diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html index 5df6db20c..9032e5968 100644 --- a/docs/_static/llama-stack-spec.html +++ b/docs/_static/llama-stack-spec.html @@ -62,11 +62,12 @@ "tags": [ "DatasetIO" ], - "description": "", + "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" @@ -89,7 +90,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A BatchChatCompletionResponse with the full completions.", "content": { "application/json": { "schema": { @@ -114,7 +115,7 @@ "tags": [ "Inference" ], - "description": "", + "description": "Generate chat completions for a batch of messages using the specified model.", "parameters": [], "requestBody": { "content": { @@ -132,7 +133,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A BatchCompletionResponse with the full completions.", "content": { "application/json": { "schema": { @@ -157,7 +158,7 @@ "tags": [ "Inference" ], - "description": "", + "description": "Generate completions for a batch of content using the specified model.", "parameters": [], "requestBody": { "content": { @@ -193,7 +194,7 @@ "tags": [ "PostTraining (Coming Soon)" ], - "description": "", + "description": "Cancel a training job.", "parameters": [], "requestBody": { "content": { @@ -211,7 +212,7 @@ "post": { "responses": { "200": { - "description": "If stream=False, returns a ChatCompletionResponse with the full completion. If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk", + "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": { @@ -259,7 +260,7 @@ "post": { "responses": { "200": { - "description": "If stream=False, returns a CompletionResponse with the full completion. If stream=True, returns an SSE event stream of CompletionResponseStreamChunk", + "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": { @@ -453,7 +454,7 @@ "post": { "responses": { "200": { - "description": "If stream=False, returns a Turn object. If stream=True, returns an SSE event stream of AgentTurnResponseStreamChunk", + "description": "If stream=False, returns a Turn object. If stream=True, returns an SSE event stream of AgentTurnResponseStreamChunk.", "content": { "application/json": { "schema": { @@ -520,7 +521,7 @@ "post": { "responses": { "200": { - "description": "Runtime representation of an annotated type.", + "description": "An OpenAIResponseObject.", "content": { "application/json": { "schema": { @@ -568,7 +569,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListBucketResponse.", "content": { "application/json": { "schema": { @@ -598,6 +599,7 @@ { "name": "bucket", "in": "query", + "description": "Bucket name (valid chars: a-zA-Z0-9_-).", "required": true, "schema": { "type": "string" @@ -608,7 +610,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A FileUploadResponse.", "content": { "application/json": { "schema": { @@ -728,7 +730,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Session.", "content": { "application/json": { "schema": { @@ -835,7 +837,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A FileResponse.", "content": { "application/json": { "schema": { @@ -865,7 +867,7 @@ { "name": "bucket", "in": "path", - "description": "Bucket name (valid chars: a-zA-Z0-9_-)", + "description": "Bucket name (valid chars: a-zA-Z0-9_-).", "required": true, "schema": { "type": "string" @@ -874,7 +876,7 @@ { "name": "key", "in": "path", - "description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)", + "description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.).", "required": true, "schema": { "type": "string" @@ -908,7 +910,7 @@ { "name": "bucket", "in": "path", - "description": "Bucket name (valid chars: a-zA-Z0-9_-)", + "description": "Bucket name (valid chars: a-zA-Z0-9_-).", "required": true, "schema": { "type": "string" @@ -917,7 +919,7 @@ { "name": "key", "in": "path", - "description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)", + "description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.).", "required": true, "schema": { "type": "string" @@ -930,7 +932,7 @@ "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}", + "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": { @@ -973,7 +975,7 @@ "post": { "responses": { "200": { - "description": "EvaluateResponse object containing generations and scores", + "description": "EvaluateResponse object containing generations and scores.", "content": { "application/json": { "schema": { @@ -1157,7 +1159,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Benchmark.", "content": { "application/json": { "schema": { @@ -1182,11 +1184,12 @@ "tags": [ "Benchmarks" ], - "description": "", + "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" @@ -1199,7 +1202,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Dataset.", "content": { "application/json": { "schema": { @@ -1224,11 +1227,12 @@ "tags": [ "Datasets" ], - "description": "", + "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" @@ -1257,11 +1261,12 @@ "tags": [ "Datasets" ], - "description": "", + "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" @@ -1274,7 +1279,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Model.", "content": { "application/json": { "schema": { @@ -1299,11 +1304,12 @@ "tags": [ "Models" ], - "description": "", + "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" @@ -1332,11 +1338,12 @@ "tags": [ "Models" ], - "description": "", + "description": "Unregister a model.", "parameters": [ { "name": "model_id", "in": "path", + "description": "The identifier of the model to unregister.", "required": true, "schema": { "type": "string" @@ -1392,7 +1399,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ScoringFn.", "content": { "application/json": { "schema": { @@ -1417,11 +1424,12 @@ "tags": [ "ScoringFunctions" ], - "description": "", + "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" @@ -1434,7 +1442,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Shield.", "content": { "application/json": { "schema": { @@ -1459,11 +1467,12 @@ "tags": [ "Shields" ], - "description": "", + "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" @@ -1476,7 +1485,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Span.", "content": { "application/json": { "schema": { @@ -1501,11 +1510,12 @@ "tags": [ "Telemetry" ], - "description": "", + "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" @@ -1514,6 +1524,7 @@ { "name": "span_id", "in": "path", + "description": "The ID of the span to get.", "required": true, "schema": { "type": "string" @@ -1526,7 +1537,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A QuerySpanTreeResponse.", "content": { "application/json": { "schema": { @@ -1551,11 +1562,12 @@ "tags": [ "Telemetry" ], - "description": "", + "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" @@ -1578,7 +1590,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Tool.", "content": { "application/json": { "schema": { @@ -1603,11 +1615,12 @@ "tags": [ "ToolGroups" ], - "description": "", + "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" @@ -1620,7 +1633,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ToolGroup.", "content": { "application/json": { "schema": { @@ -1645,11 +1658,12 @@ "tags": [ "ToolGroups" ], - "description": "", + "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" @@ -1678,11 +1692,12 @@ "tags": [ "ToolGroups" ], - "description": "Unregister a tool group", + "description": "Unregister a tool group.", "parameters": [ { "name": "toolgroup_id", "in": "path", + "description": "The ID of the tool group to unregister.", "required": true, "schema": { "type": "string" @@ -1695,7 +1710,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A Trace.", "content": { "application/json": { "schema": { @@ -1720,11 +1735,12 @@ "tags": [ "Telemetry" ], - "description": "", + "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" @@ -1737,7 +1753,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A PostTrainingJobArtifactsResponse.", "content": { "application/json": { "schema": { @@ -1762,11 +1778,12 @@ "tags": [ "PostTraining (Coming Soon)" ], - "description": "", + "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" @@ -1779,7 +1796,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A PostTrainingJobStatusResponse.", "content": { "application/json": { "schema": { @@ -1804,11 +1821,12 @@ "tags": [ "PostTraining (Coming Soon)" ], - "description": "", + "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" @@ -1821,7 +1839,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListPostTrainingJobsResponse.", "content": { "application/json": { "schema": { @@ -1846,7 +1864,7 @@ "tags": [ "PostTraining (Coming Soon)" ], - "description": "", + "description": "Get all training jobs.", "parameters": [] } }, @@ -1854,7 +1872,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A FileUploadResponse.", "content": { "application/json": { "schema": { @@ -1879,12 +1897,12 @@ "tags": [ "Files" ], - "description": "Returns information about an existsing upload session", + "description": "Returns information about an existsing upload session.", "parameters": [ { "name": "upload_id", "in": "path", - "description": "ID of the upload session", + "description": "ID of the upload session.", "required": true, "schema": { "type": "string" @@ -1895,7 +1913,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A FileResponse or None if the upload is not complete.", "content": { "application/json": { "schema": { @@ -1932,7 +1950,7 @@ { "name": "upload_id", "in": "path", - "description": "ID of the upload session", + "description": "ID of the upload session.", "required": true, "schema": { "type": "string" @@ -1956,7 +1974,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A VectorDB.", "content": { "application/json": { "schema": { @@ -1981,11 +1999,12 @@ "tags": [ "VectorDBs" ], - "description": "", + "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" @@ -2014,11 +2033,12 @@ "tags": [ "VectorDBs" ], - "description": "", + "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" @@ -2031,7 +2051,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A HealthInfo.", "content": { "application/json": { "schema": { @@ -2056,7 +2076,7 @@ "tags": [ "Inspect" ], - "description": "", + "description": "Get the health of the service.", "parameters": [] } }, @@ -2118,7 +2138,7 @@ "tags": [ "VectorIO" ], - "description": "", + "description": "Insert chunks into a vector database.", "parameters": [], "requestBody": { "content": { @@ -2136,7 +2156,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ProviderInfo object containing the provider's details.", "content": { "application/json": { "schema": { @@ -2161,11 +2181,12 @@ "tags": [ "Providers" ], - "description": "", + "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" @@ -2178,7 +2199,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A ToolInvocationResult.", "content": { "application/json": { "schema": { @@ -2203,7 +2224,7 @@ "tags": [ "ToolRuntime" ], - "description": "Run a tool with the given arguments", + "description": "Run a tool with the given arguments.", "parameters": [], "requestBody": { "content": { @@ -2221,7 +2242,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A PaginatedResponse.", "content": { "application/json": { "schema": { @@ -2246,7 +2267,7 @@ "tags": [ "DatasetIO" ], - "description": "Get a paginated list of rows from a dataset.\nUses offset-based pagination where:\n- start_index: The starting index (0-based). If None, starts from beginning.\n- limit: Number of items to return. If None or -1, returns all items.\n\nThe response includes:\n- data: List of items for the current page\n- has_more: Whether there are more items available after this set", + "description": "Get a paginated list of rows from a dataset.\nUses offset-based pagination where:\n- start_index: The starting index (0-based). If None, starts from beginning.\n- limit: Number of items to return. If None or -1, returns all items.\n\nThe response includes:\n- data: List of items for the current page.\n- has_more: Whether there are more items available after this set.", "parameters": [ { "name": "dataset_id", @@ -2282,7 +2303,7 @@ "get": { "responses": { "200": { - "description": "The status of the evaluationjob.", + "description": "The status of the evaluation job.", "content": { "application/json": { "schema": { @@ -2490,7 +2511,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListBenchmarksResponse.", "content": { "application/json": { "schema": { @@ -2515,7 +2536,7 @@ "tags": [ "Benchmarks" ], - "description": "", + "description": "List all benchmarks.", "parameters": [] }, "post": { @@ -2539,7 +2560,7 @@ "tags": [ "Benchmarks" ], - "description": "", + "description": "Register a benchmark.", "parameters": [], "requestBody": { "content": { @@ -2557,7 +2578,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListDatasetsResponse.", "content": { "application/json": { "schema": { @@ -2582,13 +2603,13 @@ "tags": [ "Datasets" ], - "description": "", + "description": "List all datasets.", "parameters": [] }, "post": { "responses": { "200": { - "description": "OK", + "description": "A Dataset.", "content": { "application/json": { "schema": { @@ -2631,7 +2652,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListFileResponse.", "content": { "application/json": { "schema": { @@ -2661,7 +2682,7 @@ { "name": "bucket", "in": "path", - "description": "Bucket name (valid chars: a-zA-Z0-9_-)", + "description": "Bucket name (valid chars: a-zA-Z0-9_-).", "required": true, "schema": { "type": "string" @@ -2674,7 +2695,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListModelsResponse.", "content": { "application/json": { "schema": { @@ -2699,13 +2720,13 @@ "tags": [ "Models" ], - "description": "", + "description": "List all models.", "parameters": [] }, "post": { "responses": { "200": { - "description": "OK", + "description": "A Model.", "content": { "application/json": { "schema": { @@ -2730,7 +2751,7 @@ "tags": [ "Models" ], - "description": "", + "description": "Register a model.", "parameters": [], "requestBody": { "content": { @@ -2748,7 +2769,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListProvidersResponse containing information about all providers.", "content": { "application/json": { "schema": { @@ -2773,7 +2794,7 @@ "tags": [ "Providers" ], - "description": "", + "description": "List all available providers.", "parameters": [] } }, @@ -2781,7 +2802,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListRoutesResponse.", "content": { "application/json": { "schema": { @@ -2806,7 +2827,7 @@ "tags": [ "Inspect" ], - "description": "", + "description": "List all routes.", "parameters": [] } }, @@ -2814,7 +2835,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListToolDefsResponse.", "content": { "application/json": { "schema": { @@ -2839,11 +2860,12 @@ "tags": [ "ToolRuntime" ], - "description": "", + "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" @@ -2852,6 +2874,7 @@ { "name": "mcp_endpoint", "in": "query", + "description": "The MCP endpoint to use for the tool group.", "required": false, "schema": { "$ref": "#/components/schemas/URL" @@ -2864,7 +2887,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListScoringFunctionsResponse.", "content": { "application/json": { "schema": { @@ -2889,7 +2912,7 @@ "tags": [ "ScoringFunctions" ], - "description": "", + "description": "List all scoring functions.", "parameters": [] }, "post": { @@ -2913,7 +2936,7 @@ "tags": [ "ScoringFunctions" ], - "description": "", + "description": "Register a scoring function.", "parameters": [], "requestBody": { "content": { @@ -2931,7 +2954,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListShieldsResponse.", "content": { "application/json": { "schema": { @@ -2956,13 +2979,13 @@ "tags": [ "Shields" ], - "description": "", + "description": "List all shields.", "parameters": [] }, "post": { "responses": { "200": { - "description": "OK", + "description": "A Shield.", "content": { "application/json": { "schema": { @@ -2987,7 +3010,7 @@ "tags": [ "Shields" ], - "description": "", + "description": "Register a shield.", "parameters": [], "requestBody": { "content": { @@ -3005,7 +3028,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListToolGroupsResponse.", "content": { "application/json": { "schema": { @@ -3030,7 +3053,7 @@ "tags": [ "ToolGroups" ], - "description": "List tool groups with optional provider", + "description": "List tool groups with optional provider.", "parameters": [] }, "post": { @@ -3054,7 +3077,7 @@ "tags": [ "ToolGroups" ], - "description": "Register a tool group", + "description": "Register a tool group.", "parameters": [], "requestBody": { "content": { @@ -3072,7 +3095,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListToolsResponse.", "content": { "application/json": { "schema": { @@ -3097,11 +3120,12 @@ "tags": [ "ToolGroups" ], - "description": "List tools with optional tool group", + "description": "List tools with optional tool group.", "parameters": [ { "name": "toolgroup_id", "in": "query", + "description": "The ID of the tool group to list tools for.", "required": false, "schema": { "type": "string" @@ -3114,7 +3138,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A ListVectorDBsResponse.", "content": { "application/json": { "schema": { @@ -3139,13 +3163,13 @@ "tags": [ "VectorDBs" ], - "description": "", + "description": "List all vector databases.", "parameters": [] }, "post": { "responses": { "200": { - "description": "OK", + "description": "A VectorDB.", "content": { "application/json": { "schema": { @@ -3170,7 +3194,7 @@ "tags": [ "VectorDBs" ], - "description": "", + "description": "Register a vector database.", "parameters": [], "requestBody": { "content": { @@ -3206,7 +3230,7 @@ "tags": [ "Telemetry" ], - "description": "", + "description": "Log an event.", "parameters": [], "requestBody": { "content": { @@ -3224,7 +3248,7 @@ "post": { "responses": { "200": { - "description": "Response from an OpenAI-compatible chat completion request. **OR** Chunk from a streaming response to an OpenAI-compatible chat completion request.", + "description": "An OpenAIChatCompletion.", "content": { "application/json": { "schema": { @@ -3274,7 +3298,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "An OpenAICompletion.", "content": { "application/json": { "schema": { @@ -3317,7 +3341,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A OpenAIListModelsResponse.", "content": { "application/json": { "schema": { @@ -3342,7 +3366,7 @@ "tags": [ "Models" ], - "description": "", + "description": "List models using the OpenAI API.", "parameters": [] } }, @@ -3350,7 +3374,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A PostTrainingJob.", "content": { "application/json": { "schema": { @@ -3375,7 +3399,7 @@ "tags": [ "PostTraining (Coming Soon)" ], - "description": "", + "description": "Run preference optimization of a model.", "parameters": [], "requestBody": { "content": { @@ -3436,7 +3460,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A QueryChunksResponse.", "content": { "application/json": { "schema": { @@ -3461,7 +3485,7 @@ "tags": [ "VectorIO" ], - "description": "", + "description": "Query chunks from a vector database.", "parameters": [], "requestBody": { "content": { @@ -3479,7 +3503,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A QueryMetricsResponse.", "content": { "application/json": { "schema": { @@ -3504,11 +3528,12 @@ "tags": [ "Telemetry" ], - "description": "", + "description": "Query metrics.", "parameters": [ { "name": "metric_name", "in": "path", + "description": "The name of the metric to query.", "required": true, "schema": { "type": "string" @@ -3531,7 +3556,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A QuerySpansResponse.", "content": { "application/json": { "schema": { @@ -3556,7 +3581,7 @@ "tags": [ "Telemetry" ], - "description": "", + "description": "Query spans.", "parameters": [], "requestBody": { "content": { @@ -3574,7 +3599,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A QueryTracesResponse.", "content": { "application/json": { "schema": { @@ -3599,7 +3624,7 @@ "tags": [ "Telemetry" ], - "description": "", + "description": "Query traces.", "parameters": [], "requestBody": { "content": { @@ -3746,7 +3771,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A RunShieldResponse.", "content": { "application/json": { "schema": { @@ -3771,7 +3796,7 @@ "tags": [ "Safety" ], - "description": "", + "description": "Run a shield.", "parameters": [], "requestBody": { "content": { @@ -3807,7 +3832,7 @@ "tags": [ "Telemetry" ], - "description": "", + "description": "Save spans to a dataset.", "parameters": [], "requestBody": { "content": { @@ -3825,7 +3850,7 @@ "post": { "responses": { "200": { - "description": "ScoreResponse object containing rows and aggregated results", + "description": "A ScoreResponse object containing rows and aggregated results.", "content": { "application/json": { "schema": { @@ -3868,7 +3893,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A ScoreBatchResponse.", "content": { "application/json": { "schema": { @@ -3893,7 +3918,7 @@ "tags": [ "Scoring" ], - "description": "", + "description": "Score a batch of rows.", "parameters": [], "requestBody": { "content": { @@ -3911,7 +3936,7 @@ "post": { "responses": { "200": { - "description": "OK", + "description": "A PostTrainingJob.", "content": { "application/json": { "schema": { @@ -3936,7 +3961,7 @@ "tags": [ "PostTraining (Coming Soon)" ], - "description": "", + "description": "Run supervised fine-tuning of a model.", "parameters": [], "requestBody": { "content": { @@ -3997,7 +4022,7 @@ "get": { "responses": { "200": { - "description": "OK", + "description": "A VersionInfo.", "content": { "application/json": { "schema": { @@ -4022,7 +4047,7 @@ "tags": [ "Inspect" ], - "description": "", + "description": "Get the version of the service.", "parameters": [] } } @@ -4088,7 +4113,8 @@ } ] } - } + }, + "description": "The rows to append to the dataset." } }, "additionalProperties": false, @@ -4795,7 +4821,8 @@ "type": "object", "properties": { "model_id": { - "type": "string" + "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", @@ -4804,22 +4831,27 @@ "items": { "$ref": "#/components/schemas/Message" } - } + }, + "description": "The messages to generate completions for." }, "sampling_params": { - "$ref": "#/components/schemas/SamplingParams" + "$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" + "$ref": "#/components/schemas/ToolConfig", + "description": "(Optional) Configuration for tool use." }, "response_format": { - "$ref": "#/components/schemas/ResponseFormat" + "$ref": "#/components/schemas/ResponseFormat", + "description": "(Optional) Grammar specification for guided (structured) decoding." }, "logprobs": { "type": "object", @@ -4831,7 +4863,7 @@ } }, "additionalProperties": false, - "title": "LogProbConfig" + "description": "(Optional) If specified, log probabilities for each token position will be returned." } }, "additionalProperties": false, @@ -4934,19 +4966,23 @@ "type": "object", "properties": { "model_id": { - "type": "string" + "type": "string", + "description": "The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint." }, "content_batch": { "type": "array", "items": { "$ref": "#/components/schemas/InterleavedContent" - } + }, + "description": "The content to generate completions for." }, "sampling_params": { - "$ref": "#/components/schemas/SamplingParams" + "$ref": "#/components/schemas/SamplingParams", + "description": "(Optional) Parameters to control the sampling strategy." }, "response_format": { - "$ref": "#/components/schemas/ResponseFormat" + "$ref": "#/components/schemas/ResponseFormat", + "description": "(Optional) Grammar specification for guided (structured) decoding." }, "logprobs": { "type": "object", @@ -4958,7 +4994,7 @@ } }, "additionalProperties": false, - "title": "LogProbConfig" + "description": "(Optional) If specified, log probabilities for each token position will be returned." } }, "additionalProperties": false, @@ -5026,7 +5062,8 @@ "type": "object", "properties": { "job_uuid": { - "type": "string" + "type": "string", + "description": "The UUID of the job to cancel." } }, "additionalProperties": false, @@ -5047,18 +5084,18 @@ "items": { "$ref": "#/components/schemas/Message" }, - "description": "List of messages in the conversation" + "description": "List of messages in the conversation." }, "sampling_params": { "$ref": "#/components/schemas/SamplingParams", - "description": "Parameters to control the sampling strategy" + "description": "Parameters to control the sampling strategy." }, "tools": { "type": "array", "items": { "$ref": "#/components/schemas/ToolDefinition" }, - "description": "(Optional) List of tool definitions available to the model" + "description": "(Optional) List of tool definitions available to the model." }, "tool_choice": { "type": "string", @@ -5278,15 +5315,15 @@ }, "content": { "$ref": "#/components/schemas/InterleavedContent", - "description": "The content to generate a completion for" + "description": "The content to generate a completion for." }, "sampling_params": { "$ref": "#/components/schemas/SamplingParams", - "description": "(Optional) Parameters to control the sampling strategy" + "description": "(Optional) Parameters to control the sampling strategy." }, "response_format": { "$ref": "#/components/schemas/ResponseFormat", - "description": "(Optional) Grammar specification for guided (structured) decoding" + "description": "(Optional) Grammar specification for guided (structured) decoding." }, "stream": { "type": "boolean", @@ -7065,19 +7102,19 @@ "properties": { "bucket": { "type": "string", - "description": "Bucket under which the file is stored (valid chars: a-zA-Z0-9_-)" + "description": "Bucket under which the file is stored (valid chars: a-zA-Z0-9_-)." }, "key": { "type": "string", - "description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)" + "description": "Key under which the file is stored (valid chars: a-zA-Z0-9_-/.)." }, "mime_type": { "type": "string", - "description": "MIME type of the file" + "description": "MIME type of the file." }, "size": { "type": "integer", - "description": "File size in bytes" + "description": "File size in bytes." } }, "additionalProperties": false, @@ -8422,10 +8459,12 @@ "type": "array", "items": { "type": "string" - } + }, + "description": "The attributes to return in the tree." }, "max_depth": { - "type": "integer" + "type": "integer", + "description": "The maximum depth of the tree." } }, "additionalProperties": false, @@ -8977,7 +9016,8 @@ "type": "object", "properties": { "vector_db_id": { - "type": "string" + "type": "string", + "description": "The identifier of the vector database to insert the chunks into." }, "chunks": { "type": "array", @@ -9019,10 +9059,12 @@ "metadata" ], "title": "Chunk" - } + }, + "description": "The chunks to insert." }, "ttl_seconds": { - "type": "integer" + "type": "integer", + "description": "The time to live of the chunks." } }, "additionalProperties": false, @@ -9109,7 +9151,8 @@ "type": "object", "properties": { "tool_name": { - "type": "string" + "type": "string", + "description": "The name of the tool to invoke." }, "kwargs": { "type": "object", @@ -9134,7 +9177,8 @@ "type": "object" } ] - } + }, + "description": "A dictionary of arguments to pass to the tool." } }, "additionalProperties": false, @@ -9797,10 +9841,12 @@ "type": "object", "properties": { "event": { - "$ref": "#/components/schemas/Event" + "$ref": "#/components/schemas/Event", + "description": "The event to log." }, "ttl_seconds": { - "type": "integer" + "type": "integer", + "description": "The time to live of the event." } }, "additionalProperties": false, @@ -10260,11 +10306,11 @@ "items": { "$ref": "#/components/schemas/OpenAIMessageParam" }, - "description": "List of messages in the conversation" + "description": "List of messages in the conversation." }, "frequency_penalty": { "type": "number", - "description": "(Optional) The penalty for repeated tokens" + "description": "(Optional) The penalty for repeated tokens." }, "function_call": { "oneOf": [ @@ -10297,7 +10343,7 @@ } } ], - "description": "(Optional) The function call to use" + "description": "(Optional) The function call to use." }, "functions": { "type": "array", @@ -10326,46 +10372,46 @@ ] } }, - "description": "(Optional) List of functions to use" + "description": "(Optional) List of functions to use." }, "logit_bias": { "type": "object", "additionalProperties": { "type": "number" }, - "description": "(Optional) The logit bias to use" + "description": "(Optional) The logit bias to use." }, "logprobs": { "type": "boolean", - "description": "(Optional) The log probabilities to use" + "description": "(Optional) The log probabilities to use." }, "max_completion_tokens": { "type": "integer", - "description": "(Optional) The maximum number of tokens to generate" + "description": "(Optional) The maximum number of tokens to generate." }, "max_tokens": { "type": "integer", - "description": "(Optional) The maximum number of tokens to generate" + "description": "(Optional) The maximum number of tokens to generate." }, "n": { "type": "integer", - "description": "(Optional) The number of completions to generate" + "description": "(Optional) The number of completions to generate." }, "parallel_tool_calls": { "type": "boolean", - "description": "(Optional) Whether to parallelize tool calls" + "description": "(Optional) Whether to parallelize tool calls." }, "presence_penalty": { "type": "number", - "description": "(Optional) The penalty for repeated tokens" + "description": "(Optional) The penalty for repeated tokens." }, "response_format": { "$ref": "#/components/schemas/OpenAIResponseFormatParam", - "description": "(Optional) The response format to use" + "description": "(Optional) The response format to use." }, "seed": { "type": "integer", - "description": "(Optional) The seed to use" + "description": "(Optional) The seed to use." }, "stop": { "oneOf": [ @@ -10379,11 +10425,11 @@ } } ], - "description": "(Optional) The stop tokens to use" + "description": "(Optional) The stop tokens to use." }, "stream": { "type": "boolean", - "description": "(Optional) Whether to stream the response" + "description": "(Optional) Whether to stream the response." }, "stream_options": { "type": "object", @@ -10409,11 +10455,11 @@ } ] }, - "description": "(Optional) The stream options to use" + "description": "(Optional) The stream options to use." }, "temperature": { "type": "number", - "description": "(Optional) The temperature to use" + "description": "(Optional) The temperature to use." }, "tool_choice": { "oneOf": [ @@ -10446,7 +10492,7 @@ } } ], - "description": "(Optional) The tool choice to use" + "description": "(Optional) The tool choice to use." }, "tools": { "type": "array", @@ -10475,19 +10521,19 @@ ] } }, - "description": "(Optional) The tools to use" + "description": "(Optional) The tools to use." }, "top_logprobs": { "type": "integer", - "description": "(Optional) The top log probabilities to use" + "description": "(Optional) The top log probabilities to use." }, "top_p": { "type": "number", - "description": "(Optional) The top p to use" + "description": "(Optional) The top p to use." }, "user": { "type": "string", - "description": "(Optional) The user to use" + "description": "(Optional) The user to use." } }, "additionalProperties": false, @@ -10773,46 +10819,46 @@ } } ], - "description": "The prompt to generate a completion for" + "description": "The prompt to generate a completion for." }, "best_of": { "type": "integer", - "description": "(Optional) The number of completions to generate" + "description": "(Optional) The number of completions to generate." }, "echo": { "type": "boolean", - "description": "(Optional) Whether to echo the prompt" + "description": "(Optional) Whether to echo the prompt." }, "frequency_penalty": { "type": "number", - "description": "(Optional) The penalty for repeated tokens" + "description": "(Optional) The penalty for repeated tokens." }, "logit_bias": { "type": "object", "additionalProperties": { "type": "number" }, - "description": "(Optional) The logit bias to use" + "description": "(Optional) The logit bias to use." }, "logprobs": { "type": "boolean", - "description": "(Optional) The log probabilities to use" + "description": "(Optional) The log probabilities to use." }, "max_tokens": { "type": "integer", - "description": "(Optional) The maximum number of tokens to generate" + "description": "(Optional) The maximum number of tokens to generate." }, "n": { "type": "integer", - "description": "(Optional) The number of completions to generate" + "description": "(Optional) The number of completions to generate." }, "presence_penalty": { "type": "number", - "description": "(Optional) The penalty for repeated tokens" + "description": "(Optional) The penalty for repeated tokens." }, "seed": { "type": "integer", - "description": "(Optional) The seed to use" + "description": "(Optional) The seed to use." }, "stop": { "oneOf": [ @@ -10826,11 +10872,11 @@ } } ], - "description": "(Optional) The stop tokens to use" + "description": "(Optional) The stop tokens to use." }, "stream": { "type": "boolean", - "description": "(Optional) Whether to stream the response" + "description": "(Optional) Whether to stream the response." }, "stream_options": { "type": "object", @@ -10856,19 +10902,19 @@ } ] }, - "description": "(Optional) The stream options to use" + "description": "(Optional) The stream options to use." }, "temperature": { "type": "number", - "description": "(Optional) The temperature to use" + "description": "(Optional) The temperature to use." }, "top_p": { "type": "number", - "description": "(Optional) The top p to use" + "description": "(Optional) The top p to use." }, "user": { "type": "string", - "description": "(Optional) The user to use" + "description": "(Optional) The user to use." }, "guided_choice": { "type": "array", @@ -11161,16 +11207,20 @@ "type": "object", "properties": { "job_uuid": { - "type": "string" + "type": "string", + "description": "The UUID of the job to create." }, "finetuned_model": { - "type": "string" + "type": "string", + "description": "The model to fine-tune." }, "algorithm_config": { - "$ref": "#/components/schemas/DPOAlignmentConfig" + "$ref": "#/components/schemas/DPOAlignmentConfig", + "description": "The algorithm configuration." }, "training_config": { - "$ref": "#/components/schemas/TrainingConfig" + "$ref": "#/components/schemas/TrainingConfig", + "description": "The training configuration." }, "hyperparam_search_config": { "type": "object", @@ -11195,7 +11245,8 @@ "type": "object" } ] - } + }, + "description": "The hyperparam search configuration." }, "logger_config": { "type": "object", @@ -11220,7 +11271,8 @@ "type": "object" } ] - } + }, + "description": "The logger configuration." } }, "additionalProperties": false, @@ -11405,10 +11457,12 @@ "type": "object", "properties": { "vector_db_id": { - "type": "string" + "type": "string", + "description": "The identifier of the vector database to query." }, "query": { - "$ref": "#/components/schemas/InterleavedContent" + "$ref": "#/components/schemas/InterleavedContent", + "description": "The query to search for." }, "params": { "type": "object", @@ -11433,7 +11487,8 @@ "type": "object" } ] - } + }, + "description": "The parameters of the query." } }, "additionalProperties": false, @@ -11506,13 +11561,16 @@ "type": "object", "properties": { "start_time": { - "type": "integer" + "type": "integer", + "description": "The start time of the metric to query." }, "end_time": { - "type": "integer" + "type": "integer", + "description": "The end time of the metric to query." }, "granularity": { - "type": "string" + "type": "string", + "description": "The granularity of the metric to query." }, "query_type": { "type": "string", @@ -11520,7 +11578,7 @@ "range", "instant" ], - "title": "MetricQueryType" + "description": "The type of query to perform." }, "label_matchers": { "type": "array", @@ -11552,7 +11610,8 @@ "operator" ], "title": "MetricLabelMatcher" - } + }, + "description": "The label matchers to apply to the metric." } }, "additionalProperties": false, @@ -11696,16 +11755,19 @@ "type": "array", "items": { "$ref": "#/components/schemas/QueryCondition" - } + }, + "description": "The attribute filters to apply to the spans." }, "attributes_to_return": { "type": "array", "items": { "type": "string" - } + }, + "description": "The attributes to return in the spans." }, "max_depth": { - "type": "integer" + "type": "integer", + "description": "The maximum depth of the tree." } }, "additionalProperties": false, @@ -11738,19 +11800,23 @@ "type": "array", "items": { "$ref": "#/components/schemas/QueryCondition" - } + }, + "description": "The attribute filters to apply to the traces." }, "limit": { - "type": "integer" + "type": "integer", + "description": "The limit of traces to return." }, "offset": { - "type": "integer" + "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, @@ -11776,22 +11842,27 @@ "type": "object", "properties": { "benchmark_id": { - "type": "string" + "type": "string", + "description": "The ID of the benchmark to register." }, "dataset_id": { - "type": "string" + "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" + "type": "string", + "description": "The ID of the provider benchmark to use for the benchmark." }, "provider_id": { - "type": "string" + "type": "string", + "description": "The ID of the provider to use for the benchmark." }, "metadata": { "type": "object", @@ -11816,7 +11887,8 @@ "type": "object" } ] - } + }, + "description": "The metadata to use for the benchmark." } }, "additionalProperties": false, @@ -11837,7 +11909,7 @@ "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\" }" + "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": { "$ref": "#/components/schemas/DataSource", @@ -11867,7 +11939,7 @@ } ] }, - "description": "The metadata for the dataset. - E.g. {\"description\": \"My dataset\"}" + "description": "The metadata for the dataset. - E.g. {\"description\": \"My dataset\"}." }, "dataset_id": { "type": "string", @@ -11885,13 +11957,16 @@ "type": "object", "properties": { "model_id": { - "type": "string" + "type": "string", + "description": "The identifier of the model to register." }, "provider_model_id": { - "type": "string" + "type": "string", + "description": "The identifier of the model in the provider." }, "provider_id": { - "type": "string" + "type": "string", + "description": "The identifier of the provider." }, "metadata": { "type": "object", @@ -11916,10 +11991,12 @@ "type": "object" } ] - } + }, + "description": "Any additional metadata for this model." }, "model_type": { - "$ref": "#/components/schemas/ModelType" + "$ref": "#/components/schemas/ModelType", + "description": "The type of model to register." } }, "additionalProperties": false, @@ -11932,22 +12009,28 @@ "type": "object", "properties": { "scoring_fn_id": { - "type": "string" + "type": "string", + "description": "The ID of the scoring function to register." }, "description": { - "type": "string" + "type": "string", + "description": "The description of the scoring function." }, "return_type": { - "$ref": "#/components/schemas/ParamType" + "$ref": "#/components/schemas/ParamType", + "description": "The return type of the scoring function." }, "provider_scoring_fn_id": { - "type": "string" + "type": "string", + "description": "The ID of the provider scoring function to use for the scoring function." }, "provider_id": { - "type": "string" + "type": "string", + "description": "The ID of the provider to use for the scoring function." }, "params": { - "$ref": "#/components/schemas/ScoringFnParams" + "$ref": "#/components/schemas/ScoringFnParams", + "description": "The parameters for the scoring function for benchmark eval, these can be overridden for app eval." } }, "additionalProperties": false, @@ -11962,13 +12045,16 @@ "type": "object", "properties": { "shield_id": { - "type": "string" + "type": "string", + "description": "The identifier of the shield to register." }, "provider_shield_id": { - "type": "string" + "type": "string", + "description": "The identifier of the shield in the provider." }, "provider_id": { - "type": "string" + "type": "string", + "description": "The identifier of the provider." }, "params": { "type": "object", @@ -11993,7 +12079,8 @@ "type": "object" } ] - } + }, + "description": "The parameters of the shield." } }, "additionalProperties": false, @@ -12006,13 +12093,16 @@ "type": "object", "properties": { "toolgroup_id": { - "type": "string" + "type": "string", + "description": "The ID of the tool group to register." }, "provider_id": { - "type": "string" + "type": "string", + "description": "The ID of the provider to use for the tool group." }, "mcp_endpoint": { - "$ref": "#/components/schemas/URL" + "$ref": "#/components/schemas/URL", + "description": "The MCP endpoint to use for the tool group." }, "args": { "type": "object", @@ -12037,7 +12127,8 @@ "type": "object" } ] - } + }, + "description": "A dictionary of arguments to pass to the tool group." } }, "additionalProperties": false, @@ -12051,19 +12142,24 @@ "type": "object", "properties": { "vector_db_id": { - "type": "string" + "type": "string", + "description": "The identifier of the vector database to register." }, "embedding_model": { - "type": "string" + "type": "string", + "description": "The embedding model to use." }, "embedding_dimension": { - "type": "integer" + "type": "integer", + "description": "The dimension of the embedding model." }, "provider_id": { - "type": "string" + "type": "string", + "description": "The identifier of the provider." }, "provider_vector_db_id": { - "type": "string" + "type": "string", + "description": "The identifier of the vector database in the provider." } }, "additionalProperties": false, @@ -12112,13 +12208,15 @@ "type": "object", "properties": { "shield_id": { - "type": "string" + "type": "string", + "description": "The identifier of the shield to run." }, "messages": { "type": "array", "items": { "$ref": "#/components/schemas/Message" - } + }, + "description": "The messages to run the shield on." }, "params": { "type": "object", @@ -12143,7 +12241,8 @@ "type": "object" } ] - } + }, + "description": "The parameters of the shield." } }, "additionalProperties": false, @@ -12171,19 +12270,23 @@ "type": "array", "items": { "$ref": "#/components/schemas/QueryCondition" - } + }, + "description": "The attribute filters to apply to the spans." }, "attributes_to_save": { "type": "array", "items": { "type": "string" - } + }, + "description": "The attributes to save to the dataset." }, "dataset_id": { - "type": "string" + "type": "string", + "description": "The ID of the dataset to save the spans to." }, "max_depth": { - "type": "integer" + "type": "integer", + "description": "The maximum depth of the tree." } }, "additionalProperties": false, @@ -12270,7 +12373,8 @@ "type": "object", "properties": { "dataset_id": { - "type": "string" + "type": "string", + "description": "The ID of the dataset to score." }, "scoring_functions": { "type": "object", @@ -12283,10 +12387,12 @@ "type": "null" } ] - } + }, + "description": "The scoring functions to use for the scoring." }, "save_results_dataset": { - "type": "boolean" + "type": "boolean", + "description": "Whether to save the results to a dataset." } }, "additionalProperties": false, @@ -12406,10 +12512,12 @@ "type": "object", "properties": { "job_uuid": { - "type": "string" + "type": "string", + "description": "The UUID of the job to create." }, "training_config": { - "$ref": "#/components/schemas/TrainingConfig" + "$ref": "#/components/schemas/TrainingConfig", + "description": "The training configuration." }, "hyperparam_search_config": { "type": "object", @@ -12434,7 +12542,8 @@ "type": "object" } ] - } + }, + "description": "The hyperparam search configuration." }, "logger_config": { "type": "object", @@ -12459,16 +12568,20 @@ "type": "object" } ] - } + }, + "description": "The logger configuration." }, "model": { - "type": "string" + "type": "string", + "description": "The model to fine-tune." }, "checkpoint_dir": { - "type": "string" + "type": "string", + "description": "The directory to save checkpoint(s) to." }, "algorithm_config": { - "$ref": "#/components/schemas/AlgorithmConfig" + "$ref": "#/components/schemas/AlgorithmConfig", + "description": "The algorithm configuration." } }, "additionalProperties": false, diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml index fb2dbf241..a988e0eab 100644 --- a/docs/_static/llama-stack-spec.yaml +++ b/docs/_static/llama-stack-spec.yaml @@ -27,10 +27,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - DatasetIO - description: '' + 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 @@ -44,7 +46,8 @@ paths: post: responses: '200': - description: OK + description: >- + A BatchChatCompletionResponse with the full completions. content: application/json: schema: @@ -61,7 +64,8 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Inference - description: '' + description: >- + Generate chat completions for a batch of messages using the specified model. parameters: [] requestBody: content: @@ -73,7 +77,8 @@ paths: post: responses: '200': - description: OK + description: >- + A BatchCompletionResponse with the full completions. content: application/json: schema: @@ -90,7 +95,8 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Inference - description: '' + description: >- + Generate completions for a batch of content using the specified model. parameters: [] requestBody: content: @@ -115,7 +121,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - PostTraining (Coming Soon) - description: '' + description: Cancel a training job. parameters: [] requestBody: content: @@ -129,7 +135,7 @@ paths: '200': description: >- If stream=False, returns a ChatCompletionResponse with the full completion. - If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk + If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk. content: application/json: schema: @@ -164,7 +170,7 @@ paths: '200': description: >- If stream=False, returns a CompletionResponse with the full completion. - If stream=True, returns an SSE event stream of CompletionResponseStreamChunk + If stream=True, returns an SSE event stream of CompletionResponseStreamChunk. content: application/json: schema: @@ -300,7 +306,7 @@ paths: '200': description: >- If stream=False, returns a Turn object. If stream=True, returns an SSE - event stream of AgentTurnResponseStreamChunk + event stream of AgentTurnResponseStreamChunk. content: application/json: schema: @@ -346,8 +352,7 @@ paths: post: responses: '200': - description: >- - Runtime representation of an annotated type. + description: An OpenAIResponseObject. content: application/json: schema: @@ -379,7 +384,7 @@ paths: get: responses: '200': - description: OK + description: A ListBucketResponse. content: application/json: schema: @@ -400,13 +405,14 @@ paths: parameters: - name: bucket in: query + description: 'Bucket name (valid chars: a-zA-Z0-9_-).' required: true schema: type: string post: responses: '200': - description: OK + description: A FileUploadResponse. content: application/json: schema: @@ -490,7 +496,7 @@ paths: get: responses: '200': - description: OK + description: A Session. content: application/json: schema: @@ -567,7 +573,7 @@ paths: get: responses: '200': - description: OK + description: A FileResponse. content: application/json: schema: @@ -589,14 +595,14 @@ paths: parameters: - name: bucket in: path - description: 'Bucket name (valid chars: a-zA-Z0-9_-)' + description: 'Bucket name (valid chars: a-zA-Z0-9_-).' required: true schema: type: string - name: key in: path description: >- - Key under which the file is stored (valid chars: a-zA-Z0-9_-/.) + Key under which the file is stored (valid chars: a-zA-Z0-9_-/.). required: true schema: type: string @@ -621,14 +627,14 @@ paths: parameters: - name: bucket in: path - description: 'Bucket name (valid chars: a-zA-Z0-9_-)' + description: 'Bucket name (valid chars: a-zA-Z0-9_-).' required: true schema: type: string - name: key in: path description: >- - Key under which the file is stored (valid chars: a-zA-Z0-9_-/.) + Key under which the file is stored (valid chars: a-zA-Z0-9_-/.). required: true schema: type: string @@ -639,7 +645,7 @@ paths: 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} + can check model metadata using /models/{model_id}. content: application/json: schema: @@ -670,7 +676,7 @@ paths: responses: '200': description: >- - EvaluateResponse object containing generations and scores + EvaluateResponse object containing generations and scores. content: application/json: schema: @@ -796,7 +802,7 @@ paths: get: responses: '200': - description: OK + description: A Benchmark. content: application/json: schema: @@ -813,10 +819,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Benchmarks - description: '' + 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 @@ -824,7 +831,7 @@ paths: get: responses: '200': - description: OK + description: A Dataset. content: application/json: schema: @@ -841,10 +848,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Datasets - description: '' + 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 @@ -864,10 +872,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Datasets - description: '' + 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 @@ -875,7 +884,7 @@ paths: get: responses: '200': - description: OK + description: A Model. content: application/json: schema: @@ -892,10 +901,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Models - description: '' + 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 @@ -915,10 +925,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Models - description: '' + description: Unregister a model. parameters: - name: model_id in: path + description: >- + The identifier of the model to unregister. required: true schema: type: string @@ -956,7 +968,7 @@ paths: get: responses: '200': - description: OK + description: A ScoringFn. content: application/json: schema: @@ -973,10 +985,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ScoringFunctions - description: '' + 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 @@ -984,7 +997,7 @@ paths: get: responses: '200': - description: OK + description: A Shield. content: application/json: schema: @@ -1001,10 +1014,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Shields - description: '' + 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 @@ -1012,7 +1026,7 @@ paths: get: responses: '200': - description: OK + description: A Span. content: application/json: schema: @@ -1029,15 +1043,18 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + 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 @@ -1045,7 +1062,7 @@ paths: post: responses: '200': - description: OK + description: A QuerySpanTreeResponse. content: application/json: schema: @@ -1062,10 +1079,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + 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 @@ -1079,7 +1097,7 @@ paths: get: responses: '200': - description: OK + description: A Tool. content: application/json: schema: @@ -1096,10 +1114,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolGroups - description: '' + 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 @@ -1107,7 +1126,7 @@ paths: get: responses: '200': - description: OK + description: A ToolGroup. content: application/json: schema: @@ -1124,10 +1143,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolGroups - description: '' + 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 @@ -1147,10 +1167,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolGroups - description: Unregister a tool group + description: Unregister a tool group. parameters: - name: toolgroup_id in: path + description: The ID of the tool group to unregister. required: true schema: type: string @@ -1158,7 +1179,7 @@ paths: get: responses: '200': - description: OK + description: A Trace. content: application/json: schema: @@ -1175,10 +1196,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + 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 @@ -1186,7 +1208,7 @@ paths: get: responses: '200': - description: OK + description: A PostTrainingJobArtifactsResponse. content: application/json: schema: @@ -1203,10 +1225,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - PostTraining (Coming Soon) - description: '' + 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 @@ -1214,7 +1238,7 @@ paths: get: responses: '200': - description: OK + description: A PostTrainingJobStatusResponse. content: application/json: schema: @@ -1231,10 +1255,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - PostTraining (Coming Soon) - description: '' + 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 @@ -1242,7 +1268,7 @@ paths: get: responses: '200': - description: OK + description: A ListPostTrainingJobsResponse. content: application/json: schema: @@ -1259,13 +1285,13 @@ paths: $ref: '#/components/responses/DefaultError' tags: - PostTraining (Coming Soon) - description: '' + description: Get all training jobs. parameters: [] /v1/files/session:{upload_id}: get: responses: '200': - description: OK + description: A FileUploadResponse. content: application/json: schema: @@ -1283,18 +1309,19 @@ paths: tags: - Files description: >- - Returns information about an existsing upload session + Returns information about an existsing upload session. parameters: - name: upload_id in: path - description: ID of the upload session + description: ID of the upload session. required: true schema: type: string post: responses: '200': - description: OK + description: >- + A FileResponse or None if the upload is not complete. content: application/json: schema: @@ -1319,7 +1346,7 @@ paths: parameters: - name: upload_id in: path - description: ID of the upload session + description: ID of the upload session. required: true schema: type: string @@ -1334,7 +1361,7 @@ paths: get: responses: '200': - description: OK + description: A VectorDB. content: application/json: schema: @@ -1351,10 +1378,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - VectorDBs - description: '' + 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 @@ -1374,10 +1403,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - VectorDBs - description: '' + 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 @@ -1385,7 +1416,7 @@ paths: get: responses: '200': - description: OK + description: A HealthInfo. content: application/json: schema: @@ -1402,7 +1433,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Inspect - description: '' + description: Get the health of the service. parameters: [] /v1/tool-runtime/rag-tool/insert: post: @@ -1447,7 +1478,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - VectorIO - description: '' + description: Insert chunks into a vector database. parameters: [] requestBody: content: @@ -1459,7 +1490,8 @@ paths: get: responses: '200': - description: OK + description: >- + A ProviderInfo object containing the provider's details. content: application/json: schema: @@ -1476,10 +1508,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Providers - description: '' + 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 @@ -1487,7 +1521,7 @@ paths: post: responses: '200': - description: OK + description: A ToolInvocationResult. content: application/json: schema: @@ -1504,7 +1538,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolRuntime - description: Run a tool with the given arguments + description: Run a tool with the given arguments. parameters: [] requestBody: content: @@ -1516,7 +1550,7 @@ paths: get: responses: '200': - description: OK + description: A PaginatedResponse. content: application/json: schema: @@ -1545,9 +1579,9 @@ paths: The response includes: - - data: List of items for the current page + - data: List of items for the current page. - - has_more: Whether there are more items available after this set + - has_more: Whether there are more items available after this set. parameters: - name: dataset_id in: path @@ -1573,7 +1607,7 @@ paths: get: responses: '200': - description: The status of the evaluationjob. + description: The status of the evaluation job. content: application/json: schema: @@ -1718,7 +1752,7 @@ paths: get: responses: '200': - description: OK + description: A ListBenchmarksResponse. content: application/json: schema: @@ -1735,7 +1769,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Benchmarks - description: '' + description: List all benchmarks. parameters: [] post: responses: @@ -1753,7 +1787,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Benchmarks - description: '' + description: Register a benchmark. parameters: [] requestBody: content: @@ -1765,7 +1799,7 @@ paths: get: responses: '200': - description: OK + description: A ListDatasetsResponse. content: application/json: schema: @@ -1782,12 +1816,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Datasets - description: '' + description: List all datasets. parameters: [] post: responses: '200': - description: OK + description: A Dataset. content: application/json: schema: @@ -1816,7 +1850,7 @@ paths: get: responses: '200': - description: OK + description: A ListFileResponse. content: application/json: schema: @@ -1837,7 +1871,7 @@ paths: parameters: - name: bucket in: path - description: 'Bucket name (valid chars: a-zA-Z0-9_-)' + description: 'Bucket name (valid chars: a-zA-Z0-9_-).' required: true schema: type: string @@ -1845,7 +1879,7 @@ paths: get: responses: '200': - description: OK + description: A ListModelsResponse. content: application/json: schema: @@ -1862,12 +1896,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Models - description: '' + description: List all models. parameters: [] post: responses: '200': - description: OK + description: A Model. content: application/json: schema: @@ -1884,7 +1918,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Models - description: '' + description: Register a model. parameters: [] requestBody: content: @@ -1896,7 +1930,8 @@ paths: get: responses: '200': - description: OK + description: >- + A ListProvidersResponse containing information about all providers. content: application/json: schema: @@ -1913,13 +1948,13 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Providers - description: '' + description: List all available providers. parameters: [] /v1/inspect/routes: get: responses: '200': - description: OK + description: A ListRoutesResponse. content: application/json: schema: @@ -1936,13 +1971,13 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Inspect - description: '' + description: List all routes. parameters: [] /v1/tool-runtime/list-tools: get: responses: '200': - description: OK + description: A ListToolDefsResponse. content: application/json: schema: @@ -1959,15 +1994,19 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolRuntime - description: '' + 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' @@ -1975,7 +2014,7 @@ paths: get: responses: '200': - description: OK + description: A ListScoringFunctionsResponse. content: application/json: schema: @@ -1992,7 +2031,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ScoringFunctions - description: '' + description: List all scoring functions. parameters: [] post: responses: @@ -2010,7 +2049,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ScoringFunctions - description: '' + description: Register a scoring function. parameters: [] requestBody: content: @@ -2022,7 +2061,7 @@ paths: get: responses: '200': - description: OK + description: A ListShieldsResponse. content: application/json: schema: @@ -2039,12 +2078,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Shields - description: '' + description: List all shields. parameters: [] post: responses: '200': - description: OK + description: A Shield. content: application/json: schema: @@ -2061,7 +2100,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Shields - description: '' + description: Register a shield. parameters: [] requestBody: content: @@ -2073,7 +2112,7 @@ paths: get: responses: '200': - description: OK + description: A ListToolGroupsResponse. content: application/json: schema: @@ -2090,7 +2129,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolGroups - description: List tool groups with optional provider + description: List tool groups with optional provider. parameters: [] post: responses: @@ -2108,7 +2147,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolGroups - description: Register a tool group + description: Register a tool group. parameters: [] requestBody: content: @@ -2120,7 +2159,7 @@ paths: get: responses: '200': - description: OK + description: A ListToolsResponse. content: application/json: schema: @@ -2137,10 +2176,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - ToolGroups - description: List tools with optional tool group + description: List tools with optional tool group. parameters: - name: toolgroup_id in: query + description: >- + The ID of the tool group to list tools for. required: false schema: type: string @@ -2148,7 +2189,7 @@ paths: get: responses: '200': - description: OK + description: A ListVectorDBsResponse. content: application/json: schema: @@ -2165,12 +2206,12 @@ paths: $ref: '#/components/responses/DefaultError' tags: - VectorDBs - description: '' + description: List all vector databases. parameters: [] post: responses: '200': - description: OK + description: A VectorDB. content: application/json: schema: @@ -2187,7 +2228,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - VectorDBs - description: '' + description: Register a vector database. parameters: [] requestBody: content: @@ -2212,7 +2253,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + description: Log an event. parameters: [] requestBody: content: @@ -2224,9 +2265,7 @@ paths: post: responses: '200': - description: >- - Response from an OpenAI-compatible chat completion request. **OR** Chunk - from a streaming response to an OpenAI-compatible chat completion request. + description: An OpenAIChatCompletion. content: application/json: schema: @@ -2259,7 +2298,7 @@ paths: post: responses: '200': - description: OK + description: An OpenAICompletion. content: application/json: schema: @@ -2290,7 +2329,7 @@ paths: get: responses: '200': - description: OK + description: A OpenAIListModelsResponse. content: application/json: schema: @@ -2307,13 +2346,13 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Models - description: '' + description: List models using the OpenAI API. parameters: [] /v1/post-training/preference-optimize: post: responses: '200': - description: OK + description: A PostTrainingJob. content: application/json: schema: @@ -2330,7 +2369,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - PostTraining (Coming Soon) - description: '' + description: Run preference optimization of a model. parameters: [] requestBody: content: @@ -2372,7 +2411,7 @@ paths: post: responses: '200': - description: OK + description: A QueryChunksResponse. content: application/json: schema: @@ -2389,7 +2428,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - VectorIO - description: '' + description: Query chunks from a vector database. parameters: [] requestBody: content: @@ -2401,7 +2440,7 @@ paths: post: responses: '200': - description: OK + description: A QueryMetricsResponse. content: application/json: schema: @@ -2418,10 +2457,11 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + description: Query metrics. parameters: - name: metric_name in: path + description: The name of the metric to query. required: true schema: type: string @@ -2435,7 +2475,7 @@ paths: post: responses: '200': - description: OK + description: A QuerySpansResponse. content: application/json: schema: @@ -2452,7 +2492,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + description: Query spans. parameters: [] requestBody: content: @@ -2464,7 +2504,7 @@ paths: post: responses: '200': - description: OK + description: A QueryTracesResponse. content: application/json: schema: @@ -2481,7 +2521,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + description: Query traces. parameters: [] requestBody: content: @@ -2587,7 +2627,7 @@ paths: post: responses: '200': - description: OK + description: A RunShieldResponse. content: application/json: schema: @@ -2604,7 +2644,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Safety - description: '' + description: Run a shield. parameters: [] requestBody: content: @@ -2629,7 +2669,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Telemetry - description: '' + description: Save spans to a dataset. parameters: [] requestBody: content: @@ -2642,7 +2682,7 @@ paths: responses: '200': description: >- - ScoreResponse object containing rows and aggregated results + A ScoreResponse object containing rows and aggregated results. content: application/json: schema: @@ -2671,7 +2711,7 @@ paths: post: responses: '200': - description: OK + description: A ScoreBatchResponse. content: application/json: schema: @@ -2688,7 +2728,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Scoring - description: '' + description: Score a batch of rows. parameters: [] requestBody: content: @@ -2700,7 +2740,7 @@ paths: post: responses: '200': - description: OK + description: A PostTrainingJob. content: application/json: schema: @@ -2717,7 +2757,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - PostTraining (Coming Soon) - description: '' + description: Run supervised fine-tuning of a model. parameters: [] requestBody: content: @@ -2758,7 +2798,7 @@ paths: get: responses: '200': - description: OK + description: A VersionInfo. content: application/json: schema: @@ -2775,7 +2815,7 @@ paths: $ref: '#/components/responses/DefaultError' tags: - Inspect - description: '' + description: Get the version of the service. parameters: [] jsonSchemaDialect: >- https://json-schema.org/draft/2020-12/schema @@ -2824,6 +2864,7 @@ components: - type: string - type: array - type: object + description: The rows to append to the dataset. additionalProperties: false required: - rows @@ -3328,22 +3369,34 @@ components: 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: @@ -3353,7 +3406,9 @@ components: description: >- How many tokens (for each position) to return log probabilities for. additionalProperties: false - title: LogProbConfig + description: >- + (Optional) If specified, log probabilities for each token position will + be returned. additionalProperties: false required: - model_id @@ -3426,14 +3481,22 @@ components: 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: @@ -3443,7 +3506,9 @@ components: description: >- How many tokens (for each position) to return log probabilities for. additionalProperties: false - title: LogProbConfig + description: >- + (Optional) If specified, log probabilities for each token position will + be returned. additionalProperties: false required: - model_id @@ -3494,6 +3559,7 @@ components: properties: job_uuid: type: string + description: The UUID of the job to cancel. additionalProperties: false required: - job_uuid @@ -3510,17 +3576,17 @@ components: type: array items: $ref: '#/components/schemas/Message' - description: List of messages in the conversation + description: List of messages in the conversation. sampling_params: $ref: '#/components/schemas/SamplingParams' description: >- - Parameters to control the sampling strategy + Parameters to control the sampling strategy. tools: type: array items: $ref: '#/components/schemas/ToolDefinition' description: >- - (Optional) List of tool definitions available to the model + (Optional) List of tool definitions available to the model. tool_choice: type: string enum: @@ -3703,15 +3769,16 @@ components: Llama Stack and available via the /models endpoint. content: $ref: '#/components/schemas/InterleavedContent' - description: The content to generate a completion for + description: >- + The content to generate a completion for. sampling_params: $ref: '#/components/schemas/SamplingParams' description: >- - (Optional) Parameters to control the sampling strategy + (Optional) Parameters to control the sampling strategy. response_format: $ref: '#/components/schemas/ResponseFormat' description: >- - (Optional) Grammar specification for guided (structured) decoding + (Optional) Grammar specification for guided (structured) decoding. stream: type: boolean description: >- @@ -4939,17 +5006,17 @@ components: bucket: type: string description: >- - Bucket under which the file is stored (valid chars: a-zA-Z0-9_-) + Bucket under which the file is stored (valid chars: a-zA-Z0-9_-). key: type: string description: >- - Key under which the file is stored (valid chars: a-zA-Z0-9_-/.) + Key under which the file is stored (valid chars: a-zA-Z0-9_-/.). mime_type: type: string - description: MIME type of the file + description: MIME type of the file. size: type: integer - description: File size in bytes + description: File size in bytes. additionalProperties: false required: - bucket @@ -5869,8 +5936,10 @@ components: 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: @@ -6234,6 +6303,8 @@ components: properties: vector_db_id: type: string + description: >- + The identifier of the vector database to insert the chunks into. chunks: type: array items: @@ -6256,8 +6327,10 @@ components: - content - metadata title: Chunk + description: The chunks to insert. ttl_seconds: type: integer + description: The time to live of the chunks. additionalProperties: false required: - vector_db_id @@ -6305,6 +6378,7 @@ components: properties: tool_name: type: string + description: The name of the tool to invoke. kwargs: type: object additionalProperties: @@ -6315,6 +6389,8 @@ components: - type: string - type: array - type: object + description: >- + A dictionary of arguments to pass to the tool. additionalProperties: false required: - tool_name @@ -6750,8 +6826,10 @@ components: 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 @@ -7077,11 +7155,11 @@ components: type: array items: $ref: '#/components/schemas/OpenAIMessageParam' - description: List of messages in the conversation + description: List of messages in the conversation. frequency_penalty: type: number description: >- - (Optional) The penalty for repeated tokens + (Optional) The penalty for repeated tokens. function_call: oneOf: - type: string @@ -7094,7 +7172,7 @@ components: - type: string - type: array - type: object - description: (Optional) The function call to use + description: (Optional) The function call to use. functions: type: array items: @@ -7107,52 +7185,52 @@ components: - type: string - type: array - type: object - description: (Optional) List of functions to use + description: (Optional) List of functions to use. logit_bias: type: object additionalProperties: type: number - description: (Optional) The logit bias to use + description: (Optional) The logit bias to use. logprobs: type: boolean - description: (Optional) The log probabilities to use + description: (Optional) The log probabilities to use. max_completion_tokens: type: integer description: >- - (Optional) The maximum number of tokens to generate + (Optional) The maximum number of tokens to generate. max_tokens: type: integer description: >- - (Optional) The maximum number of tokens to generate + (Optional) The maximum number of tokens to generate. n: type: integer description: >- - (Optional) The number of completions to generate + (Optional) The number of completions to generate. parallel_tool_calls: type: boolean description: >- - (Optional) Whether to parallelize tool calls + (Optional) Whether to parallelize tool calls. presence_penalty: type: number description: >- - (Optional) The penalty for repeated tokens + (Optional) The penalty for repeated tokens. response_format: $ref: '#/components/schemas/OpenAIResponseFormatParam' - description: (Optional) The response format to use + description: (Optional) The response format to use. seed: type: integer - description: (Optional) The seed to use + description: (Optional) The seed to use. stop: oneOf: - type: string - type: array items: type: string - description: (Optional) The stop tokens to use + description: (Optional) The stop tokens to use. stream: type: boolean description: >- - (Optional) Whether to stream the response + (Optional) Whether to stream the response. stream_options: type: object additionalProperties: @@ -7163,10 +7241,10 @@ components: - type: string - type: array - type: object - description: (Optional) The stream options to use + description: (Optional) The stream options to use. temperature: type: number - description: (Optional) The temperature to use + description: (Optional) The temperature to use. tool_choice: oneOf: - type: string @@ -7179,7 +7257,7 @@ components: - type: string - type: array - type: object - description: (Optional) The tool choice to use + description: (Optional) The tool choice to use. tools: type: array items: @@ -7192,17 +7270,17 @@ components: - type: string - type: array - type: object - description: (Optional) The tools to use + description: (Optional) The tools to use. top_logprobs: type: integer description: >- - (Optional) The top log probabilities to use + (Optional) The top log probabilities to use. top_p: type: number - description: (Optional) The top p to use + description: (Optional) The top p to use. user: type: string - description: (Optional) The user to use + description: (Optional) The user to use. additionalProperties: false required: - model @@ -7432,52 +7510,52 @@ components: type: array items: type: integer - description: The prompt to generate a completion for + description: The prompt to generate a completion for. best_of: type: integer description: >- - (Optional) The number of completions to generate + (Optional) The number of completions to generate. echo: type: boolean - description: (Optional) Whether to echo the prompt + description: (Optional) Whether to echo the prompt. frequency_penalty: type: number description: >- - (Optional) The penalty for repeated tokens + (Optional) The penalty for repeated tokens. logit_bias: type: object additionalProperties: type: number - description: (Optional) The logit bias to use + description: (Optional) The logit bias to use. logprobs: type: boolean - description: (Optional) The log probabilities to use + description: (Optional) The log probabilities to use. max_tokens: type: integer description: >- - (Optional) The maximum number of tokens to generate + (Optional) The maximum number of tokens to generate. n: type: integer description: >- - (Optional) The number of completions to generate + (Optional) The number of completions to generate. presence_penalty: type: number description: >- - (Optional) The penalty for repeated tokens + (Optional) The penalty for repeated tokens. seed: type: integer - description: (Optional) The seed to use + description: (Optional) The seed to use. stop: oneOf: - type: string - type: array items: type: string - description: (Optional) The stop tokens to use + description: (Optional) The stop tokens to use. stream: type: boolean description: >- - (Optional) Whether to stream the response + (Optional) Whether to stream the response. stream_options: type: object additionalProperties: @@ -7488,16 +7566,16 @@ components: - type: string - type: array - type: object - description: (Optional) The stream options to use + description: (Optional) The stream options to use. temperature: type: number - description: (Optional) The temperature to use + description: (Optional) The temperature to use. top_p: type: number - description: (Optional) The top p to use + description: (Optional) The top p to use. user: type: string - description: (Optional) The user to use + description: (Optional) The user to use. guided_choice: type: array items: @@ -7713,12 +7791,16 @@ components: 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: @@ -7729,6 +7811,7 @@ components: - type: string - type: array - type: object + description: The hyperparam search configuration. logger_config: type: object additionalProperties: @@ -7739,6 +7822,7 @@ components: - type: string - type: array - type: object + description: The logger configuration. additionalProperties: false required: - job_uuid @@ -7874,8 +7958,11 @@ components: 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: @@ -7886,6 +7973,7 @@ components: - type: string - type: array - type: object + description: The parameters of the query. additionalProperties: false required: - vector_db_id @@ -7930,16 +8018,19 @@ components: 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 - title: MetricQueryType + description: The type of query to perform. label_matchers: type: array items: @@ -7964,6 +8055,8 @@ components: - value - operator title: MetricLabelMatcher + description: >- + The label matchers to apply to the metric. additionalProperties: false required: - start_time @@ -8059,12 +8152,16 @@ components: 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 @@ -8088,14 +8185,19 @@ components: 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: @@ -8114,16 +8216,25 @@ components: 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: @@ -8134,6 +8245,7 @@ components: - type: string - type: array - type: object + description: The metadata to use for the benchmark. additionalProperties: false required: - benchmark_id @@ -8150,7 +8262,7 @@ components: - eval/question-answer - eval/messages-answer description: >- - The purpose of the dataset. One of - "post-training/messages": The dataset + 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 @@ -8183,7 +8295,7 @@ components: - type: array - type: object description: >- - The metadata for the dataset. - E.g. {"description": "My dataset"} + The metadata for the dataset. - E.g. {"description": "My dataset"}. dataset_id: type: string description: >- @@ -8198,10 +8310,14 @@ components: 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: @@ -8212,8 +8328,10 @@ components: - 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 @@ -8223,16 +8341,27 @@ components: 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 @@ -8244,10 +8373,15 @@ components: 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: @@ -8258,6 +8392,7 @@ components: - type: string - type: array - type: object + description: The parameters of the shield. additionalProperties: false required: - shield_id @@ -8267,10 +8402,15 @@ components: 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: @@ -8281,6 +8421,8 @@ components: - type: string - type: array - type: object + description: >- + A dictionary of arguments to pass to the tool group. additionalProperties: false required: - toolgroup_id @@ -8291,14 +8433,21 @@ components: 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. provider_vector_db_id: type: string + description: >- + The identifier of the vector database in the provider. additionalProperties: false required: - vector_db_id @@ -8335,10 +8484,12 @@ components: 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: @@ -8349,6 +8500,7 @@ components: - type: string - type: array - type: object + description: The parameters of the shield. additionalProperties: false required: - shield_id @@ -8369,14 +8521,20 @@ components: 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 @@ -8431,14 +8589,19 @@ components: 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 @@ -8523,8 +8686,10 @@ components: 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: @@ -8535,6 +8700,7 @@ components: - type: string - type: array - type: object + description: The hyperparam search configuration. logger_config: type: object additionalProperties: @@ -8545,12 +8711,16 @@ components: - 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 diff --git a/docs/openapi_generator/pyopenapi/utility.py b/docs/openapi_generator/pyopenapi/utility.py index 9bd3cd2dd..12a69050c 100644 --- a/docs/openapi_generator/pyopenapi/utility.py +++ b/docs/openapi_generator/pyopenapi/utility.py @@ -179,6 +179,35 @@ def _validate_has_ellipsis(method) -> str | None: if "..." not in source and not "NotImplementedError" in source: return "does not contain ellipsis (...) in its implementation" +def _validate_has_return_in_docstring(method) -> str | None: + source = inspect.getsource(method) + return_type = method.__annotations__.get('return') + if return_type is not None and return_type != type(None) and ":returns:" not in source: + return "does not have a ':returns:' in its docstring" + +def _validate_has_params_in_docstring(method) -> str | None: + source = inspect.getsource(method) + sig = inspect.signature(method) + # Only check if the method has more than one parameter + if len(sig.parameters) > 1 and ":param" not in source: + return "does not have a ':param' in its docstring" + +def _validate_has_no_return_none_in_docstring(method) -> str | None: + source = inspect.getsource(method) + return_type = method.__annotations__.get('return') + if return_type is None and ":returns: None" in source: + return "has a ':returns: None' in its docstring which is redundant for None-returning functions" + +def _validate_docstring_lines_end_with_dot(method) -> str | None: + docstring = inspect.getdoc(method) + if docstring is None: + return None + + lines = docstring.split('\n') + for line in lines: + line = line.strip() + if line and not any(line.endswith(char) for char in '.:{}[]()",'): + return f"docstring line '{line}' does not end with a valid character: . : {{ }} [ ] ( ) , \"" _VALIDATORS = { "GET": [ @@ -186,13 +215,23 @@ _VALIDATORS = { _validate_list_parameters_contain_data, _validate_api_method_doesnt_return_list, _validate_has_ellipsis, + _validate_has_return_in_docstring, + _validate_has_params_in_docstring, + _validate_docstring_lines_end_with_dot, ], "DELETE": [ _validate_api_delete_method_returns_none, _validate_has_ellipsis, + _validate_has_return_in_docstring, + _validate_has_params_in_docstring, + _validate_has_no_return_none_in_docstring ], "POST": [ _validate_has_ellipsis, + _validate_has_return_in_docstring, + _validate_has_params_in_docstring, + _validate_has_no_return_none_in_docstring, + _validate_docstring_lines_end_with_dot, ], } diff --git a/llama_stack/apis/agents/agents.py b/llama_stack/apis/agents/agents.py index 2a37f27c0..b2f85336c 100644 --- a/llama_stack/apis/agents/agents.py +++ b/llama_stack/apis/agents/agents.py @@ -413,7 +413,7 @@ class Agents(Protocol): :param toolgroups: (Optional) List of toolgroups to create the turn with, will be used in addition to the agent's config toolgroups for the request. :param tool_config: (Optional) The tool configuration to create the turn with, will be used to override the agent's tool_config. :returns: If stream=False, returns a Turn object. - If stream=True, returns an SSE event stream of AgentTurnResponseStreamChunk + If stream=True, returns an SSE event stream of AgentTurnResponseStreamChunk. """ ... @@ -509,6 +509,7 @@ class Agents(Protocol): :param session_id: The ID of the session to get. :param agent_id: The ID of the agent to get the session for. :param turn_ids: (Optional) List of turn IDs to filter the session by. + :returns: A Session. """ ... @@ -606,5 +607,6 @@ class Agents(Protocol): :param input: Input message(s) to create the response. :param model: The underlying LLM used for completions. :param previous_response_id: (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. + :returns: An OpenAIResponseObject. """ ... diff --git a/llama_stack/apis/batch_inference/batch_inference.py b/llama_stack/apis/batch_inference/batch_inference.py index 79bc73e4c..b2aa637e2 100644 --- a/llama_stack/apis/batch_inference/batch_inference.py +++ b/llama_stack/apis/batch_inference/batch_inference.py @@ -38,7 +38,17 @@ class BatchInference(Protocol): sampling_params: SamplingParams | None = None, response_format: ResponseFormat | None = None, logprobs: LogProbConfig | None = None, - ) -> Job: ... + ) -> Job: + """Generate completions for a batch of content. + + :param model: The model to use for the completion. + :param content_batch: The content to complete. + :param sampling_params: The sampling parameters to use for the completion. + :param response_format: The response format to use for the completion. + :param logprobs: The logprobs to use for the completion. + :returns: A job for the completion. + """ + ... @webmethod(route="/batch-inference/chat-completion", method="POST") async def chat_completion( @@ -52,4 +62,17 @@ class BatchInference(Protocol): tool_prompt_format: ToolPromptFormat | None = None, response_format: ResponseFormat | None = None, logprobs: LogProbConfig | None = None, - ) -> Job: ... + ) -> Job: + """Generate chat completions for a batch of messages. + + :param model: The model to use for the chat completion. + :param messages_batch: The messages to complete. + :param sampling_params: The sampling parameters to use for the completion. + :param tools: The tools to use for the chat completion. + :param tool_choice: The tool choice to use for the chat completion. + :param tool_prompt_format: The tool prompt format to use for the chat completion. + :param response_format: The response format to use for the chat completion. + :param logprobs: The logprobs to use for the chat completion. + :returns: A job for the chat completion. + """ + ... diff --git a/llama_stack/apis/benchmarks/benchmarks.py b/llama_stack/apis/benchmarks/benchmarks.py index e3b0502bc..d80c767f8 100644 --- a/llama_stack/apis/benchmarks/benchmarks.py +++ b/llama_stack/apis/benchmarks/benchmarks.py @@ -46,13 +46,24 @@ class ListBenchmarksResponse(BaseModel): @runtime_checkable class Benchmarks(Protocol): @webmethod(route="/eval/benchmarks", method="GET") - async def list_benchmarks(self) -> ListBenchmarksResponse: ... + async def list_benchmarks(self) -> ListBenchmarksResponse: + """List all benchmarks. + + :returns: A ListBenchmarksResponse. + """ + ... @webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET") async def get_benchmark( self, benchmark_id: str, - ) -> Benchmark: ... + ) -> Benchmark: + """Get a benchmark by its ID. + + :param benchmark_id: The ID of the benchmark to get. + :returns: A Benchmark. + """ + ... @webmethod(route="/eval/benchmarks", method="POST") async def register_benchmark( @@ -63,4 +74,14 @@ class Benchmarks(Protocol): provider_benchmark_id: str | None = None, provider_id: str | None = None, metadata: dict[str, Any] | None = None, - ) -> None: ... + ) -> None: + """Register a benchmark. + + :param benchmark_id: The ID of the benchmark to register. + :param dataset_id: The ID of the dataset to use for the benchmark. + :param scoring_functions: The scoring functions to use for the benchmark. + :param provider_benchmark_id: The ID of the provider benchmark to use for the benchmark. + :param provider_id: The ID of the provider to use for the benchmark. + :param metadata: The metadata to use for the benchmark. + """ + ... diff --git a/llama_stack/apis/datasetio/datasetio.py b/llama_stack/apis/datasetio/datasetio.py index 6d160a043..1183983cc 100644 --- a/llama_stack/apis/datasetio/datasetio.py +++ b/llama_stack/apis/datasetio/datasetio.py @@ -34,14 +34,21 @@ class DatasetIO(Protocol): - 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 + - data: List of items for the current page. + - has_more: Whether there are more items available after this set. :param dataset_id: The ID of the dataset to get the rows from. :param start_index: Index into dataset for the first row to get. Get all rows if None. :param limit: The number of rows to get. + :returns: A PaginatedResponse. """ ... @webmethod(route="/datasetio/append-rows/{dataset_id:path}", method="POST") - async def append_rows(self, dataset_id: str, rows: list[dict[str, Any]]) -> None: ... + async def append_rows(self, dataset_id: str, rows: list[dict[str, Any]]) -> None: + """Append rows to a dataset. + + :param dataset_id: The ID of the dataset to append the rows to. + :param rows: The rows to append to the dataset. + """ + ... diff --git a/llama_stack/apis/datasets/datasets.py b/llama_stack/apis/datasets/datasets.py index a0ee987ad..e3de3d5cb 100644 --- a/llama_stack/apis/datasets/datasets.py +++ b/llama_stack/apis/datasets/datasets.py @@ -137,7 +137,8 @@ class Datasets(Protocol): """ Register a new dataset. - :param purpose: The purpose of the dataset. One of + :param purpose: The purpose of the dataset. + One of: - "post-training/messages": The dataset contains a messages column with list of messages for post-training. { "messages": [ @@ -188,8 +189,9 @@ class Datasets(Protocol): ] } :param metadata: The metadata for the dataset. - - E.g. {"description": "My dataset"} + - E.g. {"description": "My dataset"}. :param dataset_id: The ID of the dataset. If not provided, an ID will be generated. + :returns: A Dataset. """ ... @@ -197,13 +199,29 @@ class Datasets(Protocol): async def get_dataset( self, dataset_id: str, - ) -> Dataset: ... + ) -> Dataset: + """Get a dataset by its ID. + + :param dataset_id: The ID of the dataset to get. + :returns: A Dataset. + """ + ... @webmethod(route="/datasets", method="GET") - async def list_datasets(self) -> ListDatasetsResponse: ... + async def list_datasets(self) -> ListDatasetsResponse: + """List all datasets. + + :returns: A ListDatasetsResponse. + """ + ... @webmethod(route="/datasets/{dataset_id:path}", method="DELETE") async def unregister_dataset( self, dataset_id: str, - ) -> None: ... + ) -> None: + """Unregister a dataset by its ID. + + :param dataset_id: The ID of the dataset to unregister. + """ + ... diff --git a/llama_stack/apis/eval/eval.py b/llama_stack/apis/eval/eval.py index 38699d3f5..83a0a8e56 100644 --- a/llama_stack/apis/eval/eval.py +++ b/llama_stack/apis/eval/eval.py @@ -93,7 +93,7 @@ class Eval(Protocol): :param benchmark_id: The ID of the benchmark to run the evaluation on. :param benchmark_config: The configuration for the benchmark. - :return: The job that was created to run the evaluation. + :returns: The job that was created to run the evaluation. """ ... @@ -111,7 +111,7 @@ class Eval(Protocol): :param input_rows: The rows to evaluate. :param scoring_functions: The scoring functions to use for the evaluation. :param benchmark_config: The configuration for the benchmark. - :return: EvaluateResponse object containing generations and scores + :returns: EvaluateResponse object containing generations and scores. """ ... @@ -121,7 +121,7 @@ class Eval(Protocol): :param benchmark_id: The ID of the benchmark to run the evaluation on. :param job_id: The ID of the job to get the status of. - :return: The status of the evaluationjob. + :returns: The status of the evaluation job. """ ... @@ -140,6 +140,6 @@ class Eval(Protocol): :param benchmark_id: The ID of the benchmark to run the evaluation on. :param job_id: The ID of the job to get the result of. - :return: The result of the job. + :returns: The result of the job. """ ... diff --git a/llama_stack/apis/files/files.py b/llama_stack/apis/files/files.py index 4a9b49978..1d762a68a 100644 --- a/llama_stack/apis/files/files.py +++ b/llama_stack/apis/files/files.py @@ -91,10 +91,11 @@ class Files(Protocol): """ Create a new upload session for a file identified by a bucket and key. - :param bucket: Bucket under which the file is stored (valid chars: a-zA-Z0-9_-) - :param key: Key under which the file is stored (valid chars: a-zA-Z0-9_-/.) - :param mime_type: MIME type of the file - :param size: File size in bytes + :param bucket: Bucket under which the file is stored (valid chars: a-zA-Z0-9_-). + :param key: Key under which the file is stored (valid chars: a-zA-Z0-9_-/.). + :param mime_type: MIME type of the file. + :param size: File size in bytes. + :returns: A FileUploadResponse. """ ... @@ -107,7 +108,8 @@ class Files(Protocol): Upload file content to an existing upload session. On the server, request body will have the raw bytes that are uploaded. - :param upload_id: ID of the upload session + :param upload_id: ID of the upload session. + :returns: A FileResponse or None if the upload is not complete. """ ... @@ -117,9 +119,10 @@ class Files(Protocol): upload_id: str, ) -> FileUploadResponse: """ - Returns information about an existsing upload session + Returns information about an existsing upload session. - :param upload_id: ID of the upload session + :param upload_id: ID of the upload session. + :returns: A FileUploadResponse. """ ... @@ -130,6 +133,9 @@ class Files(Protocol): ) -> ListBucketResponse: """ List all buckets. + + :param bucket: Bucket name (valid chars: a-zA-Z0-9_-). + :returns: A ListBucketResponse. """ ... @@ -141,7 +147,8 @@ class Files(Protocol): """ List all files in a bucket. - :param bucket: Bucket name (valid chars: a-zA-Z0-9_-) + :param bucket: Bucket name (valid chars: a-zA-Z0-9_-). + :returns: A ListFileResponse. """ ... @@ -154,8 +161,9 @@ class Files(Protocol): """ Get a file info identified by a bucket and key. - :param bucket: Bucket name (valid chars: a-zA-Z0-9_-) - :param key: Key under which the file is stored (valid chars: a-zA-Z0-9_-/.) + :param bucket: Bucket name (valid chars: a-zA-Z0-9_-). + :param key: Key under which the file is stored (valid chars: a-zA-Z0-9_-/.). + :returns: A FileResponse. """ ... @@ -168,7 +176,7 @@ class Files(Protocol): """ Delete a file identified by a bucket and key. - :param bucket: Bucket name (valid chars: a-zA-Z0-9_-) - :param key: Key under which the file is stored (valid chars: a-zA-Z0-9_-/.) + :param bucket: Bucket name (valid chars: a-zA-Z0-9_-). + :param key: Key under which the file is stored (valid chars: a-zA-Z0-9_-/.). """ ... diff --git a/llama_stack/apis/inference/inference.py b/llama_stack/apis/inference/inference.py index 00050779b..3c91b5a6e 100644 --- a/llama_stack/apis/inference/inference.py +++ b/llama_stack/apis/inference/inference.py @@ -845,13 +845,13 @@ class Inference(Protocol): """Generate a completion for the given content using the specified model. :param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint. - :param content: The content to generate a completion for - :param sampling_params: (Optional) Parameters to control the sampling strategy - :param response_format: (Optional) Grammar specification for guided (structured) decoding + :param content: The content to generate a completion for. + :param sampling_params: (Optional) Parameters to control the sampling strategy. + :param response_format: (Optional) Grammar specification for guided (structured) decoding. :param stream: (Optional) If True, generate an SSE event stream of the response. Defaults to False. :param logprobs: (Optional) If specified, log probabilities for each token position will be returned. :returns: If stream=False, returns a CompletionResponse with the full completion. - If stream=True, returns an SSE event stream of CompletionResponseStreamChunk + If stream=True, returns an SSE event stream of CompletionResponseStreamChunk. """ ... @@ -864,6 +864,15 @@ class Inference(Protocol): response_format: ResponseFormat | None = None, logprobs: LogProbConfig | None = None, ) -> BatchCompletionResponse: + """Generate completions for a batch of content using the specified model. + + :param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint. + :param content_batch: The content to generate completions for. + :param sampling_params: (Optional) Parameters to control the sampling strategy. + :param response_format: (Optional) Grammar specification for guided (structured) decoding. + :param logprobs: (Optional) If specified, log probabilities for each token position will be returned. + :returns: A BatchCompletionResponse with the full completions. + """ raise NotImplementedError("Batch completion is not implemented") @webmethod(route="/inference/chat-completion", method="POST") @@ -883,9 +892,9 @@ class Inference(Protocol): """Generate a chat completion for the given messages using the specified model. :param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint. - :param messages: List of messages in the conversation - :param sampling_params: Parameters to control the sampling strategy - :param tools: (Optional) List of tool definitions available to the model + :param messages: List of messages in the conversation. + :param sampling_params: Parameters to control the sampling strategy. + :param tools: (Optional) List of tool definitions available to the model. :param tool_choice: (Optional) Whether tool use is required or automatic. Defaults to ToolChoice.auto. .. deprecated:: Use tool_config instead. @@ -902,7 +911,7 @@ class Inference(Protocol): :param logprobs: (Optional) If specified, log probabilities for each token position will be returned. :param tool_config: (Optional) Configuration for tool use. :returns: If stream=False, returns a ChatCompletionResponse with the full completion. - If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk + If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk. """ ... @@ -917,6 +926,17 @@ class Inference(Protocol): response_format: ResponseFormat | None = None, logprobs: LogProbConfig | None = None, ) -> BatchChatCompletionResponse: + """Generate chat completions for a batch of messages using the specified model. + + :param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint. + :param messages_batch: The messages to generate completions for. + :param sampling_params: (Optional) Parameters to control the sampling strategy. + :param tools: (Optional) List of tool definitions available to the model. + :param tool_config: (Optional) Configuration for tool use. + :param response_format: (Optional) Grammar specification for guided (structured) decoding. + :param logprobs: (Optional) If specified, log probabilities for each token position will be returned. + :returns: A BatchChatCompletionResponse with the full completions. + """ raise NotImplementedError("Batch chat completion is not implemented") @webmethod(route="/inference/embeddings", method="POST") @@ -935,7 +955,7 @@ class Inference(Protocol): :param output_dimension: (Optional) Output dimensionality for the embeddings. Only supported by Matryoshka models. :param text_truncation: (Optional) Config for how to truncate text for embedding when text is longer than the model's max sequence length. :param task_type: (Optional) How is the embedding being used? This is only supported by asymmetric embedding models. - :returns: 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} + :returns: 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}. """ ... @@ -967,22 +987,23 @@ class Inference(Protocol): """Generate an OpenAI-compatible completion for the given prompt using the specified model. :param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint. - :param prompt: The prompt to generate a completion for - :param best_of: (Optional) The number of completions to generate - :param echo: (Optional) Whether to echo the prompt - :param frequency_penalty: (Optional) The penalty for repeated tokens - :param logit_bias: (Optional) The logit bias to use - :param logprobs: (Optional) The log probabilities to use - :param max_tokens: (Optional) The maximum number of tokens to generate - :param n: (Optional) The number of completions to generate - :param presence_penalty: (Optional) The penalty for repeated tokens - :param seed: (Optional) The seed to use - :param stop: (Optional) The stop tokens to use - :param stream: (Optional) Whether to stream the response - :param stream_options: (Optional) The stream options to use - :param temperature: (Optional) The temperature to use - :param top_p: (Optional) The top p to use - :param user: (Optional) The user to use + :param prompt: The prompt to generate a completion for. + :param best_of: (Optional) The number of completions to generate. + :param echo: (Optional) Whether to echo the prompt. + :param frequency_penalty: (Optional) The penalty for repeated tokens. + :param logit_bias: (Optional) The logit bias to use. + :param logprobs: (Optional) The log probabilities to use. + :param max_tokens: (Optional) The maximum number of tokens to generate. + :param n: (Optional) The number of completions to generate. + :param presence_penalty: (Optional) The penalty for repeated tokens. + :param seed: (Optional) The seed to use. + :param stop: (Optional) The stop tokens to use. + :param stream: (Optional) Whether to stream the response. + :param stream_options: (Optional) The stream options to use. + :param temperature: (Optional) The temperature to use. + :param top_p: (Optional) The top p to use. + :param user: (Optional) The user to use. + :returns: An OpenAICompletion. """ ... @@ -1016,27 +1037,28 @@ class Inference(Protocol): """Generate an OpenAI-compatible chat completion for the given messages using the specified model. :param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint. - :param messages: List of messages in the conversation - :param frequency_penalty: (Optional) The penalty for repeated tokens - :param function_call: (Optional) The function call to use - :param functions: (Optional) List of functions to use - :param logit_bias: (Optional) The logit bias to use - :param logprobs: (Optional) The log probabilities to use - :param max_completion_tokens: (Optional) The maximum number of tokens to generate - :param max_tokens: (Optional) The maximum number of tokens to generate - :param n: (Optional) The number of completions to generate - :param parallel_tool_calls: (Optional) Whether to parallelize tool calls - :param presence_penalty: (Optional) The penalty for repeated tokens - :param response_format: (Optional) The response format to use - :param seed: (Optional) The seed to use - :param stop: (Optional) The stop tokens to use - :param stream: (Optional) Whether to stream the response - :param stream_options: (Optional) The stream options to use - :param temperature: (Optional) The temperature to use - :param tool_choice: (Optional) The tool choice to use - :param tools: (Optional) The tools to use - :param top_logprobs: (Optional) The top log probabilities to use - :param top_p: (Optional) The top p to use - :param user: (Optional) The user to use + :param messages: List of messages in the conversation. + :param frequency_penalty: (Optional) The penalty for repeated tokens. + :param function_call: (Optional) The function call to use. + :param functions: (Optional) List of functions to use. + :param logit_bias: (Optional) The logit bias to use. + :param logprobs: (Optional) The log probabilities to use. + :param max_completion_tokens: (Optional) The maximum number of tokens to generate. + :param max_tokens: (Optional) The maximum number of tokens to generate. + :param n: (Optional) The number of completions to generate. + :param parallel_tool_calls: (Optional) Whether to parallelize tool calls. + :param presence_penalty: (Optional) The penalty for repeated tokens. + :param response_format: (Optional) The response format to use. + :param seed: (Optional) The seed to use. + :param stop: (Optional) The stop tokens to use. + :param stream: (Optional) Whether to stream the response. + :param stream_options: (Optional) The stream options to use. + :param temperature: (Optional) The temperature to use. + :param tool_choice: (Optional) The tool choice to use. + :param tools: (Optional) The tools to use. + :param top_logprobs: (Optional) The top log probabilities to use. + :param top_p: (Optional) The top p to use. + :param user: (Optional) The user to use. + :returns: An OpenAIChatCompletion. """ ... diff --git a/llama_stack/apis/inspect/inspect.py b/llama_stack/apis/inspect/inspect.py index fb3167635..44a5e95b2 100644 --- a/llama_stack/apis/inspect/inspect.py +++ b/llama_stack/apis/inspect/inspect.py @@ -36,10 +36,25 @@ class ListRoutesResponse(BaseModel): @runtime_checkable class Inspect(Protocol): @webmethod(route="/inspect/routes", method="GET") - async def list_routes(self) -> ListRoutesResponse: ... + async def list_routes(self) -> ListRoutesResponse: + """List all routes. + + :returns: A ListRoutesResponse. + """ + ... @webmethod(route="/health", method="GET") - async def health(self) -> HealthInfo: ... + async def health(self) -> HealthInfo: + """Get the health of the service. + + :returns: A HealthInfo. + """ + ... @webmethod(route="/version", method="GET") - async def version(self) -> VersionInfo: ... + async def version(self) -> VersionInfo: + """Get the version of the service. + + :returns: A VersionInfo. + """ + ... diff --git a/llama_stack/apis/models/models.py b/llama_stack/apis/models/models.py index 37ae95fa5..3d90a92a0 100644 --- a/llama_stack/apis/models/models.py +++ b/llama_stack/apis/models/models.py @@ -80,16 +80,32 @@ class OpenAIListModelsResponse(BaseModel): @trace_protocol class Models(Protocol): @webmethod(route="/models", method="GET") - async def list_models(self) -> ListModelsResponse: ... + async def list_models(self) -> ListModelsResponse: + """List all models. + + :returns: A ListModelsResponse. + """ + ... @webmethod(route="/openai/v1/models", method="GET") - async def openai_list_models(self) -> OpenAIListModelsResponse: ... + async def openai_list_models(self) -> OpenAIListModelsResponse: + """List models using the OpenAI API. + + :returns: A OpenAIListModelsResponse. + """ + ... @webmethod(route="/models/{model_id:path}", method="GET") async def get_model( self, model_id: str, - ) -> Model: ... + ) -> Model: + """Get a model by its identifier. + + :param model_id: The identifier of the model to get. + :returns: A Model. + """ + ... @webmethod(route="/models", method="POST") async def register_model( @@ -99,10 +115,25 @@ class Models(Protocol): provider_id: str | None = None, metadata: dict[str, Any] | None = None, model_type: ModelType | None = None, - ) -> Model: ... + ) -> Model: + """Register a model. + + :param model_id: The identifier of the model to register. + :param provider_model_id: The identifier of the model in the provider. + :param provider_id: The identifier of the provider. + :param metadata: Any additional metadata for this model. + :param model_type: The type of model to register. + :returns: A Model. + """ + ... @webmethod(route="/models/{model_id:path}", method="DELETE") async def unregister_model( self, model_id: str, - ) -> None: ... + ) -> None: + """Unregister a model. + + :param model_id: The identifier of the model to unregister. + """ + ... diff --git a/llama_stack/apis/post_training/post_training.py b/llama_stack/apis/post_training/post_training.py index 016f79fce..b196c8a17 100644 --- a/llama_stack/apis/post_training/post_training.py +++ b/llama_stack/apis/post_training/post_training.py @@ -182,7 +182,19 @@ class PostTraining(Protocol): ), checkpoint_dir: str | None = None, algorithm_config: AlgorithmConfig | None = None, - ) -> PostTrainingJob: ... + ) -> PostTrainingJob: + """Run supervised fine-tuning of a model. + + :param job_uuid: The UUID of the job to create. + :param training_config: The training configuration. + :param hyperparam_search_config: The hyperparam search configuration. + :param logger_config: The logger configuration. + :param model: The model to fine-tune. + :param checkpoint_dir: The directory to save checkpoint(s) to. + :param algorithm_config: The algorithm configuration. + :returns: A PostTrainingJob. + """ + ... @webmethod(route="/post-training/preference-optimize", method="POST") async def preference_optimize( @@ -193,16 +205,49 @@ class PostTraining(Protocol): training_config: TrainingConfig, hyperparam_search_config: dict[str, Any], logger_config: dict[str, Any], - ) -> PostTrainingJob: ... + ) -> PostTrainingJob: + """Run preference optimization of a model. + + :param job_uuid: The UUID of the job to create. + :param finetuned_model: The model to fine-tune. + :param algorithm_config: The algorithm configuration. + :param training_config: The training configuration. + :param hyperparam_search_config: The hyperparam search configuration. + :param logger_config: The logger configuration. + :returns: A PostTrainingJob. + """ + ... @webmethod(route="/post-training/jobs", method="GET") - async def get_training_jobs(self) -> ListPostTrainingJobsResponse: ... + async def get_training_jobs(self) -> ListPostTrainingJobsResponse: + """Get all training jobs. + + :returns: A ListPostTrainingJobsResponse. + """ + ... @webmethod(route="/post-training/job/status", method="GET") - async def get_training_job_status(self, job_uuid: str) -> PostTrainingJobStatusResponse: ... + async def get_training_job_status(self, job_uuid: str) -> PostTrainingJobStatusResponse: + """Get the status of a training job. + + :param job_uuid: The UUID of the job to get the status of. + :returns: A PostTrainingJobStatusResponse. + """ + ... @webmethod(route="/post-training/job/cancel", method="POST") - async def cancel_training_job(self, job_uuid: str) -> None: ... + async def cancel_training_job(self, job_uuid: str) -> None: + """Cancel a training job. + + :param job_uuid: The UUID of the job to cancel. + """ + ... @webmethod(route="/post-training/job/artifacts", method="GET") - async def get_training_job_artifacts(self, job_uuid: str) -> PostTrainingJobArtifactsResponse: ... + async def get_training_job_artifacts(self, job_uuid: str) -> PostTrainingJobArtifactsResponse: + """Get the artifacts of a training job. + + :param job_uuid: The UUID of the job to get the artifacts of. + :returns: A PostTrainingJobArtifactsResponse. + """ + ... diff --git a/llama_stack/apis/providers/providers.py b/llama_stack/apis/providers/providers.py index 751c9263b..4bc977bf1 100644 --- a/llama_stack/apis/providers/providers.py +++ b/llama_stack/apis/providers/providers.py @@ -32,7 +32,18 @@ class Providers(Protocol): """ @webmethod(route="/providers", method="GET") - async def list_providers(self) -> ListProvidersResponse: ... + async def list_providers(self) -> ListProvidersResponse: + """List all available providers. + + :returns: A ListProvidersResponse containing information about all providers. + """ + ... @webmethod(route="/providers/{provider_id}", method="GET") - async def inspect_provider(self, provider_id: str) -> ProviderInfo: ... + async def inspect_provider(self, provider_id: str) -> ProviderInfo: + """Get detailed information about a specific provider. + + :param provider_id: The ID of the provider to inspect. + :returns: A ProviderInfo object containing the provider's details. + """ + ... diff --git a/llama_stack/apis/safety/safety.py b/llama_stack/apis/safety/safety.py index b6b58262f..3aee52b7e 100644 --- a/llama_stack/apis/safety/safety.py +++ b/llama_stack/apis/safety/safety.py @@ -54,4 +54,12 @@ class Safety(Protocol): shield_id: str, messages: list[Message], params: dict[str, Any], - ) -> RunShieldResponse: ... + ) -> RunShieldResponse: + """Run a shield. + + :param shield_id: The identifier of the shield to run. + :param messages: The messages to run the shield on. + :param params: The parameters of the shield. + :returns: A RunShieldResponse. + """ + ... diff --git a/llama_stack/apis/scoring/scoring.py b/llama_stack/apis/scoring/scoring.py index 414f3d5e2..732e80e79 100644 --- a/llama_stack/apis/scoring/scoring.py +++ b/llama_stack/apis/scoring/scoring.py @@ -61,7 +61,15 @@ class Scoring(Protocol): dataset_id: str, scoring_functions: dict[str, ScoringFnParams | None], save_results_dataset: bool = False, - ) -> ScoreBatchResponse: ... + ) -> ScoreBatchResponse: + """Score a batch of rows. + + :param dataset_id: The ID of the dataset to score. + :param scoring_functions: The scoring functions to use for the scoring. + :param save_results_dataset: Whether to save the results to a dataset. + :returns: A ScoreBatchResponse. + """ + ... @webmethod(route="/scoring/score", method="POST") async def score( @@ -73,6 +81,6 @@ class Scoring(Protocol): :param input_rows: The rows to score. :param scoring_functions: The scoring functions to use for the scoring. - :return: ScoreResponse object containing rows and aggregated results + :returns: A ScoreResponse object containing rows and aggregated results. """ ... diff --git a/llama_stack/apis/scoring_functions/scoring_functions.py b/llama_stack/apis/scoring_functions/scoring_functions.py index 9ba9eb654..9cd21b7d1 100644 --- a/llama_stack/apis/scoring_functions/scoring_functions.py +++ b/llama_stack/apis/scoring_functions/scoring_functions.py @@ -134,10 +134,21 @@ class ListScoringFunctionsResponse(BaseModel): @runtime_checkable class ScoringFunctions(Protocol): @webmethod(route="/scoring-functions", method="GET") - async def list_scoring_functions(self) -> ListScoringFunctionsResponse: ... + async def list_scoring_functions(self) -> ListScoringFunctionsResponse: + """List all scoring functions. + + :returns: A ListScoringFunctionsResponse. + """ + ... @webmethod(route="/scoring-functions/{scoring_fn_id:path}", method="GET") - async def get_scoring_function(self, scoring_fn_id: str, /) -> ScoringFn: ... + async def get_scoring_function(self, scoring_fn_id: str, /) -> ScoringFn: + """Get a scoring function by its ID. + + :param scoring_fn_id: The ID of the scoring function to get. + :returns: A ScoringFn. + """ + ... @webmethod(route="/scoring-functions", method="POST") async def register_scoring_function( @@ -148,4 +159,14 @@ class ScoringFunctions(Protocol): provider_scoring_fn_id: str | None = None, provider_id: str | None = None, params: ScoringFnParams | None = None, - ) -> None: ... + ) -> None: + """Register a scoring function. + + :param scoring_fn_id: The ID of the scoring function to register. + :param description: The description of the scoring function. + :param return_type: The return type of the scoring function. + :param provider_scoring_fn_id: The ID of the provider scoring function to use for the scoring function. + :param provider_id: The ID of the provider to use for the scoring function. + :param params: The parameters for the scoring function for benchmark eval, these can be overridden for app eval. + """ + ... diff --git a/llama_stack/apis/shields/shields.py b/llama_stack/apis/shields/shields.py index 66bb9a0b8..ce1f73d8e 100644 --- a/llama_stack/apis/shields/shields.py +++ b/llama_stack/apis/shields/shields.py @@ -46,10 +46,21 @@ class ListShieldsResponse(BaseModel): @trace_protocol class Shields(Protocol): @webmethod(route="/shields", method="GET") - async def list_shields(self) -> ListShieldsResponse: ... + async def list_shields(self) -> ListShieldsResponse: + """List all shields. + + :returns: A ListShieldsResponse. + """ + ... @webmethod(route="/shields/{identifier:path}", method="GET") - async def get_shield(self, identifier: str) -> Shield: ... + async def get_shield(self, identifier: str) -> Shield: + """Get a shield by its identifier. + + :param identifier: The identifier of the shield to get. + :returns: A Shield. + """ + ... @webmethod(route="/shields", method="POST") async def register_shield( @@ -58,4 +69,13 @@ class Shields(Protocol): provider_shield_id: str | None = None, provider_id: str | None = None, params: dict[str, Any] | None = None, - ) -> Shield: ... + ) -> Shield: + """Register a shield. + + :param shield_id: The identifier of the shield to register. + :param provider_shield_id: The identifier of the shield in the provider. + :param provider_id: The identifier of the provider. + :param params: The parameters of the shield. + :returns: A Shield. + """ + ... diff --git a/llama_stack/apis/telemetry/telemetry.py b/llama_stack/apis/telemetry/telemetry.py index 0a3e63a88..0eb53f397 100644 --- a/llama_stack/apis/telemetry/telemetry.py +++ b/llama_stack/apis/telemetry/telemetry.py @@ -247,7 +247,17 @@ class QueryMetricsResponse(BaseModel): @runtime_checkable class Telemetry(Protocol): @webmethod(route="/telemetry/events", method="POST") - async def log_event(self, event: Event, ttl_seconds: int = DEFAULT_TTL_DAYS * 86400) -> None: ... + async def log_event( + self, + event: Event, + ttl_seconds: int = DEFAULT_TTL_DAYS * 86400, + ) -> None: + """Log an event. + + :param event: The event to log. + :param ttl_seconds: The time to live of the event. + """ + ... @webmethod(route="/telemetry/traces", method="POST") async def query_traces( @@ -256,13 +266,35 @@ class Telemetry(Protocol): limit: int | None = 100, offset: int | None = 0, order_by: list[str] | None = None, - ) -> QueryTracesResponse: ... + ) -> QueryTracesResponse: + """Query traces. + + :param attribute_filters: The attribute filters to apply to the traces. + :param limit: The limit of traces to return. + :param offset: The offset of the traces to return. + :param order_by: The order by of the traces to return. + :returns: A QueryTracesResponse. + """ + ... @webmethod(route="/telemetry/traces/{trace_id:path}", method="GET") - async def get_trace(self, trace_id: str) -> Trace: ... + async def get_trace(self, trace_id: str) -> Trace: + """Get a trace by its ID. + + :param trace_id: The ID of the trace to get. + :returns: A Trace. + """ + ... @webmethod(route="/telemetry/traces/{trace_id:path}/spans/{span_id:path}", method="GET") - async def get_span(self, trace_id: str, span_id: str) -> Span: ... + async def get_span(self, trace_id: str, span_id: str) -> Span: + """Get a span by its ID. + + :param trace_id: The ID of the trace to get the span from. + :param span_id: The ID of the span to get. + :returns: A Span. + """ + ... @webmethod(route="/telemetry/spans/{span_id:path}/tree", method="POST") async def get_span_tree( @@ -270,7 +302,15 @@ class Telemetry(Protocol): span_id: str, attributes_to_return: list[str] | None = None, max_depth: int | None = None, - ) -> QuerySpanTreeResponse: ... + ) -> QuerySpanTreeResponse: + """Get a span tree by its ID. + + :param span_id: The ID of the span to get the tree from. + :param attributes_to_return: The attributes to return in the tree. + :param max_depth: The maximum depth of the tree. + :returns: A QuerySpanTreeResponse. + """ + ... @webmethod(route="/telemetry/spans", method="POST") async def query_spans( @@ -278,7 +318,15 @@ class Telemetry(Protocol): attribute_filters: list[QueryCondition], attributes_to_return: list[str], max_depth: int | None = None, - ) -> QuerySpansResponse: ... + ) -> QuerySpansResponse: + """Query spans. + + :param attribute_filters: The attribute filters to apply to the spans. + :param attributes_to_return: The attributes to return in the spans. + :param max_depth: The maximum depth of the tree. + :returns: A QuerySpansResponse. + """ + ... @webmethod(route="/telemetry/spans/export", method="POST") async def save_spans_to_dataset( @@ -287,7 +335,15 @@ class Telemetry(Protocol): attributes_to_save: list[str], dataset_id: str, max_depth: int | None = None, - ) -> None: ... + ) -> None: + """Save spans to a dataset. + + :param attribute_filters: The attribute filters to apply to the spans. + :param attributes_to_save: The attributes to save to the dataset. + :param dataset_id: The ID of the dataset to save the spans to. + :param max_depth: The maximum depth of the tree. + """ + ... @webmethod(route="/telemetry/metrics/{metric_name}", method="POST") async def query_metrics( @@ -298,4 +354,15 @@ class Telemetry(Protocol): granularity: str | None = "1d", query_type: MetricQueryType = MetricQueryType.RANGE, label_matchers: list[MetricLabelMatcher] | None = None, - ) -> QueryMetricsResponse: ... + ) -> QueryMetricsResponse: + """Query metrics. + + :param metric_name: The name of the metric to query. + :param start_time: The start time of the metric to query. + :param end_time: The end time of the metric to query. + :param granularity: The granularity of the metric to query. + :param query_type: The type of query to perform. + :param label_matchers: The label matchers to apply to the metric. + :returns: A QueryMetricsResponse. + """ + ... diff --git a/llama_stack/apis/tools/tools.py b/llama_stack/apis/tools/tools.py index 2860ddbd8..2f62b0ba1 100644 --- a/llama_stack/apis/tools/tools.py +++ b/llama_stack/apis/tools/tools.py @@ -103,37 +103,65 @@ class ToolGroups(Protocol): mcp_endpoint: URL | None = None, args: dict[str, Any] | None = None, ) -> None: - """Register a tool group""" + """Register a tool group. + + :param toolgroup_id: The ID of the tool group to register. + :param provider_id: The ID of the provider to use for the tool group. + :param mcp_endpoint: The MCP endpoint to use for the tool group. + :param args: A dictionary of arguments to pass to the tool group. + """ ... @webmethod(route="/toolgroups/{toolgroup_id:path}", method="GET") async def get_tool_group( self, toolgroup_id: str, - ) -> ToolGroup: ... + ) -> ToolGroup: + """Get a tool group by its ID. + + :param toolgroup_id: The ID of the tool group to get. + :returns: A ToolGroup. + """ + ... @webmethod(route="/toolgroups", method="GET") async def list_tool_groups(self) -> ListToolGroupsResponse: - """List tool groups with optional provider""" + """List tool groups with optional provider. + + :returns: A ListToolGroupsResponse. + """ ... @webmethod(route="/tools", method="GET") async def list_tools(self, toolgroup_id: str | None = None) -> ListToolsResponse: - """List tools with optional tool group""" + """List tools with optional tool group. + + :param toolgroup_id: The ID of the tool group to list tools for. + :returns: A ListToolsResponse. + """ ... @webmethod(route="/tools/{tool_name:path}", method="GET") async def get_tool( self, tool_name: str, - ) -> Tool: ... + ) -> Tool: + """Get a tool by its name. + + :param tool_name: The name of the tool to get. + :returns: A Tool. + """ + ... @webmethod(route="/toolgroups/{toolgroup_id:path}", method="DELETE") async def unregister_toolgroup( self, toolgroup_id: str, ) -> None: - """Unregister a tool group""" + """Unregister a tool group. + + :param toolgroup_id: The ID of the tool group to unregister. + """ ... @@ -152,9 +180,21 @@ class ToolRuntime(Protocol): @webmethod(route="/tool-runtime/list-tools", method="GET") async def list_runtime_tools( self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None - ) -> ListToolDefsResponse: ... + ) -> ListToolDefsResponse: + """List all tools in the runtime. + + :param tool_group_id: The ID of the tool group to list tools for. + :param mcp_endpoint: The MCP endpoint to use for the tool group. + :returns: A ListToolDefsResponse. + """ + ... @webmethod(route="/tool-runtime/invoke", method="POST") async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: - """Run a tool with the given arguments""" + """Run a tool with the given arguments. + + :param tool_name: The name of the tool to invoke. + :param kwargs: A dictionary of arguments to pass to the tool. + :returns: A ToolInvocationResult. + """ ... diff --git a/llama_stack/apis/vector_dbs/vector_dbs.py b/llama_stack/apis/vector_dbs/vector_dbs.py index a01892888..405852476 100644 --- a/llama_stack/apis/vector_dbs/vector_dbs.py +++ b/llama_stack/apis/vector_dbs/vector_dbs.py @@ -44,13 +44,24 @@ class ListVectorDBsResponse(BaseModel): @trace_protocol class VectorDBs(Protocol): @webmethod(route="/vector-dbs", method="GET") - async def list_vector_dbs(self) -> ListVectorDBsResponse: ... + async def list_vector_dbs(self) -> ListVectorDBsResponse: + """List all vector databases. + + :returns: A ListVectorDBsResponse. + """ + ... @webmethod(route="/vector-dbs/{vector_db_id:path}", method="GET") async def get_vector_db( self, vector_db_id: str, - ) -> VectorDB: ... + ) -> VectorDB: + """Get a vector database by its identifier. + + :param vector_db_id: The identifier of the vector database to get. + :returns: A VectorDB. + """ + ... @webmethod(route="/vector-dbs", method="POST") async def register_vector_db( @@ -60,7 +71,22 @@ class VectorDBs(Protocol): embedding_dimension: int | None = 384, provider_id: str | None = None, provider_vector_db_id: str | None = None, - ) -> VectorDB: ... + ) -> VectorDB: + """Register a vector database. + + :param vector_db_id: The identifier of the vector database to register. + :param embedding_model: The embedding model to use. + :param embedding_dimension: The dimension of the embedding model. + :param provider_id: The identifier of the provider. + :param provider_vector_db_id: The identifier of the vector database in the provider. + :returns: A VectorDB. + """ + ... @webmethod(route="/vector-dbs/{vector_db_id:path}", method="DELETE") - async def unregister_vector_db(self, vector_db_id: str) -> None: ... + async def unregister_vector_db(self, vector_db_id: str) -> None: + """Unregister a vector database. + + :param vector_db_id: The identifier of the vector database to unregister. + """ + ... diff --git a/llama_stack/apis/vector_io/vector_io.py b/llama_stack/apis/vector_io/vector_io.py index bfae0f802..3ac62d42c 100644 --- a/llama_stack/apis/vector_io/vector_io.py +++ b/llama_stack/apis/vector_io/vector_io.py @@ -46,7 +46,14 @@ class VectorIO(Protocol): vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None, - ) -> None: ... + ) -> None: + """Insert chunks into a vector database. + + :param vector_db_id: The identifier of the vector database to insert the chunks into. + :param chunks: The chunks to insert. + :param ttl_seconds: The time to live of the chunks. + """ + ... @webmethod(route="/vector-io/query", method="POST") async def query_chunks( @@ -54,4 +61,12 @@ class VectorIO(Protocol): vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None, - ) -> QueryChunksResponse: ... + ) -> QueryChunksResponse: + """Query chunks from a vector database. + + :param vector_db_id: The identifier of the vector database to query. + :param query: The query to search for. + :param params: The parameters of the query. + :returns: A QueryChunksResponse. + """ + ...