type: string - const: union - default: union - description: Discriminator type. Always "union" - additionalProperties: false - required: - - type - title: UnionType - description: Parameter type for union values. - Shield: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: shield - default: shield - description: The resource type, always shield - params: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Configuration parameters for the shield - additionalProperties: false - required: - - identifier - - provider_id - - type - title: Shield - description: >- - A safety shield resource that can be used to check content. - Span: - type: object - properties: - span_id: - type: string - description: Unique identifier for the span - trace_id: - type: string - description: >- - Unique identifier for the trace this span belongs to - parent_span_id: - type: string - description: >- - (Optional) Unique identifier for the parent span, if this is a child span - name: - type: string - description: >- - Human-readable name describing the operation this span represents - start_time: - type: string - format: date-time - description: Timestamp when the operation began - end_time: - type: string - format: date-time - description: >- - (Optional) Timestamp when the operation finished, if completed - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Key-value pairs containing additional metadata about the span - additionalProperties: false - required: - - span_id - - trace_id - - name - - start_time - title: Span - description: >- - A span representing a single operation within a trace. - GetSpanTreeRequest: - type: object - properties: - attributes_to_return: - type: array - items: - type: string - description: The attributes to return in the tree. - max_depth: - type: integer - description: The maximum depth of the tree. - additionalProperties: false - title: GetSpanTreeRequest - SpanStatus: - type: string - enum: - - ok - - error - title: SpanStatus - description: >- - The status of a span indicating whether it completed successfully or with - an error. - SpanWithStatus: - type: object - properties: - span_id: - type: string - description: Unique identifier for the span - trace_id: - type: string - description: >- - Unique identifier for the trace this span belongs to - parent_span_id: - type: string - description: >- - (Optional) Unique identifier for the parent span, if this is a child span - name: - type: string - description: >- - Human-readable name describing the operation this span represents - start_time: - type: string - format: date-time - description: Timestamp when the operation began - end_time: - type: string - format: date-time - description: >- - (Optional) Timestamp when the operation finished, if completed - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Key-value pairs containing additional metadata about the span - status: - $ref: '#/components/schemas/SpanStatus' - description: >- - (Optional) The current status of the span - additionalProperties: false - required: - - span_id - - trace_id - - name - - start_time - title: SpanWithStatus - description: A span that includes status information. - QuerySpanTreeResponse: - type: object - properties: - data: - type: object - additionalProperties: - $ref: '#/components/schemas/SpanWithStatus' - description: >- - Dictionary mapping span IDs to spans with status information - additionalProperties: false - required: - - data - title: QuerySpanTreeResponse - description: >- - Response containing a tree structure of spans. - Tool: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: tool - default: tool - description: Type of resource, always 'tool' - toolgroup_id: - type: string - description: >- - ID of the tool group this tool belongs to - description: - type: string - description: >- - Human-readable description of what the tool does - parameters: - type: array - items: - $ref: '#/components/schemas/ToolParameter' - description: List of parameters this tool accepts - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional metadata about the tool - additionalProperties: false - required: - - identifier - - provider_id - - type - - toolgroup_id - - description - - parameters - title: Tool - description: A tool that can be invoked by agents. - ToolGroup: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: tool_group - default: tool_group - description: Type of resource, always 'tool_group' - mcp_endpoint: - $ref: '#/components/schemas/URL' - description: >- - (Optional) Model Context Protocol endpoint for remote tools - args: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional arguments for the tool group - additionalProperties: false - required: - - identifier - - provider_id - - type - title: ToolGroup - description: >- - A group of related tools managed together. - Trace: - type: object - properties: - trace_id: - type: string - description: Unique identifier for the trace - root_span_id: - type: string - description: >- - Unique identifier for the root span that started this trace - start_time: - type: string - format: date-time - description: Timestamp when the trace began - end_time: - type: string - format: date-time - description: >- - (Optional) Timestamp when the trace finished, if completed - additionalProperties: false - required: - - trace_id - - root_span_id - - start_time - title: Trace - description: >- - A trace representing the complete execution path of a request across multiple - operations. - Checkpoint: - type: object - properties: - identifier: - type: string - description: Unique identifier for the checkpoint - created_at: - type: string - format: date-time - description: >- - Timestamp when the checkpoint was created - epoch: - type: integer - description: >- - Training epoch when the checkpoint was saved - post_training_job_id: - type: string - description: >- - Identifier of the training job that created this checkpoint - path: - type: string - description: >- - File system path where the checkpoint is stored - training_metrics: - $ref: '#/components/schemas/PostTrainingMetric' - description: >- - (Optional) Training metrics associated with this checkpoint - additionalProperties: false - required: - - identifier - - created_at - - epoch - - post_training_job_id - - path - title: Checkpoint - description: Checkpoint created during training runs. - PostTrainingJobArtifactsResponse: - type: object - properties: - job_uuid: - type: string - description: Unique identifier for the training job - checkpoints: - type: array - items: - $ref: '#/components/schemas/Checkpoint' - description: >- - List of model checkpoints created during training - additionalProperties: false - required: - - job_uuid - - checkpoints - title: PostTrainingJobArtifactsResponse - description: Artifacts of a finetuning job. - PostTrainingMetric: - type: object - properties: - epoch: - type: integer - description: Training epoch number - train_loss: - type: number - description: Loss value on the training dataset - validation_loss: - type: number - description: Loss value on the validation dataset - perplexity: - type: number - description: >- - Perplexity metric indicating model confidence - additionalProperties: false - required: - - epoch - - train_loss - - validation_loss - - perplexity - title: PostTrainingMetric - description: >- - Training metrics captured during post-training jobs. - PostTrainingJobStatusResponse: - type: object - properties: - job_uuid: - type: string - description: Unique identifier for the training job - status: - type: string - enum: - - completed - - in_progress - - failed - - scheduled - - cancelled - description: Current status of the training job - scheduled_at: - type: string - format: date-time - description: >- - (Optional) Timestamp when the job was scheduled - started_at: - type: string - format: date-time - description: >- - (Optional) Timestamp when the job execution began - completed_at: - type: string - format: date-time - description: >- - (Optional) Timestamp when the job finished, if completed - resources_allocated: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Information about computational resources allocated to the - job - checkpoints: - type: array - items: - $ref: '#/components/schemas/Checkpoint' - description: >- - List of model checkpoints created during training - additionalProperties: false - required: - - job_uuid - - status - - checkpoints - title: PostTrainingJobStatusResponse - description: Status of a finetuning job. - ListPostTrainingJobsResponse: - type: object - properties: - data: - type: array - items: - type: object - properties: - job_uuid: - type: string - additionalProperties: false - required: - - job_uuid - title: PostTrainingJob - additionalProperties: false - required: - - data - title: ListPostTrainingJobsResponse - VectorDB: - type: object - properties: - identifier: - type: string - provider_resource_id: - type: string - provider_id: - type: string - type: - type: string - enum: - - model - - shield - - vector_db - - dataset - - scoring_function - - benchmark - - tool - - tool_group - - prompt - const: vector_db - default: vector_db - description: >- - Type of resource, always 'vector_db' for vector databases - embedding_model: - type: string - description: >- - Name of the embedding model to use for vector generation - embedding_dimension: - type: integer - description: Dimension of the embedding vectors - vector_db_name: - type: string - additionalProperties: false - required: - - identifier - - provider_id - - type - - embedding_model - - embedding_dimension - title: VectorDB - description: >- - Vector database resource for storing and querying vector embeddings. - HealthInfo: - type: object - properties: - status: - type: string - enum: - - OK - - Error - - Not Implemented - description: Current health status of the service - additionalProperties: false - required: - - status - title: HealthInfo - description: >- - Health status information for the service. - RAGDocument: - type: object - properties: - document_id: - type: string - description: The unique identifier for the document. - content: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - type: array - items: - $ref: '#/components/schemas/InterleavedContentItem' - - $ref: '#/components/schemas/URL' - description: The content of the document. - mime_type: - type: string - description: The MIME type of the document. - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Additional metadata for the document. - additionalProperties: false - required: - - document_id - - content - - metadata - title: RAGDocument - description: >- - A document to be used for document ingestion in the RAG Tool. - InsertRequest: - type: object - properties: - documents: - type: array - items: - $ref: '#/components/schemas/RAGDocument' - description: >- - List of documents to index in the RAG system - vector_db_id: - type: string - description: >- - ID of the vector database to store the document embeddings - chunk_size_in_tokens: - type: integer - description: >- - (Optional) Size in tokens for document chunking during indexing - additionalProperties: false - required: - - documents - - vector_db_id - - chunk_size_in_tokens - title: InsertRequest - Chunk: - type: object - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - The content of the chunk, which can be interleaved text, images, or other - types. - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Metadata associated with the chunk that will be used in the model context - during inference. - embedding: - type: array - items: - type: number - description: >- - Optional embedding for the chunk. If not provided, it will be computed - later. - stored_chunk_id: - type: string - description: >- - The chunk ID that is stored in the vector database. Used for backend functionality. - chunk_metadata: - $ref: '#/components/schemas/ChunkMetadata' - description: >- - Metadata for the chunk that will NOT be used in the context during inference. - The `chunk_metadata` is required backend functionality. - additionalProperties: false - required: - - content - - metadata - title: Chunk - description: >- - A chunk of content that can be inserted into a vector database. - ChunkMetadata: - type: object - properties: - chunk_id: - type: string - description: >- - The ID of the chunk. If not set, it will be generated based on the document - ID and content. - document_id: - type: string - description: >- - The ID of the document this chunk belongs to. - source: - type: string - description: >- - The source of the content, such as a URL, file path, or other identifier. - created_timestamp: - type: integer - description: >- - An optional timestamp indicating when the chunk was created. - updated_timestamp: - type: integer - description: >- - An optional timestamp indicating when the chunk was last updated. - chunk_window: - type: string - description: >- - The window of the chunk, which can be used to group related chunks together. - chunk_tokenizer: - type: string - description: >- - The tokenizer used to create the chunk. Default is Tiktoken. - chunk_embedding_model: - type: string - description: >- - The embedding model used to create the chunk's embedding. - chunk_embedding_dimension: - type: integer - description: >- - The dimension of the embedding vector for the chunk. - content_token_count: - type: integer - description: >- - The number of tokens in the content of the chunk. - metadata_token_count: - type: integer - description: >- - The number of tokens in the metadata of the chunk. - additionalProperties: false - title: ChunkMetadata - description: >- - `ChunkMetadata` is backend metadata for a `Chunk` that is used to store additional - information about the chunk that will not be used in the context during - inference, but is required for backend functionality. The `ChunkMetadata` is - set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not - expected to change after. Use `Chunk.metadata` for metadata that will - be used in the context during inference. - InsertChunksRequest: - type: object - properties: - vector_db_id: - type: string - description: >- - The identifier of the vector database to insert the chunks into. - chunks: - type: array - items: - $ref: '#/components/schemas/Chunk' - description: >- - The chunks to insert. Each `Chunk` should contain content which can be - interleaved text, images, or other types. `metadata`: `dict[str, Any]` - and `embedding`: `List[float]` are optional. If `metadata` is provided, - you configure how Llama Stack formats the chunk during generation. If - `embedding` is not provided, it will be computed later. - ttl_seconds: - type: integer - description: The time to live of the chunks. - additionalProperties: false - required: - - vector_db_id - - chunks - title: InsertChunksRequest - ProviderInfo: - type: object - properties: - api: - type: string - description: The API name this provider implements - provider_id: - type: string - description: Unique identifier for the provider - provider_type: - type: string - description: The type of provider implementation - config: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Configuration parameters for the provider - health: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Current health status of the provider - additionalProperties: false - required: - - api - - provider_id - - provider_type - - config - - health - title: ProviderInfo - description: >- - Information about a registered provider including its configuration and health - status. - InvokeToolRequest: - type: object - properties: - tool_name: - type: string - description: The name of the tool to invoke. - kwargs: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - A dictionary of arguments to pass to the tool. - additionalProperties: false - required: - - tool_name - - kwargs - title: InvokeToolRequest - ToolInvocationResult: - type: object - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - (Optional) The output content from the tool execution - error_message: - type: string - description: >- - (Optional) Error message if the tool execution failed - error_code: - type: integer - description: >- - (Optional) Numeric error code if the tool execution failed - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Additional metadata about the tool execution - additionalProperties: false - title: ToolInvocationResult - description: Result of a tool invocation. - PaginatedResponse: - type: object - properties: - data: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The list of items for the current page - has_more: - type: boolean - description: >- - Whether there are more items available after this set - url: - type: string - description: The URL for accessing this list - additionalProperties: false - required: - - data - - has_more - title: PaginatedResponse - description: >- - A generic paginated response that follows a simple format. - Job: - type: object - properties: - job_id: - type: string - description: Unique identifier for the job - status: - type: string - enum: - - completed - - in_progress - - failed - - scheduled - - cancelled - description: Current execution status of the job - additionalProperties: false - required: - - job_id - - status - title: Job - description: >- - A job execution instance with status tracking. - ListBenchmarksResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Benchmark' - additionalProperties: false - required: - - data - title: ListBenchmarksResponse - Order: - type: string - enum: - - asc - - desc - title: Order - description: Sort order for paginated responses. - ListOpenAIChatCompletionResponse: - type: object - properties: - data: - type: array - items: - type: object - properties: - id: - type: string - description: The ID of the chat completion - choices: - type: array - items: - $ref: '#/components/schemas/OpenAIChoice' - description: List of choices - object: - type: string - const: chat.completion - default: chat.completion - description: >- - The object type, which will be "chat.completion" - created: - type: integer - description: >- - The Unix timestamp in seconds when the chat completion was created - model: - type: string - description: >- - The model that was used to generate the chat completion - input_messages: - type: array - items: - $ref: '#/components/schemas/OpenAIMessageParam' - additionalProperties: false - required: - - id - - choices - - object - - created - - model - - input_messages - title: OpenAICompletionWithInputMessages - description: >- - List of chat completion objects with their input messages - has_more: - type: boolean - description: >- - Whether there are more completions available beyond this list - first_id: - type: string - description: ID of the first completion in this list - last_id: - type: string - description: ID of the last completion in this list - object: - type: string - const: list - default: list - description: >- - Must be "list" to identify this as a list response - additionalProperties: false - required: - - data - - has_more - - first_id - - last_id - - object - title: ListOpenAIChatCompletionResponse - description: >- - Response from listing OpenAI-compatible chat completions. - ListDatasetsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Dataset' - description: List of datasets - additionalProperties: false - required: - - data - title: ListDatasetsResponse - description: Response from listing datasets. - ListModelsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Model' - additionalProperties: false - required: - - data - title: ListModelsResponse - ListOpenAIResponseInputItem: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseInput' - description: List of input items - object: - type: string - const: list - default: list - description: Object type identifier, always "list" - additionalProperties: false - required: - - data - - object - title: ListOpenAIResponseInputItem - description: >- - List container for OpenAI response input items. - ListOpenAIResponseObject: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseObjectWithInput' - description: >- - List of response objects with their input context - has_more: - type: boolean - description: >- - Whether there are more results available beyond this page - first_id: - type: string - description: >- - Identifier of the first item in this page - last_id: - type: string - description: Identifier of the last item in this page - object: - type: string - const: list - default: list - description: Object type identifier, always "list" - additionalProperties: false - required: - - data - - has_more - - first_id - - last_id - - object - title: ListOpenAIResponseObject - description: >- - Paginated list of OpenAI response objects with navigation metadata. - OpenAIResponseObjectWithInput: - type: object - properties: - created_at: - type: integer - description: >- - Unix timestamp when the response was created - error: - $ref: '#/components/schemas/OpenAIResponseError' - description: >- - (Optional) Error details if the response generation failed - id: - type: string - description: Unique identifier for this response - model: - type: string - description: Model identifier used for generation - object: - type: string - const: response - default: response - description: >- - Object type identifier, always "response" - output: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseOutput' - description: >- - List of generated output items (messages, tool calls, etc.) - parallel_tool_calls: - type: boolean - default: false - description: >- - Whether tool calls can be executed in parallel - previous_response_id: - type: string - description: >- - (Optional) ID of the previous response in a conversation - status: - type: string - description: >- - Current status of the response generation - temperature: - type: number - description: >- - (Optional) Sampling temperature used for generation - text: - $ref: '#/components/schemas/OpenAIResponseText' - description: >- - Text formatting configuration for the response - top_p: - type: number - description: >- - (Optional) Nucleus sampling parameter used for generation - truncation: - type: string - description: >- - (Optional) Truncation strategy applied to the response - user: - type: string - description: >- - (Optional) User identifier associated with the request - input: - type: array - items: - $ref: '#/components/schemas/OpenAIResponseInput' - description: >- - List of input items that led to this response - additionalProperties: false - required: - - created_at - - id - - model - - object - - output - - parallel_tool_calls - - status - - text - - input - title: OpenAIResponseObjectWithInput - description: >- - OpenAI response object extended with input context information. - ListPromptsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Prompt' - additionalProperties: false - required: - - data - title: ListPromptsResponse - description: Response model to list prompts. - ListProvidersResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/ProviderInfo' - description: List of provider information objects - additionalProperties: false - required: - - data - title: ListProvidersResponse - description: >- - Response containing a list of all available providers. - RouteInfo: - type: object - properties: - route: - type: string - description: The API endpoint path - method: - type: string - description: HTTP method for the route - provider_types: - type: array - items: - type: string - description: >- - List of provider types that implement this route - additionalProperties: false - required: - - route - - method - - provider_types - title: RouteInfo - description: >- - Information about an API route including its path, method, and implementing - providers. - ListRoutesResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/RouteInfo' - description: >- - List of available route information objects - additionalProperties: false - required: - - data - title: ListRoutesResponse - description: >- - Response containing a list of all available API routes. - ListToolDefsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/ToolDef' - description: List of tool definitions - additionalProperties: false - required: - - data - title: ListToolDefsResponse - description: >- - Response containing a list of tool definitions. - ListScoringFunctionsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/ScoringFn' - additionalProperties: false - required: - - data - title: ListScoringFunctionsResponse - ListShieldsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Shield' - additionalProperties: false - required: - - data - title: ListShieldsResponse - ListToolGroupsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/ToolGroup' - description: List of tool groups - additionalProperties: false - required: - - data - title: ListToolGroupsResponse - description: >- - Response containing a list of tool groups. - ListToolsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Tool' - description: List of tools - additionalProperties: false - required: - - data - title: ListToolsResponse - description: Response containing a list of tools. - ListVectorDBsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/VectorDB' - description: List of vector databases - additionalProperties: false - required: - - data - title: ListVectorDBsResponse - description: Response from listing vector databases. - Event: - oneOf: - - $ref: '#/components/schemas/UnstructuredLogEvent' - - $ref: '#/components/schemas/MetricEvent' - - $ref: '#/components/schemas/StructuredLogEvent' - discriminator: - propertyName: type - mapping: - unstructured_log: '#/components/schemas/UnstructuredLogEvent' - metric: '#/components/schemas/MetricEvent' - structured_log: '#/components/schemas/StructuredLogEvent' - EventType: - type: string - enum: - - unstructured_log - - structured_log - - metric - title: EventType - description: >- - The type of telemetry event being logged. - LogSeverity: - type: string - enum: - - verbose - - debug - - info - - warn - - error - - critical - title: LogSeverity - description: The severity level of a log message. - MetricEvent: - type: object - properties: - trace_id: - type: string - description: >- - Unique identifier for the trace this event belongs to - span_id: - type: string - description: >- - Unique identifier for the span this event belongs to - timestamp: - type: string - format: date-time - description: Timestamp when the event occurred - attributes: - type: object - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - description: >- - (Optional) Key-value pairs containing additional metadata about the event - type: - $ref: '#/components/schemas/EventType' - const: metric - default: metric - description: Event type identifier set to METRIC - metric: - type: string - description: The name of the metric being measured - value: - oneOf: - - type: integer - - type: number - description: >- - The numeric value of the metric measurement - unit: - type: string - description: >- - The unit of measurement for the metric value - additionalProperties: false - required: - - trace_id - - span_id - - timestamp - - type - - metric - - value - - unit - title: MetricEvent - description: >- - A metric event containing a measured value. - SpanEndPayload: - type: object - properties: - type: - $ref: '#/components/schemas/StructuredLogType' - const: span_end - default: span_end - description: Payload type identifier set to SPAN_END - status: - $ref: '#/components/schemas/SpanStatus' - description: >- - The final status of the span indicating success or failure - additionalProperties: false - required: - - type - - status - title: SpanEndPayload - description: Payload for a span end event. - SpanStartPayload: - type: object - properties: - type: - $ref: '#/components/schemas/StructuredLogType' - const: span_start - default: span_start - description: >- - Payload type identifier set to SPAN_START - name: - type: string - description: >- - Human-readable name describing the operation this span represents - parent_span_id: - type: string - description: >- - (Optional) Unique identifier for the parent span, if this is a child span - additionalProperties: false - required: - - type - - name - title: SpanStartPayload - description: Payload for a span start event. - StructuredLogEvent: - type: object - properties: - trace_id: - type: string - description: >- - Unique identifier for the trace this event belongs to - span_id: - type: string - description: >- - Unique identifier for the span this event belongs to - timestamp: - type: string - format: date-time - description: Timestamp when the event occurred - attributes: - type: object - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - description: >- - (Optional) Key-value pairs containing additional metadata about the event - type: - $ref: '#/components/schemas/EventType' - const: structured_log - default: structured_log - description: >- - Event type identifier set to STRUCTURED_LOG - payload: - $ref: '#/components/schemas/StructuredLogPayload' - description: >- - The structured payload data for the log event - additionalProperties: false - required: - - trace_id - - span_id - - timestamp - - type - - payload - title: StructuredLogEvent - description: >- - A structured log event containing typed payload data. - StructuredLogPayload: - oneOf: - - $ref: '#/components/schemas/SpanStartPayload' - - $ref: '#/components/schemas/SpanEndPayload' - discriminator: - propertyName: type - mapping: - span_start: '#/components/schemas/SpanStartPayload' - span_end: '#/components/schemas/SpanEndPayload' - StructuredLogType: - type: string - enum: - - span_start - - span_end - title: StructuredLogType - description: >- - The type of structured log event payload. - UnstructuredLogEvent: - type: object - properties: - trace_id: - type: string - description: >- - Unique identifier for the trace this event belongs to - span_id: - type: string - description: >- - Unique identifier for the span this event belongs to - timestamp: - type: string - format: date-time - description: Timestamp when the event occurred - attributes: - type: object - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - description: >- - (Optional) Key-value pairs containing additional metadata about the event - type: - $ref: '#/components/schemas/EventType' - const: unstructured_log - default: unstructured_log - description: >- - Event type identifier set to UNSTRUCTURED_LOG - message: - type: string - description: The log message text - severity: - $ref: '#/components/schemas/LogSeverity' - description: The severity level of the log message - additionalProperties: false - required: - - trace_id - - span_id - - timestamp - - type - - message - - severity - title: UnstructuredLogEvent - description: >- - An unstructured log event containing a simple text message. - LogEventRequest: - type: object - properties: - event: - $ref: '#/components/schemas/Event' - description: The event to log. - ttl_seconds: - type: integer - description: The time to live of the event. - additionalProperties: false - required: - - event - - ttl_seconds - title: LogEventRequest - VectorStoreChunkingStrategy: - oneOf: - - $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto' - - $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic' - discriminator: - propertyName: type - mapping: - auto: '#/components/schemas/VectorStoreChunkingStrategyAuto' - static: '#/components/schemas/VectorStoreChunkingStrategyStatic' - VectorStoreChunkingStrategyAuto: - type: object - properties: - type: - type: string - const: auto - default: auto - description: >- - Strategy type, always "auto" for automatic chunking - additionalProperties: false - required: - - type - title: VectorStoreChunkingStrategyAuto - description: >- - Automatic chunking strategy for vector store files. - VectorStoreChunkingStrategyStatic: - type: object - properties: - type: - type: string - const: static - default: static - description: >- - Strategy type, always "static" for static chunking - static: - $ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig' - description: >- - Configuration parameters for the static chunking strategy - additionalProperties: false - required: - - type - - static - title: VectorStoreChunkingStrategyStatic - description: >- - Static chunking strategy with configurable parameters. - VectorStoreChunkingStrategyStaticConfig: - type: object - properties: - chunk_overlap_tokens: - type: integer - default: 400 - description: >- - Number of tokens to overlap between adjacent chunks - max_chunk_size_tokens: - type: integer - default: 800 - description: >- - Maximum number of tokens per chunk, must be between 100 and 4096 - additionalProperties: false - required: - - chunk_overlap_tokens - - max_chunk_size_tokens - title: VectorStoreChunkingStrategyStaticConfig - description: >- - Configuration for static chunking strategy. - OpenaiAttachFileToVectorStoreRequest: - type: object - properties: - file_id: - type: string - description: >- - The ID of the file to attach to the vector store. - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The key-value attributes stored with the file, which can be used for filtering. - chunking_strategy: - $ref: '#/components/schemas/VectorStoreChunkingStrategy' - description: >- - The chunking strategy to use for the file. - additionalProperties: false - required: - - file_id - title: OpenaiAttachFileToVectorStoreRequest - VectorStoreFileLastError: - type: object - properties: - code: - oneOf: - - type: string - const: server_error - - type: string - const: rate_limit_exceeded - description: >- - Error code indicating the type of failure - message: - type: string - description: >- - Human-readable error message describing the failure - additionalProperties: false - required: - - code - - message - title: VectorStoreFileLastError - description: >- - Error information for failed vector store file processing. - VectorStoreFileObject: - type: object - properties: - id: - type: string - description: Unique identifier for the file - object: - type: string - default: vector_store.file - description: >- - Object type identifier, always "vector_store.file" - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Key-value attributes associated with the file - chunking_strategy: - $ref: '#/components/schemas/VectorStoreChunkingStrategy' - description: >- - Strategy used for splitting the file into chunks - created_at: - type: integer - description: >- - Timestamp when the file was added to the vector store - last_error: - $ref: '#/components/schemas/VectorStoreFileLastError' - description: >- - (Optional) Error information if file processing failed - status: - $ref: '#/components/schemas/VectorStoreFileStatus' - description: Current processing status of the file - usage_bytes: - type: integer - default: 0 - description: Storage space used by this file in bytes - vector_store_id: - type: string - description: >- - ID of the vector store containing this file - additionalProperties: false - required: - - id - - object - - attributes - - chunking_strategy - - created_at - - status - - usage_bytes - - vector_store_id - title: VectorStoreFileObject - description: OpenAI Vector Store File object. - VectorStoreFileStatus: - oneOf: - - type: string - const: completed - - type: string - const: in_progress - - type: string - const: cancelled - - type: string - const: failed - OpenAIJSONSchema: - type: object - properties: - name: - type: string - description: Name of the schema - description: - type: string - description: (Optional) Description of the schema - strict: - type: boolean - description: >- - (Optional) Whether to enforce strict adherence to the schema - schema: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) The JSON schema definition - additionalProperties: false - required: - - name - title: OpenAIJSONSchema - description: >- - JSON schema specification for OpenAI-compatible structured response format. - OpenAIResponseFormatJSONObject: - type: object - properties: - type: - type: string - const: json_object - default: json_object - description: >- - Must be "json_object" to indicate generic JSON object response format - additionalProperties: false - required: - - type - title: OpenAIResponseFormatJSONObject - description: >- - JSON object response format for OpenAI-compatible chat completion requests. - OpenAIResponseFormatJSONSchema: - type: object - properties: - type: - type: string - const: json_schema - default: json_schema - description: >- - Must be "json_schema" to indicate structured JSON response format - json_schema: - $ref: '#/components/schemas/OpenAIJSONSchema' - description: >- - The JSON schema specification for the response - additionalProperties: false - required: - - type - - json_schema - title: OpenAIResponseFormatJSONSchema - description: >- - JSON schema response format for OpenAI-compatible chat completion requests. - OpenAIResponseFormatParam: - oneOf: - - $ref: '#/components/schemas/OpenAIResponseFormatText' - - $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema' - - $ref: '#/components/schemas/OpenAIResponseFormatJSONObject' - discriminator: - propertyName: type - mapping: - text: '#/components/schemas/OpenAIResponseFormatText' - json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema' - json_object: '#/components/schemas/OpenAIResponseFormatJSONObject' - OpenAIResponseFormatText: - type: object - properties: - type: - type: string - const: text - default: text - description: >- - Must be "text" to indicate plain text response format - additionalProperties: false - required: - - type - title: OpenAIResponseFormatText - description: >- - Text response format for OpenAI-compatible chat completion requests. - OpenaiChatCompletionRequest: - type: object - properties: - model: - type: string - description: >- - The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint. - messages: - type: array - items: - $ref: '#/components/schemas/OpenAIMessageParam' - description: List of messages in the conversation. - frequency_penalty: - type: number - description: >- - (Optional) The penalty for repeated tokens. - function_call: - oneOf: - - type: string - - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) The function call to use. - functions: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) List of functions to use. - logit_bias: - type: object - additionalProperties: - type: number - description: (Optional) The logit bias to use. - logprobs: - type: boolean - description: (Optional) The log probabilities to use. - max_completion_tokens: - type: integer - description: >- - (Optional) The maximum number of tokens to generate. - max_tokens: - type: integer - description: >- - (Optional) The maximum number of tokens to generate. - n: - type: integer - description: >- - (Optional) The number of completions to generate. - parallel_tool_calls: - type: boolean - description: >- - (Optional) Whether to parallelize tool calls. - presence_penalty: - type: number - description: >- - (Optional) The penalty for repeated tokens. - response_format: - $ref: '#/components/schemas/OpenAIResponseFormatParam' - description: (Optional) The response format to use. - seed: - type: integer - description: (Optional) The seed to use. - stop: - oneOf: - - type: string - - type: array - items: - type: string - description: (Optional) The stop tokens to use. - stream: - type: boolean - description: >- - (Optional) Whether to stream the response. - stream_options: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) The stream options to use. - temperature: - type: number - description: (Optional) The temperature to use. - tool_choice: - oneOf: - - type: string - - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) The tool choice to use. - tools: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) The tools to use. - top_logprobs: - type: integer - description: >- - (Optional) The top log probabilities to use. - top_p: - type: number - description: (Optional) The top p to use. - user: - type: string - description: (Optional) The user to use. - additionalProperties: false - required: - - model - - messages - title: OpenaiChatCompletionRequest - OpenAIChatCompletion: - type: object - properties: - id: - type: string - description: The ID of the chat completion - choices: - type: array - items: - $ref: '#/components/schemas/OpenAIChoice' - description: List of choices - object: - type: string - const: chat.completion - default: chat.completion - description: >- - The object type, which will be "chat.completion" - created: - type: integer - description: >- - The Unix timestamp in seconds when the chat completion was created - model: - type: string - description: >- - The model that was used to generate the chat completion - additionalProperties: false - required: - - id - - choices - - object - - created - - model - title: OpenAIChatCompletion - description: >- - Response from an OpenAI-compatible chat completion request. - OpenAIChatCompletionChunk: - type: object - properties: - id: - type: string - description: The ID of the chat completion - choices: - type: array - items: - $ref: '#/components/schemas/OpenAIChunkChoice' - description: List of choices - object: - type: string - const: chat.completion.chunk - default: chat.completion.chunk - description: >- - The object type, which will be "chat.completion.chunk" - created: - type: integer - description: >- - The Unix timestamp in seconds when the chat completion was created - model: - type: string - description: >- - The model that was used to generate the chat completion - additionalProperties: false - required: - - id - - choices - - object - - created - - model - title: OpenAIChatCompletionChunk - description: >- - Chunk from a streaming response to an OpenAI-compatible chat completion request. - OpenAIChoiceDelta: - type: object - properties: - content: - type: string - description: (Optional) The content of the delta - refusal: - type: string - description: (Optional) The refusal of the delta - role: - type: string - description: (Optional) The role of the delta - tool_calls: - type: array - items: - $ref: '#/components/schemas/OpenAIChatCompletionToolCall' - description: (Optional) The tool calls of the delta - additionalProperties: false - title: OpenAIChoiceDelta - description: >- - A delta from an OpenAI-compatible chat completion streaming response. - OpenAIChunkChoice: - type: object - properties: - delta: - $ref: '#/components/schemas/OpenAIChoiceDelta' - description: The delta from the chunk - finish_reason: - type: string - description: The reason the model stopped generating - index: - type: integer - description: The index of the choice - logprobs: - $ref: '#/components/schemas/OpenAIChoiceLogprobs' - description: >- - (Optional) The log probabilities for the tokens in the message - additionalProperties: false - required: - - delta - - finish_reason - - index - title: OpenAIChunkChoice - description: >- - A chunk choice from an OpenAI-compatible chat completion streaming response. - OpenaiCompletionRequest: - type: object - properties: - model: - type: string - description: >- - The identifier of the model to use. The model must be registered with - Llama Stack and available via the /models endpoint. - prompt: - oneOf: - - type: string - - type: array - items: - type: string - - type: array - items: - type: integer - - type: array - items: - type: array - items: - type: integer - description: The prompt to generate a completion for. - best_of: - type: integer - description: >- - (Optional) The number of completions to generate. - echo: - type: boolean - description: (Optional) Whether to echo the prompt. - frequency_penalty: - type: number - description: >- - (Optional) The penalty for repeated tokens. - logit_bias: - type: object - additionalProperties: - type: number - description: (Optional) The logit bias to use. - logprobs: - type: boolean - description: (Optional) The log probabilities to use. - max_tokens: - type: integer - description: >- - (Optional) The maximum number of tokens to generate. - n: - type: integer - description: >- - (Optional) The number of completions to generate. - presence_penalty: - type: number - description: >- - (Optional) The penalty for repeated tokens. - seed: - type: integer - description: (Optional) The seed to use. - stop: - oneOf: - - type: string - - type: array - items: - type: string - description: (Optional) The stop tokens to use. - stream: - type: boolean - description: >- - (Optional) Whether to stream the response. - stream_options: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: (Optional) The stream options to use. - temperature: - type: number - description: (Optional) The temperature to use. - top_p: - type: number - description: (Optional) The top p to use. - user: - type: string - description: (Optional) The user to use. - guided_choice: - type: array - items: - type: string - prompt_logprobs: - type: integer - suffix: - type: string - description: >- - (Optional) The suffix that should be appended to the completion. - additionalProperties: false - required: - - model - - prompt - title: OpenaiCompletionRequest - OpenAICompletion: - type: object - properties: - id: - type: string - choices: - type: array - items: - $ref: '#/components/schemas/OpenAICompletionChoice' - created: - type: integer - model: - type: string - object: - type: string - const: text_completion - default: text_completion - additionalProperties: false - required: - - id - - choices - - created - - model - - object - title: OpenAICompletion - description: >- - Response from an OpenAI-compatible completion request. - OpenAICompletionChoice: - type: object - properties: - finish_reason: - type: string - text: - type: string - index: - type: integer - logprobs: - $ref: '#/components/schemas/OpenAIChoiceLogprobs' - additionalProperties: false - required: - - finish_reason - - text - - index - title: OpenAICompletionChoice - description: >- - A choice from an OpenAI-compatible completion response. - OpenaiCreateVectorStoreRequest: - type: object - properties: - name: - type: string - description: A name for the vector store. - file_ids: - type: array - items: - type: string - description: >- - A list of File IDs that the vector store should use. Useful for tools - like `file_search` that can access files. - expires_after: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The expiration policy for a vector store. - chunking_strategy: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The chunking strategy used to chunk the file(s). If not set, will use - the `auto` strategy. - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Set of 16 key-value pairs that can be attached to an object. - embedding_model: - type: string - description: >- - The embedding model to use for this vector store. - embedding_dimension: - type: integer - description: >- - The dimension of the embedding vectors (default: 384). - provider_id: - type: string - description: >- - The ID of the provider to use for this vector store. - additionalProperties: false - title: OpenaiCreateVectorStoreRequest - VectorStoreFileCounts: - type: object - properties: - completed: - type: integer - description: >- - Number of files that have been successfully processed - cancelled: - type: integer - description: >- - Number of files that had their processing cancelled - failed: - type: integer - description: Number of files that failed to process - in_progress: - type: integer - description: >- - Number of files currently being processed - total: - type: integer - description: >- - Total number of files in the vector store - additionalProperties: false - required: - - completed - - cancelled - - failed - - in_progress - - total - title: VectorStoreFileCounts - description: >- - File processing status counts for a vector store. - VectorStoreObject: - type: object - properties: - id: - type: string - description: Unique identifier for the vector store - object: - type: string - default: vector_store - description: >- - Object type identifier, always "vector_store" - created_at: - type: integer - description: >- - Timestamp when the vector store was created - name: - type: string - description: (Optional) Name of the vector store - usage_bytes: - type: integer - default: 0 - description: >- - Storage space used by the vector store in bytes - file_counts: - $ref: '#/components/schemas/VectorStoreFileCounts' - description: >- - File processing status counts for the vector store - status: - type: string - default: completed - description: Current status of the vector store - expires_after: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Expiration policy for the vector store - expires_at: - type: integer - description: >- - (Optional) Timestamp when the vector store will expire - last_active_at: - type: integer - description: >- - (Optional) Timestamp of last activity on the vector store - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Set of key-value pairs that can be attached to the vector store - additionalProperties: false - required: - - id - - object - - created_at - - usage_bytes - - file_counts - - status - - metadata - title: VectorStoreObject - description: OpenAI Vector Store object. - OpenAIFileDeleteResponse: - type: object - properties: - id: - type: string - description: The file identifier that was deleted - object: - type: string - const: file - default: file - description: The object type, which is always "file" - deleted: - type: boolean - description: >- - Whether the file was successfully deleted - additionalProperties: false - required: - - id - - object - - deleted - title: OpenAIFileDeleteResponse - description: >- - Response for deleting a file in OpenAI Files API. - VectorStoreDeleteResponse: - type: object - properties: - id: - type: string - description: >- - Unique identifier of the deleted vector store - object: - type: string - default: vector_store.deleted - description: >- - Object type identifier for the deletion response - deleted: - type: boolean - default: true - description: >- - Whether the deletion operation was successful - additionalProperties: false - required: - - id - - object - - deleted - title: VectorStoreDeleteResponse - description: Response from deleting a vector store. - VectorStoreFileDeleteResponse: - type: object - properties: - id: - type: string - description: Unique identifier of the deleted file - object: - type: string - default: vector_store.file.deleted - description: >- - Object type identifier for the deletion response - deleted: - type: boolean - default: true - description: >- - Whether the deletion operation was successful - additionalProperties: false - required: - - id - - object - - deleted - title: VectorStoreFileDeleteResponse - description: >- - Response from deleting a vector store file. - OpenaiEmbeddingsRequest: - type: object - properties: - model: - type: string - description: >- - The identifier of the model to use. The model must be an embedding model - registered with Llama Stack and available via the /models endpoint. - input: - oneOf: - - type: string - - type: array - items: - type: string - description: >- - Input text to embed, encoded as a string or array of strings. To embed - multiple inputs in a single request, pass an array of strings. - encoding_format: - type: string - description: >- - (Optional) The format to return the embeddings in. Can be either "float" - or "base64". Defaults to "float". - dimensions: - type: integer - description: >- - (Optional) The number of dimensions the resulting output embeddings should - have. Only supported in text-embedding-3 and later models. - user: - type: string - description: >- - (Optional) A unique identifier representing your end-user, which can help - OpenAI to monitor and detect abuse. - additionalProperties: false - required: - - model - - input - title: OpenaiEmbeddingsRequest - OpenAIEmbeddingData: - type: object - properties: - object: - type: string - const: embedding - default: embedding - description: >- - The object type, which will be "embedding" - embedding: - oneOf: - - type: array - items: - type: number - - type: string - description: >- - The embedding vector as a list of floats (when encoding_format="float") - or as a base64-encoded string (when encoding_format="base64") - index: - type: integer - description: >- - The index of the embedding in the input list - additionalProperties: false - required: - - object - - embedding - - index - title: OpenAIEmbeddingData - description: >- - A single embedding data object from an OpenAI-compatible embeddings response. - OpenAIEmbeddingUsage: - type: object - properties: - prompt_tokens: - type: integer - description: The number of tokens in the input - total_tokens: - type: integer - description: The total number of tokens used - additionalProperties: false - required: - - prompt_tokens - - total_tokens - title: OpenAIEmbeddingUsage - description: >- - Usage information for an OpenAI-compatible embeddings response. - OpenAIEmbeddingsResponse: - type: object - properties: - object: - type: string - const: list - default: list - description: The object type, which will be "list" - data: - type: array - items: - $ref: '#/components/schemas/OpenAIEmbeddingData' - description: List of embedding data objects - model: - type: string - description: >- - The model that was used to generate the embeddings - usage: - $ref: '#/components/schemas/OpenAIEmbeddingUsage' - description: Usage information - additionalProperties: false - required: - - object - - data - - model - - usage - title: OpenAIEmbeddingsResponse - description: >- - Response from an OpenAI-compatible embeddings request. - OpenAIFilePurpose: - type: string - enum: - - assistants - - batch - title: OpenAIFilePurpose - description: >- - Valid purpose values for OpenAI Files API. - ListOpenAIFileResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/OpenAIFileObject' - description: List of file objects - has_more: - type: boolean - description: >- - Whether there are more files available beyond this page - first_id: - type: string - description: >- - ID of the first file in the list for pagination - last_id: - type: string - description: >- - ID of the last file in the list for pagination - object: - type: string - const: list - default: list - description: The object type, which is always "list" - additionalProperties: false - required: - - data - - has_more - - first_id - - last_id - - object - title: ListOpenAIFileResponse - description: >- - Response for listing files in OpenAI Files API. - OpenAIFileObject: - type: object - properties: - object: - type: string - const: file - default: file - description: The object type, which is always "file" - id: - type: string - description: >- - The file identifier, which can be referenced in the API endpoints - bytes: - type: integer - description: The size of the file, in bytes - created_at: - type: integer - description: >- - The Unix timestamp (in seconds) for when the file was created - expires_at: - type: integer - description: >- - The Unix timestamp (in seconds) for when the file expires - filename: - type: string - description: The name of the file - purpose: - type: string - enum: - - assistants - - batch - description: The intended purpose of the file - additionalProperties: false - required: - - object - - id - - bytes - - created_at - - expires_at - - filename - - purpose - title: OpenAIFileObject - description: >- - OpenAI File object as defined in the OpenAI Files API. - VectorStoreListFilesResponse: - type: object - properties: - object: - type: string - default: list - description: Object type identifier, always "list" - data: - type: array - items: - $ref: '#/components/schemas/VectorStoreFileObject' - description: List of vector store file objects - first_id: - type: string - description: >- - (Optional) ID of the first file in the list for pagination - last_id: - type: string - description: >- - (Optional) ID of the last file in the list for pagination - has_more: - type: boolean - default: false - description: >- - Whether there are more files available beyond this page - additionalProperties: false - required: - - object - - data - - has_more - title: VectorStoreListFilesResponse - description: >- - Response from listing files in a vector store. - OpenAIModel: - type: object - properties: - id: - type: string - object: - type: string - const: model - default: model - created: - type: integer - owned_by: - type: string - additionalProperties: false - required: - - id - - object - - created - - owned_by - title: OpenAIModel - description: A model from OpenAI. - OpenAIListModelsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/OpenAIModel' - additionalProperties: false - required: - - data - title: OpenAIListModelsResponse - VectorStoreListResponse: - type: object - properties: - object: - type: string - default: list - description: Object type identifier, always "list" - data: - type: array - items: - $ref: '#/components/schemas/VectorStoreObject' - description: List of vector store objects - first_id: - type: string - description: >- - (Optional) ID of the first vector store in the list for pagination - last_id: - type: string - description: >- - (Optional) ID of the last vector store in the list for pagination - has_more: - type: boolean - default: false - description: >- - Whether there are more vector stores available beyond this page - additionalProperties: false - required: - - object - - data - - has_more - title: VectorStoreListResponse - description: Response from listing vector stores. - Response: - type: object - title: Response - VectorStoreContent: - type: object - properties: - type: - type: string - const: text - description: >- - Content type, currently only "text" is supported - text: - type: string - description: The actual text content - additionalProperties: false - required: - - type - - text - title: VectorStoreContent - description: >- - Content item from a vector store file or search result. - VectorStoreFileContentsResponse: - type: object - properties: - file_id: - type: string - description: Unique identifier for the file - filename: - type: string - description: Name of the file - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Key-value attributes associated with the file - content: - type: array - items: - $ref: '#/components/schemas/VectorStoreContent' - description: List of content items from the file - additionalProperties: false - required: - - file_id - - filename - - attributes - - content - title: VectorStoreFileContentsResponse - description: >- - Response from retrieving the contents of a vector store file. - OpenaiSearchVectorStoreRequest: - type: object - properties: - query: - oneOf: - - type: string - - type: array - items: - type: string - description: >- - The query string or array for performing the search. - filters: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Filters based on file attributes to narrow the search results. - max_num_results: - type: integer - description: >- - Maximum number of results to return (1 to 50 inclusive, default 10). - ranking_options: - type: object - properties: - ranker: - type: string - description: >- - (Optional) Name of the ranking algorithm to use - score_threshold: - type: number - default: 0.0 - description: >- - (Optional) Minimum relevance score threshold for results - additionalProperties: false - description: >- - Ranking options for fine-tuning the search results. - rewrite_query: - type: boolean - description: >- - Whether to rewrite the natural language query for vector search (default - false) - search_mode: - type: string - description: >- - The search mode to use - "keyword", "vector", or "hybrid" (default "vector") - additionalProperties: false - required: - - query - title: OpenaiSearchVectorStoreRequest - VectorStoreSearchResponse: - type: object - properties: - file_id: - type: string - description: >- - Unique identifier of the file containing the result - filename: - type: string - description: Name of the file containing the result - score: - type: number - description: Relevance score for this search result - attributes: - type: object - additionalProperties: - oneOf: - - type: string - - type: number - - type: boolean - description: >- - (Optional) Key-value attributes associated with the file - content: - type: array - items: - $ref: '#/components/schemas/VectorStoreContent' - description: >- - List of content items matching the search query - additionalProperties: false - required: - - file_id - - filename - - score - - content - title: VectorStoreSearchResponse - description: Response from searching a vector store. - VectorStoreSearchResponsePage: - type: object - properties: - object: - type: string - default: vector_store.search_results.page - description: >- - Object type identifier for the search results page - search_query: - type: string - description: >- - The original search query that was executed - data: - type: array - items: - $ref: '#/components/schemas/VectorStoreSearchResponse' - description: List of search result objects - has_more: - type: boolean - default: false - description: >- - Whether there are more results available beyond this page - next_page: - type: string - description: >- - (Optional) Token for retrieving the next page of results - additionalProperties: false - required: - - object - - search_query - - data - - has_more - title: VectorStoreSearchResponsePage - description: >- - Paginated response from searching a vector store. - OpenaiUpdateVectorStoreRequest: - type: object - properties: - name: - type: string - description: The name of the vector store. - expires_after: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The expiration policy for a vector store. - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Set of 16 key-value pairs that can be attached to an object. - additionalProperties: false - title: OpenaiUpdateVectorStoreRequest - OpenaiUpdateVectorStoreFileRequest: - type: object - properties: - attributes: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The updated key-value attributes to store with the file. - additionalProperties: false - required: - - attributes - title: OpenaiUpdateVectorStoreFileRequest - DPOAlignmentConfig: - type: object - properties: - beta: - type: number - description: Temperature parameter for the DPO loss - loss_type: - $ref: '#/components/schemas/DPOLossType' - default: sigmoid - description: The type of loss function to use for DPO - additionalProperties: false - required: - - beta - - loss_type - title: DPOAlignmentConfig - description: >- - Configuration for Direct Preference Optimization (DPO) alignment. - DPOLossType: - type: string - enum: - - sigmoid - - hinge - - ipo - - kto_pair - title: DPOLossType - DataConfig: - type: object - properties: - dataset_id: - type: string - description: >- - Unique identifier for the training dataset - batch_size: - type: integer - description: Number of samples per training batch - shuffle: - type: boolean - description: >- - Whether to shuffle the dataset during training - data_format: - $ref: '#/components/schemas/DatasetFormat' - description: >- - Format of the dataset (instruct or dialog) - validation_dataset_id: - type: string - description: >- - (Optional) Unique identifier for the validation dataset - packed: - type: boolean - default: false - description: >- - (Optional) Whether to pack multiple samples into a single sequence for - efficiency - train_on_input: - type: boolean - default: false - description: >- - (Optional) Whether to compute loss on input tokens as well as output tokens - additionalProperties: false - required: - - dataset_id - - batch_size - - shuffle - - data_format - title: DataConfig - description: >- - Configuration for training data and data loading. - DatasetFormat: - type: string - enum: - - instruct - - dialog - title: DatasetFormat - description: Format of the training dataset. - EfficiencyConfig: - type: object - properties: - enable_activation_checkpointing: - type: boolean - default: false - description: >- - (Optional) Whether to use activation checkpointing to reduce memory usage - enable_activation_offloading: - type: boolean - default: false - description: >- - (Optional) Whether to offload activations to CPU to save GPU memory - memory_efficient_fsdp_wrap: - type: boolean - default: false - description: >- - (Optional) Whether to use memory-efficient FSDP wrapping - fsdp_cpu_offload: - type: boolean - default: false - description: >- - (Optional) Whether to offload FSDP parameters to CPU - additionalProperties: false - title: EfficiencyConfig - description: >- - Configuration for memory and compute efficiency optimizations. - OptimizerConfig: - type: object - properties: - optimizer_type: - $ref: '#/components/schemas/OptimizerType' - description: >- - Type of optimizer to use (adam, adamw, or sgd) - lr: - type: number - description: Learning rate for the optimizer - weight_decay: - type: number - description: >- - Weight decay coefficient for regularization - num_warmup_steps: - type: integer - description: Number of steps for learning rate warmup - additionalProperties: false - required: - - optimizer_type - - lr - - weight_decay - - num_warmup_steps - title: OptimizerConfig - description: >- - Configuration parameters for the optimization algorithm. - OptimizerType: - type: string - enum: - - adam - - adamw - - sgd - title: OptimizerType - description: >- - Available optimizer algorithms for training. - TrainingConfig: - type: object - properties: - n_epochs: - type: integer - description: Number of training epochs to run - max_steps_per_epoch: - type: integer - default: 1 - description: Maximum number of steps to run per epoch - gradient_accumulation_steps: - type: integer - default: 1 - description: >- - Number of steps to accumulate gradients before updating - max_validation_steps: - type: integer - default: 1 - description: >- - (Optional) Maximum number of validation steps per epoch - data_config: - $ref: '#/components/schemas/DataConfig' - description: >- - (Optional) Configuration for data loading and formatting - optimizer_config: - $ref: '#/components/schemas/OptimizerConfig' - description: >- - (Optional) Configuration for the optimization algorithm - efficiency_config: - $ref: '#/components/schemas/EfficiencyConfig' - description: >- - (Optional) Configuration for memory and compute optimizations - dtype: - type: string - default: bf16 - description: >- - (Optional) Data type for model parameters (bf16, fp16, fp32) - additionalProperties: false - required: - - n_epochs - - max_steps_per_epoch - - gradient_accumulation_steps - title: TrainingConfig - description: >- - Comprehensive configuration for the training process. - PreferenceOptimizeRequest: - type: object - properties: - job_uuid: - type: string - description: The UUID of the job to create. - finetuned_model: - type: string - description: The model to fine-tune. - algorithm_config: - $ref: '#/components/schemas/DPOAlignmentConfig' - description: The algorithm configuration. - training_config: - $ref: '#/components/schemas/TrainingConfig' - description: The training configuration. - hyperparam_search_config: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The hyperparam search configuration. - logger_config: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The logger configuration. - additionalProperties: false - required: - - job_uuid - - finetuned_model - - algorithm_config - - training_config - - hyperparam_search_config - - logger_config - title: PreferenceOptimizeRequest - PostTrainingJob: - type: object - properties: - job_uuid: - type: string - additionalProperties: false - required: - - job_uuid - title: PostTrainingJob - DefaultRAGQueryGeneratorConfig: - type: object - properties: - type: - type: string - const: default - default: default - description: >- - Type of query generator, always 'default' - separator: - type: string - default: ' ' - description: >- - String separator used to join query terms - additionalProperties: false - required: - - type - - separator - title: DefaultRAGQueryGeneratorConfig - description: >- - Configuration for the default RAG query generator. - LLMRAGQueryGeneratorConfig: - type: object - properties: - type: - type: string - const: llm - default: llm - description: Type of query generator, always 'llm' - model: - type: string - description: >- - Name of the language model to use for query generation - template: - type: string - description: >- - Template string for formatting the query generation prompt - additionalProperties: false - required: - - type - - model - - template - title: LLMRAGQueryGeneratorConfig - description: >- - Configuration for the LLM-based RAG query generator. - RAGQueryConfig: - type: object - properties: - query_generator_config: - $ref: '#/components/schemas/RAGQueryGeneratorConfig' - description: Configuration for the query generator. - max_tokens_in_context: - type: integer - default: 4096 - description: Maximum number of tokens in the context. - max_chunks: - type: integer - default: 5 - description: Maximum number of chunks to retrieve. - chunk_template: - type: string - default: > - Result {index} - - Content: {chunk.content} - - Metadata: {metadata} - description: >- - Template for formatting each retrieved chunk in the context. Available - placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk - content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent: - {chunk.content}\nMetadata: {metadata}\n" - mode: - $ref: '#/components/schemas/RAGSearchMode' - default: vector - description: >- - Search mode for retrieval—either "vector", "keyword", or "hybrid". Default - "vector". - ranker: - $ref: '#/components/schemas/Ranker' - description: >- - Configuration for the ranker to use in hybrid search. Defaults to RRF - ranker. - additionalProperties: false - required: - - query_generator_config - - max_tokens_in_context - - max_chunks - - chunk_template - title: RAGQueryConfig - description: >- - Configuration for the RAG query generation. - RAGQueryGeneratorConfig: - oneOf: - - $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig' - - $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig' - discriminator: - propertyName: type - mapping: - default: '#/components/schemas/DefaultRAGQueryGeneratorConfig' - llm: '#/components/schemas/LLMRAGQueryGeneratorConfig' - RAGSearchMode: - type: string - enum: - - vector - - keyword - - hybrid - title: RAGSearchMode - description: >- - Search modes for RAG query retrieval: - VECTOR: Uses vector similarity search - for semantic matching - KEYWORD: Uses keyword-based search for exact matching - - HYBRID: Combines both vector and keyword search for better results - RRFRanker: - type: object - properties: - type: - type: string - const: rrf - default: rrf - description: The type of ranker, always "rrf" - impact_factor: - type: number - default: 60.0 - description: >- - The impact factor for RRF scoring. Higher values give more weight to higher-ranked - results. Must be greater than 0 - additionalProperties: false - required: - - type - - impact_factor - title: RRFRanker - description: >- - Reciprocal Rank Fusion (RRF) ranker configuration. - Ranker: - oneOf: - - $ref: '#/components/schemas/RRFRanker' - - $ref: '#/components/schemas/WeightedRanker' - discriminator: - propertyName: type - mapping: - rrf: '#/components/schemas/RRFRanker' - weighted: '#/components/schemas/WeightedRanker' - WeightedRanker: - type: object - properties: - type: - type: string - const: weighted - default: weighted - description: The type of ranker, always "weighted" - alpha: - type: number - default: 0.5 - description: >- - Weight factor between 0 and 1. 0 means only use keyword scores, 1 means - only use vector scores, values in between blend both scores. - additionalProperties: false - required: - - type - - alpha - title: WeightedRanker - description: >- - Weighted ranker configuration that combines vector and keyword scores. - QueryRequest: - type: object - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - The query content to search for in the indexed documents - vector_db_ids: - type: array - items: - type: string - description: >- - List of vector database IDs to search within - query_config: - $ref: '#/components/schemas/RAGQueryConfig' - description: >- - (Optional) Configuration parameters for the query operation - additionalProperties: false - required: - - content - - vector_db_ids - title: QueryRequest - RAGQueryResult: - type: object - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - description: >- - (Optional) The retrieved content from the query - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - Additional metadata about the query result - additionalProperties: false - required: - - metadata - title: RAGQueryResult - description: >- - Result of a RAG query containing retrieved content and metadata. - QueryChunksRequest: - type: object - properties: - vector_db_id: - type: string - description: >- - The identifier of the vector database to query. - query: - $ref: '#/components/schemas/InterleavedContent' - description: The query to search for. - params: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The parameters of the query. - additionalProperties: false - required: - - vector_db_id - - query - title: QueryChunksRequest - QueryChunksResponse: - type: object - properties: - chunks: - type: array - items: - $ref: '#/components/schemas/Chunk' - description: >- - List of content chunks returned from the query - scores: - type: array - items: - type: number - description: >- - Relevance scores corresponding to each returned chunk - additionalProperties: false - required: - - chunks - - scores - title: QueryChunksResponse - description: >- - Response from querying chunks in a vector database. - QueryMetricsRequest: - type: object - properties: - start_time: - type: integer - description: The start time of the metric to query. - end_time: - type: integer - description: The end time of the metric to query. - granularity: - type: string - description: The granularity of the metric to query. - query_type: - type: string - enum: - - range - - instant - description: The type of query to perform. - label_matchers: - type: array - items: - type: object - properties: - name: - type: string - description: The name of the label to match - value: - type: string - description: The value to match against - operator: - type: string - enum: - - '=' - - '!=' - - =~ - - '!~' - description: >- - The comparison operator to use for matching - default: '=' - additionalProperties: false - required: - - name - - value - - operator - title: MetricLabelMatcher - description: >- - A matcher for filtering metrics by label values. - description: >- - The label matchers to apply to the metric. - additionalProperties: false - required: - - start_time - - query_type - title: QueryMetricsRequest - MetricDataPoint: - type: object - properties: - timestamp: - type: integer - description: >- - Unix timestamp when the metric value was recorded - value: - type: number - description: >- - The numeric value of the metric at this timestamp - unit: - type: string - additionalProperties: false - required: - - timestamp - - value - - unit - title: MetricDataPoint - description: >- - A single data point in a metric time series. - MetricLabel: - type: object - properties: - name: - type: string - description: The name of the label - value: - type: string - description: The value of the label - additionalProperties: false - required: - - name - - value - title: MetricLabel - description: A label associated with a metric. - MetricSeries: - type: object - properties: - metric: - type: string - description: The name of the metric - labels: - type: array - items: - $ref: '#/components/schemas/MetricLabel' - description: >- - List of labels associated with this metric series - values: - type: array - items: - $ref: '#/components/schemas/MetricDataPoint' - description: >- - List of data points in chronological order - additionalProperties: false - required: - - metric - - labels - - values - title: MetricSeries - description: A time series of metric data points. - QueryMetricsResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/MetricSeries' - description: >- - List of metric series matching the query criteria - additionalProperties: false - required: - - data - title: QueryMetricsResponse - description: >- - Response containing metric time series data. - QueryCondition: - type: object - properties: - key: - type: string - description: The attribute key to filter on - op: - $ref: '#/components/schemas/QueryConditionOp' - description: The comparison operator to apply - value: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The value to compare against - additionalProperties: false - required: - - key - - op - - value - title: QueryCondition - description: A condition for filtering query results. - QueryConditionOp: - type: string - enum: - - eq - - ne - - gt - - lt - title: QueryConditionOp - description: >- - Comparison operators for query conditions. - QuerySpansRequest: - type: object - properties: - attribute_filters: - type: array - items: - $ref: '#/components/schemas/QueryCondition' - description: >- - The attribute filters to apply to the spans. - attributes_to_return: - type: array - items: - type: string - description: The attributes to return in the spans. - max_depth: - type: integer - description: The maximum depth of the tree. - additionalProperties: false - required: - - attribute_filters - - attributes_to_return - title: QuerySpansRequest - QuerySpansResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Span' - description: >- - List of spans matching the query criteria - additionalProperties: false - required: - - data - title: QuerySpansResponse - description: Response containing a list of spans. - QueryTracesRequest: - type: object - properties: - attribute_filters: - type: array - items: - $ref: '#/components/schemas/QueryCondition' - description: >- - The attribute filters to apply to the traces. - limit: - type: integer - description: The limit of traces to return. - offset: - type: integer - description: The offset of the traces to return. - order_by: - type: array - items: - type: string - description: The order by of the traces to return. - additionalProperties: false - title: QueryTracesRequest - QueryTracesResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/Trace' - description: >- - List of traces matching the query criteria - additionalProperties: false - required: - - data - title: QueryTracesResponse - description: Response containing a list of traces. - RegisterBenchmarkRequest: - type: object - properties: - benchmark_id: - type: string - description: The ID of the benchmark to register. - dataset_id: - type: string - description: >- - The ID of the dataset to use for the benchmark. - scoring_functions: - type: array - items: - type: string - description: >- - The scoring functions to use for the benchmark. - provider_benchmark_id: - type: string - description: >- - The ID of the provider benchmark to use for the benchmark. - provider_id: - type: string - description: >- - The ID of the provider to use for the benchmark. - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The metadata to use for the benchmark. - additionalProperties: false - required: - - benchmark_id - - dataset_id - - scoring_functions - title: RegisterBenchmarkRequest - RegisterDatasetRequest: - type: object - properties: - purpose: - type: string - enum: - - post-training/messages - - eval/question-answer - - eval/messages-answer - description: >- - The purpose of the dataset. One of: - "post-training/messages": The dataset - contains a messages column with list of messages for post-training. { - "messages": [ {"role": "user", "content": "Hello, world!"}, {"role": "assistant", - "content": "Hello, world!"}, ] } - "eval/question-answer": The dataset - contains a question column and an answer column for evaluation. { "question": - "What is the capital of France?", "answer": "Paris" } - "eval/messages-answer": - The dataset contains a messages column with list of messages and an answer - column for evaluation. { "messages": [ {"role": "user", "content": "Hello, - my name is John Doe."}, {"role": "assistant", "content": "Hello, John - Doe. How can I help you today?"}, {"role": "user", "content": "What's - my name?"}, ], "answer": "John Doe" } - source: - $ref: '#/components/schemas/DataSource' - description: >- - The data source of the dataset. Ensure that the data source schema is - compatible with the purpose of the dataset. Examples: - { "type": "uri", - "uri": "https://mywebsite.com/mydata.jsonl" } - { "type": "uri", "uri": - "lsfs://mydata.jsonl" } - { "type": "uri", "uri": "data:csv;base64,{base64_content}" - } - { "type": "uri", "uri": "huggingface://llamastack/simpleqa?split=train" - } - { "type": "rows", "rows": [ { "messages": [ {"role": "user", "content": - "Hello, world!"}, {"role": "assistant", "content": "Hello, world!"}, ] - } ] } - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - The metadata for the dataset. - E.g. {"description": "My dataset"}. - dataset_id: - type: string - description: >- - The ID of the dataset. If not provided, an ID will be generated. - additionalProperties: false - required: - - purpose - - source - title: RegisterDatasetRequest - RegisterModelRequest: - type: object - properties: - model_id: - type: string - description: The identifier of the model to register. - provider_model_id: - type: string - description: >- - The identifier of the model in the provider. - provider_id: - type: string - description: The identifier of the provider. - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: Any additional metadata for this model. - model_type: - $ref: '#/components/schemas/ModelType' - description: The type of model to register. - additionalProperties: false - required: - - model_id - title: RegisterModelRequest - RegisterScoringFunctionRequest: - type: object - properties: - scoring_fn_id: - type: string - description: >- - The ID of the scoring function to register. - description: - type: string - description: The description of the scoring function. - return_type: - $ref: '#/components/schemas/ParamType' - description: The return type of the scoring function. - provider_scoring_fn_id: - type: string - description: >- - The ID of the provider scoring function to use for the scoring function. - provider_id: - type: string - description: >- - The ID of the provider to use for the scoring function. - params: - $ref: '#/components/schemas/ScoringFnParams' - description: >- - The parameters for the scoring function for benchmark eval, these can - be overridden for app eval. - additionalProperties: false - required: - - scoring_fn_id - - description - - return_type - title: RegisterScoringFunctionRequest - RegisterShieldRequest: - type: object - properties: - shield_id: - type: string - description: >- - The identifier of the shield to register. - provider_shield_id: - type: string - description: >- - The identifier of the shield in the provider. - provider_id: - type: string - description: The identifier of the provider. - params: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The parameters of the shield. - additionalProperties: false - required: - - shield_id - title: RegisterShieldRequest - RegisterToolGroupRequest: - type: object - properties: - toolgroup_id: - type: string - description: The ID of the tool group to register. - provider_id: - type: string - description: >- - The ID of the provider to use for the tool group. - mcp_endpoint: - $ref: '#/components/schemas/URL' - description: >- - The MCP endpoint to use for the tool group. - args: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - A dictionary of arguments to pass to the tool group. - additionalProperties: false - required: - - toolgroup_id - - provider_id - title: RegisterToolGroupRequest - RegisterVectorDbRequest: - type: object - properties: - vector_db_id: - type: string - description: >- - The identifier of the vector database to register. - embedding_model: - type: string - description: The embedding model to use. - embedding_dimension: - type: integer - description: The dimension of the embedding model. - provider_id: - type: string - description: The identifier of the provider. - vector_db_name: - type: string - description: The name of the vector database. - provider_vector_db_id: - type: string - description: >- - The identifier of the vector database in the provider. - additionalProperties: false - required: - - vector_db_id - - embedding_model - title: RegisterVectorDbRequest - RerankRequest: - type: object - properties: - model: - type: string - description: >- - The identifier of the reranking model to use. - query: - oneOf: - - type: string - - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' - description: >- - The search query to rank items against. Can be a string, text content - part, or image content part. The input must not exceed the model's max - input token length. - items: - type: array - items: - oneOf: - - type: string - - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam' - - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam' - description: >- - List of items to rerank. Each item can be a string, text content part, - or image content part. Each input must not exceed the model's max input - token length. - max_num_results: - type: integer - description: >- - (Optional) Maximum number of results to return. Default: returns all. - additionalProperties: false - required: - - model - - query - - items - title: RerankRequest - RerankData: - type: object - properties: - index: - type: integer - description: >- - The original index of the document in the input list - relevance_score: - type: number - description: >- - The relevance score from the model output. Values are inverted when applicable - so that higher scores indicate greater relevance. - additionalProperties: false - required: - - index - - relevance_score - title: RerankData - description: >- - A single rerank result from a reranking response. - RerankResponse: - type: object - properties: - data: - type: array - items: - $ref: '#/components/schemas/RerankData' - description: >- - List of rerank result objects, sorted by relevance score (descending) - additionalProperties: false - required: - - data - title: RerankResponse - description: Response from a reranking request. - ResumeAgentTurnRequest: - type: object - properties: - tool_responses: - type: array - items: - $ref: '#/components/schemas/ToolResponse' - description: >- - The tool call responses to resume the turn with. - stream: - type: boolean - description: Whether to stream the response. - additionalProperties: false - required: - - tool_responses - title: ResumeAgentTurnRequest - RunEvalRequest: - type: object - properties: - benchmark_config: - $ref: '#/components/schemas/BenchmarkConfig' - description: The configuration for the benchmark. - additionalProperties: false - required: - - benchmark_config - title: RunEvalRequest - RunModerationRequest: - type: object - properties: - input: - oneOf: - - type: string - - type: array - items: - type: string - description: >- - Input (or inputs) to classify. Can be a single string, an array of strings, - or an array of multi-modal input objects similar to other models. - model: - type: string - description: >- - The content moderation model you would like to use. - additionalProperties: false - required: - - input - - model - title: RunModerationRequest - ModerationObject: - type: object - properties: - id: - type: string - description: >- - The unique identifier for the moderation request. - model: - type: string - description: >- - The model used to generate the moderation results. - results: - type: array - items: - $ref: '#/components/schemas/ModerationObjectResults' - description: A list of moderation objects - additionalProperties: false - required: - - id - - model - - results - title: ModerationObject - description: A moderation object. - ModerationObjectResults: - type: object - properties: - flagged: - type: boolean - description: >- - Whether any of the below categories are flagged. - categories: - type: object - additionalProperties: - type: boolean - description: >- - A list of the categories, and whether they are flagged or not. - category_applied_input_types: - type: object - additionalProperties: - type: array - items: - type: string - description: >- - A list of the categories along with the input type(s) that the score applies - to. - category_scores: - type: object - additionalProperties: - type: number - description: >- - A list of the categories along with their scores as predicted by model. - user_message: - type: string - metadata: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - additionalProperties: false - required: - - flagged - - metadata - title: ModerationObjectResults - description: A moderation object. - RunShieldRequest: - type: object - properties: - shield_id: - type: string - description: The identifier of the shield to run. - messages: - type: array - items: - $ref: '#/components/schemas/Message' - description: The messages to run the shield on. - params: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The parameters of the shield. - additionalProperties: false - required: - - shield_id - - messages - - params - title: RunShieldRequest - RunShieldResponse: - type: object - properties: - violation: - $ref: '#/components/schemas/SafetyViolation' - description: >- - (Optional) Safety violation detected by the shield, if any - additionalProperties: false - title: RunShieldResponse - description: Response from running a safety shield. - SaveSpansToDatasetRequest: - type: object - properties: - attribute_filters: - type: array - items: - $ref: '#/components/schemas/QueryCondition' - description: >- - The attribute filters to apply to the spans. - attributes_to_save: - type: array - items: - type: string - description: The attributes to save to the dataset. - dataset_id: - type: string - description: >- - The ID of the dataset to save the spans to. - max_depth: - type: integer - description: The maximum depth of the tree. - additionalProperties: false - required: - - attribute_filters - - attributes_to_save - - dataset_id - title: SaveSpansToDatasetRequest - ScoreRequest: - type: object - properties: - input_rows: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The rows to score. - scoring_functions: - type: object - additionalProperties: - oneOf: - - $ref: '#/components/schemas/ScoringFnParams' - - type: 'null' - description: >- - The scoring functions to use for the scoring. - additionalProperties: false - required: - - input_rows - - scoring_functions - title: ScoreRequest - ScoreResponse: - type: object - properties: - results: - type: object - additionalProperties: - $ref: '#/components/schemas/ScoringResult' - description: >- - A map of scoring function name to ScoringResult. - additionalProperties: false - required: - - results - title: ScoreResponse - description: The response from scoring. - ScoreBatchRequest: - type: object - properties: - dataset_id: - type: string - description: The ID of the dataset to score. - scoring_functions: - type: object - additionalProperties: - oneOf: - - $ref: '#/components/schemas/ScoringFnParams' - - type: 'null' - description: >- - The scoring functions to use for the scoring. - save_results_dataset: - type: boolean - description: >- - Whether to save the results to a dataset. - additionalProperties: false - required: - - dataset_id - - scoring_functions - - save_results_dataset - title: ScoreBatchRequest - ScoreBatchResponse: - type: object - properties: - dataset_id: - type: string - description: >- - (Optional) The identifier of the dataset that was scored - results: - type: object - additionalProperties: - $ref: '#/components/schemas/ScoringResult' - description: >- - A map of scoring function name to ScoringResult - additionalProperties: false - required: - - results - title: ScoreBatchResponse - description: >- - Response from batch scoring operations on datasets. - SetDefaultVersionRequest: - type: object - properties: - version: - type: integer - description: The version to set as default. - additionalProperties: false - required: - - version - title: SetDefaultVersionRequest - AlgorithmConfig: - oneOf: - - $ref: '#/components/schemas/LoraFinetuningConfig' - - $ref: '#/components/schemas/QATFinetuningConfig' - discriminator: - propertyName: type - mapping: - LoRA: '#/components/schemas/LoraFinetuningConfig' - QAT: '#/components/schemas/QATFinetuningConfig' - LoraFinetuningConfig: - type: object - properties: - type: - type: string - const: LoRA - default: LoRA - description: Algorithm type identifier, always "LoRA" - lora_attn_modules: - type: array - items: - type: string - description: >- - List of attention module names to apply LoRA to - apply_lora_to_mlp: - type: boolean - description: Whether to apply LoRA to MLP layers - apply_lora_to_output: - type: boolean - description: >- - Whether to apply LoRA to output projection layers - rank: - type: integer - description: >- - Rank of the LoRA adaptation (lower rank = fewer parameters) - alpha: - type: integer - description: >- - LoRA scaling parameter that controls adaptation strength - use_dora: - type: boolean - default: false - description: >- - (Optional) Whether to use DoRA (Weight-Decomposed Low-Rank Adaptation) - quantize_base: - type: boolean - default: false - description: >- - (Optional) Whether to quantize the base model weights - additionalProperties: false - required: - - type - - lora_attn_modules - - apply_lora_to_mlp - - apply_lora_to_output - - rank - - alpha - title: LoraFinetuningConfig - description: >- - Configuration for Low-Rank Adaptation (LoRA) fine-tuning. - QATFinetuningConfig: - type: object - properties: - type: - type: string - const: QAT - default: QAT - description: Algorithm type identifier, always "QAT" - quantizer_name: - type: string - description: >- - Name of the quantization algorithm to use - group_size: - type: integer - description: Size of groups for grouped quantization - additionalProperties: false - required: - - type - - quantizer_name - - group_size - title: QATFinetuningConfig - description: >- - Configuration for Quantization-Aware Training (QAT) fine-tuning. - SupervisedFineTuneRequest: - type: object - properties: - job_uuid: - type: string - description: The UUID of the job to create. - training_config: - $ref: '#/components/schemas/TrainingConfig' - description: The training configuration. - hyperparam_search_config: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The hyperparam search configuration. - logger_config: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: The logger configuration. - model: - type: string - description: The model to fine-tune. - checkpoint_dir: - type: string - description: The directory to save checkpoint(s) to. - algorithm_config: - $ref: '#/components/schemas/AlgorithmConfig' - description: The algorithm configuration. - additionalProperties: false - required: - - job_uuid - - training_config - - hyperparam_search_config - - logger_config - title: SupervisedFineTuneRequest - SyntheticDataGenerateRequest: - type: object - properties: - dialogs: - type: array - items: - $ref: '#/components/schemas/Message' - description: >- - List of conversation messages to use as input for synthetic data generation - filtering_function: - type: string - enum: - - none - - random - - top_k - - top_p - - top_k_top_p - - sigmoid - description: >- - Type of filtering to apply to generated synthetic data samples - model: - type: string - description: >- - (Optional) The identifier of the model to use. The model must be registered - with Llama Stack and available via the /models endpoint - additionalProperties: false - required: - - dialogs - - filtering_function - title: SyntheticDataGenerateRequest - SyntheticDataGenerationResponse: - type: object - properties: - synthetic_data: - type: array - items: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - List of generated synthetic data samples that passed the filtering criteria - statistics: - type: object - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: >- - (Optional) Statistical information about the generation process and filtering - results - additionalProperties: false - required: - - synthetic_data - title: SyntheticDataGenerationResponse - description: >- - Response from the synthetic data generation. Batch of (prompt, response, score) - tuples that pass the threshold. - UpdatePromptRequest: - type: object - properties: - prompt: - type: string - description: The updated prompt text content. - version: - type: integer - description: >- - The current version of the prompt being updated. - variables: - type: array - items: - type: string - description: >- - Updated list of variable names that can be used in the prompt template. - set_as_default: - type: boolean - description: >- - Set the new version as the default (default=True). - additionalProperties: false - required: - - prompt - - version - - set_as_default - title: UpdatePromptRequest - VersionInfo: - type: object - properties: - version: - type: string - description: Version number of the service - additionalProperties: false - required: - - version - title: VersionInfo - description: Version information for the service. - responses: - BadRequest400: - description: The request was invalid or malformed - content: - application/json: - schema: - $ref: '#/components/schemas/Error' - example: - status: 400 - title: Bad Request - detail: The request was invalid or malformed - TooManyRequests429: - description: >- - The client has sent too many requests in a given amount of time - content: - application/json: - schema: - $ref: '#/components/schemas/Error' - example: - status: 429 - title: Too Many Requests - detail: >- - You have exceeded the rate limit. Please try again later. - InternalServerError500: - description: >- - The server encountered an unexpected error - content: - application/json: - schema: - $ref: '#/components/schemas/Error' - example: - status: 500 - title: Internal Server Error - detail: >- - An unexpected error occurred. Our team has been notified. - DefaultError: - description: An unexpected error occurred - content: - application/json: - schema: - $ref: '#/components/schemas/Error' - example: - status: 0 - title: Error - detail: An unexpected error occurred -security: - - Default: [] -tags: - - name: Agents - description: >- - Main functionalities provided by this API: - - - Create agents with specific instructions and ability to use tools. - - - Interactions with agents are grouped into sessions ("threads"), and each interaction - is called a "turn". - - - Agents can be provided with various tools (see the ToolGroups and ToolRuntime - APIs for more details). - - - Agents can be provided with various shields (see the Safety API for more details). - - - Agents can also use Memory to retrieve information from knowledge bases. See - the RAG Tool and Vector IO APIs for more details. - x-displayName: >- - Agents API for creating and interacting with agentic systems. - - name: BatchInference (Coming Soon) - description: >- - This is an asynchronous API. If the request is successful, the response will - be a job which can be polled for completion. - - - NOTE: This API is not yet implemented and is subject to change in concert with - other asynchronous APIs - - including (post-training, evals, etc). - x-displayName: >- - Batch inference API for generating completions and chat completions. - - name: Benchmarks - - name: DatasetIO - - name: Datasets - - name: Eval - x-displayName: >- - Llama Stack Evaluation API for running evaluations on model and agent candidates. - - name: Files - - name: Inference - description: >- - This API provides the raw interface to the underlying models. Two kinds of models - are supported: - - - LLM models: these models generate "raw" and "chat" (conversational) completions. - - - Embedding models: these models generate embeddings to be used for semantic - search. - x-displayName: >- - Llama Stack Inference API for generating completions, chat completions, and - embeddings. - - name: Inspect - - name: Models - - name: PostTraining (Coming Soon) - - name: Prompts - x-displayName: >- - Protocol for prompt management operations. - - name: Providers - x-displayName: >- - Providers API for inspecting, listing, and modifying providers and their configurations. - - name: Safety - - name: Scoring - - name: ScoringFunctions - - name: Shields - - name: SyntheticDataGeneration (Coming Soon) - - name: Telemetry - - name: ToolGroups - - name: ToolRuntime - - name: VectorDBs - - name: VectorIO -x-tagGroups: - - name: Operations - tags: - - Agents - - BatchInference (Coming Soon) - - Benchmarks - - DatasetIO - - Datasets - - Eval - - Files - - Inference - - Inspect - - Models - - PostTraining (Coming Soon) - - Prompts - - Providers - - Safety - - Scoring - - ScoringFunctions - - Shields - - SyntheticDataGeneration (Coming Soon) - - Telemetry - - ToolGroups - - ToolRuntime - - VectorDBs - - VectorIO diff --git a/docs/_static/llama-stack.png b/docs/_static/llama-stack.png deleted file mode 100644 index 5f68c18a8..000000000 Binary files a/docs/_static/llama-stack.png and /dev/null differ diff --git a/docs/_static/providers/vector_io/read_time_comparison_sqlite-vec-faiss.png b/docs/_static/providers/vector_io/read_time_comparison_sqlite-vec-faiss.png deleted file mode 100644 index 00e5fe03a..000000000 Binary files a/docs/_static/providers/vector_io/read_time_comparison_sqlite-vec-faiss.png and /dev/null differ diff --git a/docs/_static/providers/vector_io/write_time_comparison_sqlite-vec-faiss.png b/docs/_static/providers/vector_io/write_time_comparison_sqlite-vec-faiss.png deleted file mode 100644 index bec796939..000000000 Binary files a/docs/_static/providers/vector_io/write_time_comparison_sqlite-vec-faiss.png and /dev/null differ diff --git a/docs/_static/providers/vector_io/write_time_sequence_sqlite-vec-faiss.png b/docs/_static/providers/vector_io/write_time_sequence_sqlite-vec-faiss.png deleted file mode 100644 index 192d5e96e..000000000 Binary files a/docs/_static/providers/vector_io/write_time_sequence_sqlite-vec-faiss.png and /dev/null differ diff --git a/docs/_static/remote_or_local.gif b/docs/_static/remote_or_local.gif deleted file mode 100644 index e1760dcfa..000000000 Binary files a/docs/_static/remote_or_local.gif and /dev/null differ diff --git a/docs/_static/safety_system.webp b/docs/_static/safety_system.webp deleted file mode 100644 index e153da05e..000000000 Binary files a/docs/_static/safety_system.webp and /dev/null differ