From 0b6725ac7ad9aa28900cc4826932689e09da5a3d Mon Sep 17 00:00:00 2001 From: Alexey Rybak Date: Tue, 23 Sep 2025 10:00:13 -0700 Subject: [PATCH] api docs --- docs/docs/api/agents.tag.mdx | 1 - docs/docs/api/append-rows-to-a-dataset.api.mdx | 11 ++++------- docs/docs/api/attach-a-file-to-a-vector-store.api.mdx | 11 ++++------- docs/docs/api/batch-inference-coming-soon.tag.mdx | 1 - docs/docs/api/benchmarks.tag.mdx | 1 - docs/docs/api/cancel-a-job.api.mdx | 11 ++++------- docs/docs/api/cancel-a-training-job.api.mdx | 11 ++++------- ...nd-or-image-inputs-are-potentially-harmful.api.mdx | 11 ++++------- docs/docs/api/create-a-new-open-ai-response.api.mdx | 11 ++++------- docs/docs/api/create-a-new-prompt.api.mdx | 11 ++++------- .../api/create-a-new-session-for-an-agent.api.mdx | 11 ++++------- docs/docs/api/create-a-new-turn-for-an-agent.api.mdx | 11 ++++------- ...eate-an-agent-with-the-given-configuration.api.mdx | 11 ++++------- docs/docs/api/creates-a-vector-store.api.mdx | 11 ++++------- docs/docs/api/dataset-io.tag.mdx | 1 - docs/docs/api/datasets.tag.mdx | 1 - docs/docs/api/delete-a-file.api.mdx | 11 ++++------- docs/docs/api/delete-a-prompt.api.mdx | 11 ++++------- docs/docs/api/delete-a-vector-store-file.api.mdx | 11 ++++------- docs/docs/api/delete-a-vector-store.api.mdx | 11 ++++------- ...s-id-and-its-associated-sessions-and-turns.api.mdx | 11 ++++------- ...session-by-its-id-and-its-associated-turns.api.mdx | 11 ++++------- .../api/delete-an-open-ai-response-by-its-id.api.mdx | 11 ++++------- .../api/describe-a-chat-completion-by-its-id.api.mdx | 11 ++++------- docs/docs/api/describe-an-agent-by-its-id.api.mdx | 11 ++++------- docs/docs/api/eval.tag.mdx | 1 - .../evaluate-a-list-of-rows-on-a-benchmark.api.mdx | 11 ++++------- docs/docs/api/files.tag.mdx | 1 - ...e-given-messages-using-the-specified-model.api.mdx | 11 ++++------- ...he-given-content-using-the-specified-model.api.mdx | 11 ++++------- ...e-given-messages-using-the-specified-model.api.mdx | 11 ++++------- ...the-given-prompt-using-the-specified-model.api.mdx | 11 ++++------- ...atch-of-messages-using-the-specified-model.api.mdx | 11 ++++------- ...batch-of-content-using-the-specified-model.api.mdx | 11 ++++------- ...r-content-pieces-using-the-specified-model.api.mdx | 11 ++++------- ...-the-given-input-using-the-specified-model.api.mdx | 11 ++++------- ...based-on-input-dialogs-and-apply-filtering.api.mdx | 11 ++++------- docs/docs/api/get-a-benchmark-by-its-id.api.mdx | 11 ++++------- docs/docs/api/get-a-dataset-by-its-id.api.mdx | 11 ++++------- docs/docs/api/get-a-model-by-its-identifier.api.mdx | 11 ++++------- ...et-a-paginated-list-of-rows-from-a-dataset.api.mdx | 11 ++++------- ...mpt-by-its-identifier-and-optional-version.api.mdx | 11 ++++------- .../docs/api/get-a-scoring-function-by-its-id.api.mdx | 11 ++++------- docs/docs/api/get-a-shield-by-its-identifier.api.mdx | 11 ++++------- docs/docs/api/get-a-span-by-its-id.api.mdx | 11 ++++------- docs/docs/api/get-a-span-tree-by-its-id.api.mdx | 11 ++++------- docs/docs/api/get-a-tool-by-its-name.api.mdx | 11 ++++------- docs/docs/api/get-a-tool-group-by-its-id.api.mdx | 11 ++++------- docs/docs/api/get-a-trace-by-its-id.api.mdx | 11 ++++------- .../get-a-vector-database-by-its-identifier.api.mdx | 11 ++++------- docs/docs/api/get-all-training-jobs.api.mdx | 11 ++++------- ...iled-information-about-a-specific-provider.api.mdx | 11 ++++------- .../api/get-the-artifacts-of-a-training-job.api.mdx | 11 ++++------- ...t-the-current-health-status-of-the-service.api.mdx | 11 ++++------- docs/docs/api/get-the-result-of-a-job.api.mdx | 11 ++++------- docs/docs/api/get-the-status-of-a-job.api.mdx | 11 ++++------- .../docs/api/get-the-status-of-a-training-job.api.mdx | 11 ++++------- docs/docs/api/get-the-version-of-the-service.api.mdx | 11 ++++------- ...ents-so-they-can-be-used-by-the-rag-system.api.mdx | 11 ++++------- docs/docs/api/inference.tag.mdx | 1 - .../api/insert-chunks-into-a-vector-database.api.mdx | 11 ++++------- docs/docs/api/inspect.tag.mdx | 1 - docs/docs/api/list-all-agents.api.mdx | 11 ++++------- ...h-their-methods-and-implementing-providers.api.mdx | 11 ++++------- docs/docs/api/list-all-available-providers.api.mdx | 11 ++++------- docs/docs/api/list-all-benchmarks.api.mdx | 11 ++++------- docs/docs/api/list-all-chat-completions.api.mdx | 11 ++++------- docs/docs/api/list-all-datasets.api.mdx | 11 ++++------- docs/docs/api/list-all-models.api.mdx | 11 ++++------- docs/docs/api/list-all-open-ai-responses.api.mdx | 11 ++++------- docs/docs/api/list-all-prompts.api.mdx | 11 ++++------- docs/docs/api/list-all-scoring-functions.api.mdx | 11 ++++------- .../api/list-all-session-s-of-a-given-agent.api.mdx | 11 ++++------- docs/docs/api/list-all-shields.api.mdx | 11 ++++------- docs/docs/api/list-all-tools-in-the-runtime.api.mdx | 11 ++++------- docs/docs/api/list-all-vector-databases.api.mdx | 11 ++++------- .../list-all-versions-of-a-specific-prompt.api.mdx | 11 ++++------- docs/docs/api/list-files-in-a-vector-store.api.mdx | 11 ++++------- ...t-input-items-for-a-given-open-ai-response.api.mdx | 11 ++++------- .../api/list-models-using-the-open-ai-api.api.mdx | 11 ++++------- .../list-tool-groups-with-optional-provider.api.mdx | 11 ++++------- .../api/list-tools-with-optional-tool-group.api.mdx | 11 ++++------- docs/docs/api/llama-stack-specification.info.mdx | 5 +---- docs/docs/api/log-an-event.api.mdx | 11 ++++------- docs/docs/api/models.tag.mdx | 1 - docs/docs/api/post-training-coming-soon.tag.mdx | 1 - docs/docs/api/prompts.tag.mdx | 1 - docs/docs/api/providers.tag.mdx | 1 - .../api/query-chunks-from-a-vector-database.api.mdx | 11 ++++------- docs/docs/api/query-metrics.api.mdx | 11 ++++------- docs/docs/api/query-spans.api.mdx | 11 ++++------- ...for-context-typically-invoked-by-the-agent.api.mdx | 11 ++++------- docs/docs/api/query-traces.api.mdx | 11 ++++------- docs/docs/api/register-a-benchmark.api.mdx | 11 ++++------- docs/docs/api/register-a-model.api.mdx | 11 ++++------- docs/docs/api/register-a-new-dataset.api.mdx | 11 ++++------- docs/docs/api/register-a-scoring-function.api.mdx | 11 ++++------- docs/docs/api/register-a-shield.api.mdx | 11 ++++------- docs/docs/api/register-a-tool-group.api.mdx | 11 ++++------- docs/docs/api/register-a-vector-database.api.mdx | 11 ++++------- ...uments-based-on-their-relevance-to-a-query.api.mdx | 11 ++++------- ...ent-turn-with-executed-tool-call-responses.api.mdx | 11 ++++------- .../api/retrieve-an-agent-session-by-its-id.api.mdx | 11 ++++------- .../docs/api/retrieve-an-agent-step-by-its-id.api.mdx | 11 ++++------- .../docs/api/retrieve-an-agent-turn-by-its-id.api.mdx | 11 ++++------- .../retrieve-an-open-ai-response-by-its-id.api.mdx | 11 ++++------- docs/docs/api/retrieves-a-vector-store-file.api.mdx | 11 ++++------- docs/docs/api/retrieves-a-vector-store.api.mdx | 11 ++++------- ...rieves-the-contents-of-a-vector-store-file.api.mdx | 11 ++++------- ...iles-that-belong-to-the-users-organization.api.mdx | 11 ++++------- docs/docs/api/returns-a-list-of-vector-stores.api.mdx | 11 ++++------- .../returns-information-about-a-specific-file.api.mdx | 11 ++++------- ...returns-the-contents-of-the-specified-file.api.mdx | 11 ++++------- docs/docs/api/run-a-shield.api.mdx | 11 ++++------- .../api/run-a-tool-with-the-given-arguments.api.mdx | 11 ++++------- .../docs/api/run-an-evaluation-on-a-benchmark.api.mdx | 11 ++++------- .../run-preference-optimization-of-a-model.api.mdx | 11 ++++------- .../api/run-supervised-fine-tuning-of-a-model.api.mdx | 11 ++++------- docs/docs/api/safety.tag.mdx | 1 - docs/docs/api/save-spans-to-a-dataset.api.mdx | 11 ++++------- docs/docs/api/score-a-batch-of-rows.api.mdx | 11 ++++------- docs/docs/api/score-a-list-of-rows.api.mdx | 11 ++++------- docs/docs/api/scoring-functions.tag.mdx | 1 - docs/docs/api/scoring.tag.mdx | 1 - .../api/search-for-chunks-in-a-vector-store.api.mdx | 11 ++++------- ...should-be-the-default-in-get-prompt-latest.api.mdx | 11 ++++------- docs/docs/api/shields.tag.mdx | 1 - .../api/synthetic-data-generation-coming-soon.tag.mdx | 1 - docs/docs/api/telemetry.tag.mdx | 1 - docs/docs/api/tool-groups.tag.mdx | 1 - docs/docs/api/tool-runtime.tag.mdx | 1 - docs/docs/api/unregister-a-benchmark.api.mdx | 11 ++++------- docs/docs/api/unregister-a-dataset-by-its-id.api.mdx | 11 ++++------- docs/docs/api/unregister-a-model.api.mdx | 11 ++++------- docs/docs/api/unregister-a-scoring-function.api.mdx | 11 ++++------- docs/docs/api/unregister-a-shield.api.mdx | 11 ++++------- docs/docs/api/unregister-a-tool-group.api.mdx | 11 ++++------- docs/docs/api/unregister-a-vector-database.api.mdx | 11 ++++------- ...date-an-existing-prompt-increments-version.api.mdx | 11 ++++------- docs/docs/api/updates-a-vector-store-file.api.mdx | 11 ++++------- docs/docs/api/updates-a-vector-store.api.mdx | 11 ++++------- ...-that-can-be-used-across-various-endpoints.api.mdx | 11 ++++------- docs/docs/api/vector-d-bs.tag.mdx | 1 - docs/docs/api/vector-io.tag.mdx | 1 - 144 files changed, 481 insertions(+), 867 deletions(-) diff --git a/docs/docs/api/agents.tag.mdx b/docs/docs/api/agents.tag.mdx index 55d57181a..ce0632f33 100644 --- a/docs/docs/api/agents.tag.mdx +++ b/docs/docs/api/agents.tag.mdx @@ -22,4 +22,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/append-rows-to-a-dataset.api.mdx b/docs/docs/api/append-rows-to-a-dataset.api.mdx index 2bbccec9a..9622f68e8 100644 --- a/docs/docs/api/append-rows-to-a-dataset.api.mdx +++ b/docs/docs/api/append-rows-to-a-dataset.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/datasetio/append-rows/{dataset_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Append rows to a dataset. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/attach-a-file-to-a-vector-store.api.mdx b/docs/docs/api/attach-a-file-to-a-vector-store.api.mdx index 7547f4bba..4a0b2519d 100644 --- a/docs/docs/api/attach-a-file-to-a-vector-store.api.mdx +++ b/docs/docs/api/attach-a-file-to-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/files"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Attach a file to a vector store. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/batch-inference-coming-soon.tag.mdx b/docs/docs/api/batch-inference-coming-soon.tag.mdx index bdf1ac474..e430bd388 100644 --- a/docs/docs/api/batch-inference-coming-soon.tag.mdx +++ b/docs/docs/api/batch-inference-coming-soon.tag.mdx @@ -20,4 +20,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/benchmarks.tag.mdx b/docs/docs/api/benchmarks.tag.mdx index 40a98afa2..41402bc42 100644 --- a/docs/docs/api/benchmarks.tag.mdx +++ b/docs/docs/api/benchmarks.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/cancel-a-job.api.mdx b/docs/docs/api/cancel-a-job.api.mdx index 8e9a99eb7..1530b43aa 100644 --- a/docs/docs/api/cancel-a-job.api.mdx +++ b/docs/docs/api/cancel-a-job.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Cancel a job. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/cancel-a-training-job.api.mdx b/docs/docs/api/cancel-a-training-job.api.mdx index 2fae70147..1c44bfb12 100644 --- a/docs/docs/api/cancel-a-training-job.api.mdx +++ b/docs/docs/api/cancel-a-training-job.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/post-training/job/cancel"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Cancel a training job. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/classifies-if-text-and-or-image-inputs-are-potentially-harmful.api.mdx b/docs/docs/api/classifies-if-text-and-or-image-inputs-are-potentially-harmful.api.mdx index e3f8cc637..cb13f6860 100644 --- a/docs/docs/api/classifies-if-text-and-or-image-inputs-are-potentially-harmful.api.mdx +++ b/docs/docs/api/classifies-if-text-and-or-image-inputs-are-potentially-harmful.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/moderations"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Classifies if text and/or image inputs are potentially harmful. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/create-a-new-open-ai-response.api.mdx b/docs/docs/api/create-a-new-open-ai-response.api.mdx index 43aa8d120..b3073b2d8 100644 --- a/docs/docs/api/create-a-new-open-ai-response.api.mdx +++ b/docs/docs/api/create-a-new-open-ai-response.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/responses"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Create a new OpenAI response. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/create-a-new-prompt.api.mdx b/docs/docs/api/create-a-new-prompt.api.mdx index 6b7ab5e79..f3b191825 100644 --- a/docs/docs/api/create-a-new-prompt.api.mdx +++ b/docs/docs/api/create-a-new-prompt.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Create a new prompt. - + - + '"},"variables":{"type":"array","items":{"type":"string"},"description":"List of prompt variable names that can be used in the prompt template"},"is_default":{"type":"boolean","default":false,"description":"Boolean indicating whether this version is the default version for this prompt"}},"additionalProperties":false,"required":["version","prompt_id","variables","is_default"],"title":"Prompt","description":"A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/create-a-new-session-for-an-agent.api.mdx b/docs/docs/api/create-a-new-session-for-an-agent.api.mdx index 0b09ad620..51ffa619e 100644 --- a/docs/docs/api/create-a-new-session-for-an-agent.api.mdx +++ b/docs/docs/api/create-a-new-session-for-an-agent.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Create a new session for an agent. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/create-a-new-turn-for-an-agent.api.mdx b/docs/docs/api/create-a-new-turn-for-an-agent.api.mdx index 40b4624db..893862cb7 100644 --- a/docs/docs/api/create-a-new-turn-for-an-agent.api.mdx +++ b/docs/docs/api/create-a-new-turn-for-an-agent.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session/{session_id}/turn"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Create a new turn for an agent. - + tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."}},"additionalProperties":false,"required":["messages"],"title":"CreateAgentTurnRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/create-an-agent-with-the-given-configuration.api.mdx b/docs/docs/api/create-an-agent-with-the-given-configuration.api.mdx index f7526ea7c..fd8ebdedd 100644 --- a/docs/docs/api/create-an-agent-with-the-given-configuration.api.mdx +++ b/docs/docs/api/create-an-agent-with-the-given-configuration.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Create an agent with the given configuration. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"input_shields":{"type":"array","items":{"type":"string"}},"output_shields":{"type":"array","items":{"type":"string"}},"toolgroups":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","properties":{"name":{"type":"string"},"args":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}}},"additionalProperties":false,"required":["name","args"],"title":"AgentToolGroupWithArgs"}],"title":"AgentTool"}},"client_tools":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool"},"description":{"type":"string","description":"(Optional) Human-readable description of what the tool does"},"parameters":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the parameter"},"parameter_type":{"type":"string","description":"Type of the parameter (e.g., string, integer)"},"description":{"type":"string","description":"Human-readable description of what the parameter does"},"required":{"type":"boolean","default":true,"description":"Whether this parameter is required for tool invocation"},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}],"description":"(Optional) Default value for the parameter if not provided"}},"additionalProperties":false,"required":["name","parameter_type","description","required"],"title":"ToolParameter","description":"Parameter definition for a tool."},"description":"(Optional) List of parameters this tool accepts"},"metadata":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"(Optional) Additional metadata about the tool"}},"additionalProperties":false,"required":["name"],"title":"ToolDef","description":"Tool definition used in runtime contexts."}},"tool_choice":{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.","deprecated":true},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"title":"ToolPromptFormat","description":"Prompt format for calling custom / zero shot tools.","deprecated":true},"tool_config":{"type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."},"max_infer_iters":{"type":"integer","default":10},"model":{"type":"string","description":"The model identifier to use for the agent"},"instructions":{"type":"string","description":"The system instructions for the agent"},"name":{"type":"string","description":"Optional name for the agent, used in telemetry and identification"},"enable_session_persistence":{"type":"boolean","default":false,"description":"Optional flag indicating whether session data has to be persisted"},"response_format":{"description":"Optional response format configuration","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"}},"additionalProperties":false,"required":["model","instructions"],"title":"AgentConfig"}},"additionalProperties":false,"required":["agent_config"],"title":"CreateAgentRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/creates-a-vector-store.api.mdx b/docs/docs/api/creates-a-vector-store.api.mdx index b278525b2..87c71696f 100644 --- a/docs/docs/api/creates-a-vector-store.api.mdx +++ b/docs/docs/api/creates-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Creates a vector store. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/dataset-io.tag.mdx b/docs/docs/api/dataset-io.tag.mdx index c2c8956eb..dae7d4341 100644 --- a/docs/docs/api/dataset-io.tag.mdx +++ b/docs/docs/api/dataset-io.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/datasets.tag.mdx b/docs/docs/api/datasets.tag.mdx index beb520c4f..2cf7b50c8 100644 --- a/docs/docs/api/datasets.tag.mdx +++ b/docs/docs/api/datasets.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/delete-a-file.api.mdx b/docs/docs/api/delete-a-file.api.mdx index 145420599..47f81b85d 100644 --- a/docs/docs/api/delete-a-file.api.mdx +++ b/docs/docs/api/delete-a-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/files/{file_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete a file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/delete-a-prompt.api.mdx b/docs/docs/api/delete-a-prompt.api.mdx index 42e03c406..151289452 100644 --- a/docs/docs/api/delete-a-prompt.api.mdx +++ b/docs/docs/api/delete-a-prompt.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts/{prompt_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete a prompt. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/delete-a-vector-store-file.api.mdx b/docs/docs/api/delete-a-vector-store-file.api.mdx index 411b3a342..76d34bdd8 100644 --- a/docs/docs/api/delete-a-vector-store-file.api.mdx +++ b/docs/docs/api/delete-a-vector-store-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete a vector store file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/delete-a-vector-store.api.mdx b/docs/docs/api/delete-a-vector-store.api.mdx index 1b6a7f327..265fc371c 100644 --- a/docs/docs/api/delete-a-vector-store.api.mdx +++ b/docs/docs/api/delete-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete a vector store. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/delete-an-agent-by-its-id-and-its-associated-sessions-and-turns.api.mdx b/docs/docs/api/delete-an-agent-by-its-id-and-its-associated-sessions-and-turns.api.mdx index ec947e036..82adb6682 100644 --- a/docs/docs/api/delete-an-agent-by-its-id-and-its-associated-sessions-and-turns.api.mdx +++ b/docs/docs/api/delete-an-agent-by-its-id-and-its-associated-sessions-and-turns.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete an agent by its ID and its associated sessions and turns. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/delete-an-agent-session-by-its-id-and-its-associated-turns.api.mdx b/docs/docs/api/delete-an-agent-session-by-its-id-and-its-associated-turns.api.mdx index 8ebfb9d1a..a1252dbad 100644 --- a/docs/docs/api/delete-an-agent-session-by-its-id-and-its-associated-turns.api.mdx +++ b/docs/docs/api/delete-an-agent-session-by-its-id-and-its-associated-turns.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session/{session_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete an agent session by its ID and its associated turns. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/delete-an-open-ai-response-by-its-id.api.mdx b/docs/docs/api/delete-an-open-ai-response-by-its-id.api.mdx index bedc52337..892e52e8b 100644 --- a/docs/docs/api/delete-an-open-ai-response-by-its-id.api.mdx +++ b/docs/docs/api/delete-an-open-ai-response-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/responses/{response_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Delete an OpenAI response by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/describe-a-chat-completion-by-its-id.api.mdx b/docs/docs/api/describe-a-chat-completion-by-its-id.api.mdx index cc71b171d..2e89ab94f 100644 --- a/docs/docs/api/describe-a-chat-completion-by-its-id.api.mdx +++ b/docs/docs/api/describe-a-chat-completion-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/chat/completions/{completion_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Describe a chat completion by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/describe-an-agent-by-its-id.api.mdx b/docs/docs/api/describe-an-agent-by-its-id.api.mdx index d26077cb7..1a072edd7 100644 --- a/docs/docs/api/describe-an-agent-by-its-id.api.mdx +++ b/docs/docs/api/describe-an-agent-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Describe an agent by its ID. - + - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"input_shields":{"type":"array","items":{"type":"string"}},"output_shields":{"type":"array","items":{"type":"string"}},"toolgroups":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","properties":{"name":{"type":"string"},"args":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}}},"additionalProperties":false,"required":["name","args"],"title":"AgentToolGroupWithArgs"}],"title":"AgentTool"}},"client_tools":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool"},"description":{"type":"string","description":"(Optional) Human-readable description of what the tool does"},"parameters":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the parameter"},"parameter_type":{"type":"string","description":"Type of the parameter (e.g., string, integer)"},"description":{"type":"string","description":"Human-readable description of what the parameter does"},"required":{"type":"boolean","default":true,"description":"Whether this parameter is required for tool invocation"},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}],"description":"(Optional) Default value for the parameter if not provided"}},"additionalProperties":false,"required":["name","parameter_type","description","required"],"title":"ToolParameter","description":"Parameter definition for a tool."},"description":"(Optional) List of parameters this tool accepts"},"metadata":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"(Optional) Additional metadata about the tool"}},"additionalProperties":false,"required":["name"],"title":"ToolDef","description":"Tool definition used in runtime contexts."}},"tool_choice":{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.","deprecated":true},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"title":"ToolPromptFormat","description":"Prompt format for calling custom / zero shot tools.","deprecated":true},"tool_config":{"type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."},"max_infer_iters":{"type":"integer","default":10},"model":{"type":"string","description":"The model identifier to use for the agent"},"instructions":{"type":"string","description":"The system instructions for the agent"},"name":{"type":"string","description":"Optional name for the agent, used in telemetry and identification"},"enable_session_persistence":{"type":"boolean","default":false,"description":"Optional flag indicating whether session data has to be persisted"},"response_format":{"description":"Optional response format configuration","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"}},"additionalProperties":false,"required":["model","instructions"],"title":"AgentConfig"},"created_at":{"type":"string","format":"date-time","description":"Timestamp when the agent was created"}},"additionalProperties":false,"required":["agent_id","agent_config","created_at"],"title":"Agent","description":"An agent instance with configuration and metadata."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/eval.tag.mdx b/docs/docs/api/eval.tag.mdx index 24015957c..b75422307 100644 --- a/docs/docs/api/eval.tag.mdx +++ b/docs/docs/api/eval.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/evaluate-a-list-of-rows-on-a-benchmark.api.mdx b/docs/docs/api/evaluate-a-list-of-rows-on-a-benchmark.api.mdx index 2e7a17ff0..468abcbff 100644 --- a/docs/docs/api/evaluate-a-list-of-rows-on-a-benchmark.api.mdx +++ b/docs/docs/api/evaluate-a-list-of-rows-on-a-benchmark.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}/evaluations"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Evaluate a list of rows on a benchmark. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"system_message":{"type":"object","properties":{"role":{"type":"string","const":"system","default":"system","description":"Must be \"system\" to identify this as a system message"},"content":{"description":"The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions).","oneOf":[{"type":"string"},{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"}}],"title":"InterleavedContent"}},"additionalProperties":false,"required":["role","content"],"title":"SystemMessage","description":"A system message providing instructions or context to the model."}},"additionalProperties":false,"required":["type","model","sampling_params"],"title":"ModelCandidate","description":"A model candidate for evaluation."},{"type":"object","properties":{"type":{"type":"string","const":"agent","default":"agent"},"config":{"description":"The configuration for the agent candidate.","type":"object","properties":{"sampling_params":{"type":"object","properties":{"strategy":{"description":"The sampling strategy.","oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"input_shields":{"type":"array","items":{"type":"string"}},"output_shields":{"type":"array","items":{"type":"string"}},"toolgroups":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","properties":{"name":{"type":"string"},"args":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}}},"additionalProperties":false,"required":["name","args"],"title":"AgentToolGroupWithArgs"}],"title":"AgentTool"}},"client_tools":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool"},"description":{"type":"string","description":"(Optional) Human-readable description of what the tool does"},"parameters":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the parameter"},"parameter_type":{"type":"string","description":"Type of the parameter (e.g., string, integer)"},"description":{"type":"string","description":"Human-readable description of what the parameter does"},"required":{"type":"boolean","default":true,"description":"Whether this parameter is required for tool invocation"},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}],"description":"(Optional) Default value for the parameter if not provided"}},"additionalProperties":false,"required":["name","parameter_type","description","required"],"title":"ToolParameter","description":"Parameter definition for a tool."},"description":"(Optional) List of parameters this tool accepts"},"metadata":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"(Optional) Additional metadata about the tool"}},"additionalProperties":false,"required":["name"],"title":"ToolDef","description":"Tool definition used in runtime contexts."}},"tool_choice":{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.","deprecated":true},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"title":"ToolPromptFormat","description":"Prompt format for calling custom / zero shot tools.","deprecated":true},"tool_config":{"type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."},"max_infer_iters":{"type":"integer","default":10},"model":{"type":"string","description":"The model identifier to use for the agent"},"instructions":{"type":"string","description":"The system instructions for the agent"},"name":{"type":"string","description":"Optional name for the agent, used in telemetry and identification"},"enable_session_persistence":{"type":"boolean","default":false,"description":"Optional flag indicating whether session data has to be persisted"},"response_format":{"description":"Optional response format configuration","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"}},"additionalProperties":false,"required":["model","instructions"],"title":"AgentConfig"}},"additionalProperties":false,"required":["type","config"],"title":"AgentCandidate","description":"An agent candidate for evaluation."}],"discriminator":{"propertyName":"type","mapping":{"model":{"type":"object","properties":{"type":{"type":"string","const":"model","default":"model"},"model":{"type":"string","description":"The model ID to evaluate."},"sampling_params":{"type":"object","properties":{"strategy":{"description":"The sampling strategy.","oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"system_message":{"type":"object","properties":{"role":{"type":"string","const":"system","default":"system","description":"Must be \"system\" to identify this as a system message"},"content":{"description":"The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions).","oneOf":[{"type":"string"},{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"}}],"title":"InterleavedContent"}},"additionalProperties":false,"required":["role","content"],"title":"SystemMessage","description":"A system message providing instructions or context to the model."}},"additionalProperties":false,"required":["type","model","sampling_params"],"title":"ModelCandidate","description":"A model candidate for evaluation."},"agent":{"type":"object","properties":{"type":{"type":"string","const":"agent","default":"agent"},"config":{"description":"The configuration for the agent candidate.","type":"object","properties":{"sampling_params":{"type":"object","properties":{"strategy":{"description":"The sampling strategy.","oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"input_shields":{"type":"array","items":{"type":"string"}},"output_shields":{"type":"array","items":{"type":"string"}},"toolgroups":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","properties":{"name":{"type":"string"},"args":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}}},"additionalProperties":false,"required":["name","args"],"title":"AgentToolGroupWithArgs"}],"title":"AgentTool"}},"client_tools":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool"},"description":{"type":"string","description":"(Optional) Human-readable description of what the tool does"},"parameters":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the parameter"},"parameter_type":{"type":"string","description":"Type of the parameter (e.g., string, integer)"},"description":{"type":"string","description":"Human-readable description of what the parameter does"},"required":{"type":"boolean","default":true,"description":"Whether this parameter is required for tool invocation"},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}],"description":"(Optional) Default value for the parameter if not provided"}},"additionalProperties":false,"required":["name","parameter_type","description","required"],"title":"ToolParameter","description":"Parameter definition for a tool."},"description":"(Optional) List of parameters this tool accepts"},"metadata":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"(Optional) Additional metadata about the tool"}},"additionalProperties":false,"required":["name"],"title":"ToolDef","description":"Tool definition used in runtime contexts."}},"tool_choice":{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.","deprecated":true},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"title":"ToolPromptFormat","description":"Prompt format for calling custom / zero shot tools.","deprecated":true},"tool_config":{"type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."},"max_infer_iters":{"type":"integer","default":10},"model":{"type":"string","description":"The model identifier to use for the agent"},"instructions":{"type":"string","description":"The system instructions for the agent"},"name":{"type":"string","description":"Optional name for the agent, used in telemetry and identification"},"enable_session_persistence":{"type":"boolean","default":false,"description":"Optional flag indicating whether session data has to be persisted"},"response_format":{"description":"Optional response format configuration","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"}},"additionalProperties":false,"required":["model","instructions"],"title":"AgentConfig"}},"additionalProperties":false,"required":["type","config"],"title":"AgentCandidate","description":"An agent candidate for evaluation."}}},"title":"EvalCandidate"},"scoring_params":{"type":"object","additionalProperties":{"oneOf":[{"type":"object","properties":{"type":{"const":"llm_as_judge","default":"llm_as_judge","description":"The type of scoring function parameters, always llm_as_judge","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"judge_model":{"type":"string","description":"Identifier of the LLM model to use as a judge for scoring"},"prompt_template":{"type":"string","description":"(Optional) Custom prompt template for the judge model"},"judge_score_regexes":{"type":"array","items":{"type":"string"},"description":"Regexes to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","judge_model","judge_score_regexes","aggregation_functions"],"title":"LLMAsJudgeScoringFnParams","description":"Parameters for LLM-as-judge scoring function configuration."},{"type":"object","properties":{"type":{"const":"regex_parser","default":"regex_parser","description":"The type of scoring function parameters, always regex_parser","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"parsing_regexes":{"type":"array","items":{"type":"string"},"description":"Regex to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","parsing_regexes","aggregation_functions"],"title":"RegexParserScoringFnParams","description":"Parameters for regex parser scoring function configuration."},{"type":"object","properties":{"type":{"const":"basic","default":"basic","description":"The type of scoring function parameters, always basic","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","aggregation_functions"],"title":"BasicScoringFnParams","description":"Parameters for basic scoring function configuration."}],"discriminator":{"propertyName":"type","mapping":{"llm_as_judge":{"type":"object","properties":{"type":{"const":"llm_as_judge","default":"llm_as_judge","description":"The type of scoring function parameters, always llm_as_judge","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"judge_model":{"type":"string","description":"Identifier of the LLM model to use as a judge for scoring"},"prompt_template":{"type":"string","description":"(Optional) Custom prompt template for the judge model"},"judge_score_regexes":{"type":"array","items":{"type":"string"},"description":"Regexes to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","judge_model","judge_score_regexes","aggregation_functions"],"title":"LLMAsJudgeScoringFnParams","description":"Parameters for LLM-as-judge scoring function configuration."},"regex_parser":{"type":"object","properties":{"type":{"const":"regex_parser","default":"regex_parser","description":"The type of scoring function parameters, always regex_parser","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"parsing_regexes":{"type":"array","items":{"type":"string"},"description":"Regex to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","parsing_regexes","aggregation_functions"],"title":"RegexParserScoringFnParams","description":"Parameters for regex parser scoring function configuration."},"basic":{"type":"object","properties":{"type":{"const":"basic","default":"basic","description":"The type of scoring function parameters, always basic","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","aggregation_functions"],"title":"BasicScoringFnParams","description":"Parameters for basic scoring function configuration."}}},"title":"ScoringFnParams"},"description":"Map between scoring function id and parameters for each scoring function you want to run"},"num_examples":{"type":"integer","description":"(Optional) The number of examples to evaluate. If not provided, all examples in the dataset will be evaluated"}},"additionalProperties":false,"required":["eval_candidate","scoring_params"],"title":"BenchmarkConfig"}},"additionalProperties":false,"required":["input_rows","scoring_functions","benchmark_config"],"title":"EvaluateRowsRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/files.tag.mdx b/docs/docs/api/files.tag.mdx index 164a49384..bd62d0b2e 100644 --- a/docs/docs/api/files.tag.mdx +++ b/docs/docs/api/files.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/generate-a-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx b/docs/docs/api/generate-a-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx index 7f9d673cc..b29fe9f7c 100644 --- a/docs/docs/api/generate-a-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-a-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inference/chat-completion"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate a chat completion for the given messages using the specified model. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams"},"tools":{"type":"array","items":{"type":"object","properties":{"tool_name":{"oneOf":[{"type":"string","enum":["brave_search","wolfram_alpha","photogen","code_interpreter"],"title":"BuiltinTool"},{"type":"string"}]},"description":{"type":"string"},"parameters":{"type":"object","additionalProperties":{"type":"object","properties":{"param_type":{"type":"string"},"description":{"type":"string"},"required":{"type":"boolean","default":true},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}},"additionalProperties":false,"required":["param_type"],"title":"ToolParamDefinition"}}},"additionalProperties":false,"required":["tool_name"],"title":"ToolDefinition"},"description":"(Optional) List of tool definitions available to the model."},"tool_choice":{"type":"string","enum":["auto","required","none"],"description":"(Optional) Whether tool use is required or automatic. Defaults to ToolChoice.auto. .. deprecated:: Use tool_config instead."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls. .. deprecated:: Use tool_config instead."},"response_format":{"description":"(Optional) Grammar specification for guided (structured) decoding. There are two options: - `ResponseFormat.json_schema`: The grammar is a JSON schema. Most providers support this format. - `ResponseFormat.grammar`: The grammar is a BNF grammar. This format is more flexible, but not all providers support it.","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"},"stream":{"type":"boolean","description":"(Optional) If True, generate an SSE event stream of the response. Defaults to False."},"logprobs":{"type":"object","properties":{"top_k":{"type":"integer","default":0,"description":"How many tokens (for each position) to return log probabilities for."}},"additionalProperties":false,"description":"(Optional) If specified, log probabilities for each token position will be returned."},"tool_config":{"description":"(Optional) Configuration for tool use.","type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig"}},"additionalProperties":false,"required":["model_id","messages"],"title":"ChatCompletionRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-a-completion-for-the-given-content-using-the-specified-model.api.mdx b/docs/docs/api/generate-a-completion-for-the-given-content-using-the-specified-model.api.mdx index 7e228a4a2..3e826faa4 100644 --- a/docs/docs/api/generate-a-completion-for-the-given-content-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-a-completion-for-the-given-content-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inference/completion"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate a completion for the given content using the specified model. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams"},"response_format":{"description":"(Optional) Grammar specification for guided (structured) decoding.","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"},"stream":{"type":"boolean","description":"(Optional) If True, generate an SSE event stream of the response. Defaults to False."},"logprobs":{"type":"object","properties":{"top_k":{"type":"integer","default":0,"description":"How many tokens (for each position) to return log probabilities for."}},"additionalProperties":false,"description":"(Optional) If specified, log probabilities for each token position will be returned."}},"additionalProperties":false,"required":["model_id","content"],"title":"CompletionRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-an-open-ai-compatible-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx b/docs/docs/api/generate-an-open-ai-compatible-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx index af1f5823c..c3034a726 100644 --- a/docs/docs/api/generate-an-open-ai-compatible-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-an-open-ai-compatible-chat-completion-for-the-given-messages-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/chat/completions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate an OpenAI-compatible chat completion for the given messages using the s - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-an-open-ai-compatible-completion-for-the-given-prompt-using-the-specified-model.api.mdx b/docs/docs/api/generate-an-open-ai-compatible-completion-for-the-given-prompt-using-the-specified-model.api.mdx index f90f95ad8..8056e0bfa 100644 --- a/docs/docs/api/generate-an-open-ai-compatible-completion-for-the-given-prompt-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-an-open-ai-compatible-completion-for-the-given-prompt-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/completions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate an OpenAI-compatible completion for the given prompt using the specifie - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-chat-completions-for-a-batch-of-messages-using-the-specified-model.api.mdx b/docs/docs/api/generate-chat-completions-for-a-batch-of-messages-using-the-specified-model.api.mdx index eb19e1a2a..c9a4c8d3b 100644 --- a/docs/docs/api/generate-chat-completions-for-a-batch-of-messages-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-chat-completions-for-a-batch-of-messages-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inference/batch-chat-completion"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate chat completions for a batch of messages using the specified model. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams"},"tools":{"type":"array","items":{"type":"object","properties":{"tool_name":{"oneOf":[{"type":"string","enum":["brave_search","wolfram_alpha","photogen","code_interpreter"],"title":"BuiltinTool"},{"type":"string"}]},"description":{"type":"string"},"parameters":{"type":"object","additionalProperties":{"type":"object","properties":{"param_type":{"type":"string"},"description":{"type":"string"},"required":{"type":"boolean","default":true},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}},"additionalProperties":false,"required":["param_type"],"title":"ToolParamDefinition"}}},"additionalProperties":false,"required":["tool_name"],"title":"ToolDefinition"},"description":"(Optional) List of tool definitions available to the model."},"tool_config":{"description":"(Optional) Configuration for tool use.","type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig"},"response_format":{"description":"(Optional) Grammar specification for guided (structured) decoding.","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"},"logprobs":{"type":"object","properties":{"top_k":{"type":"integer","default":0,"description":"How many tokens (for each position) to return log probabilities for."}},"additionalProperties":false,"description":"(Optional) If specified, log probabilities for each token position will be returned."}},"additionalProperties":false,"required":["model_id","messages_batch"],"title":"BatchChatCompletionRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-completions-for-a-batch-of-content-using-the-specified-model.api.mdx b/docs/docs/api/generate-completions-for-a-batch-of-content-using-the-specified-model.api.mdx index 7b8959c56..6691ce780 100644 --- a/docs/docs/api/generate-completions-for-a-batch-of-content-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-completions-for-a-batch-of-content-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inference/batch-completion"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate completions for a batch of content using the specified model. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams"},"response_format":{"description":"(Optional) Grammar specification for guided (structured) decoding.","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"},"logprobs":{"type":"object","properties":{"top_k":{"type":"integer","default":0,"description":"How many tokens (for each position) to return log probabilities for."}},"additionalProperties":false,"description":"(Optional) If specified, log probabilities for each token position will be returned."}},"additionalProperties":false,"required":["model_id","content_batch"],"title":"BatchCompletionRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-embeddings-for-content-pieces-using-the-specified-model.api.mdx b/docs/docs/api/generate-embeddings-for-content-pieces-using-the-specified-model.api.mdx index 59fa02b69..c48123036 100644 --- a/docs/docs/api/generate-embeddings-for-content-pieces-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-embeddings-for-content-pieces-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inference/embeddings"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate embeddings for content pieces using the specified model. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-open-ai-compatible-embeddings-for-the-given-input-using-the-specified-model.api.mdx b/docs/docs/api/generate-open-ai-compatible-embeddings-for-the-given-input-using-the-specified-model.api.mdx index 7e5c88794..1ed46df25 100644 --- a/docs/docs/api/generate-open-ai-compatible-embeddings-for-the-given-input-using-the-specified-model.api.mdx +++ b/docs/docs/api/generate-open-ai-compatible-embeddings-for-the-given-input-using-the-specified-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/embeddings"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate OpenAI-compatible embeddings for the given input using the specified mo - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/generate-synthetic-data-based-on-input-dialogs-and-apply-filtering.api.mdx b/docs/docs/api/generate-synthetic-data-based-on-input-dialogs-and-apply-filtering.api.mdx index 13cfcb382..f39829ebf 100644 --- a/docs/docs/api/generate-synthetic-data-based-on-input-dialogs-and-apply-filtering.api.mdx +++ b/docs/docs/api/generate-synthetic-data-based-on-input-dialogs-and-apply-filtering.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/synthetic-data-generation/generate"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Generate synthetic data based on input dialogs and apply filtering. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-benchmark-by-its-id.api.mdx b/docs/docs/api/get-a-benchmark-by-its-id.api.mdx index 383e46710..0c416534a 100644 --- a/docs/docs/api/get-a-benchmark-by-its-id.api.mdx +++ b/docs/docs/api/get-a-benchmark-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a benchmark by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-dataset-by-its-id.api.mdx b/docs/docs/api/get-a-dataset-by-its-id.api.mdx index 12459bfdc..d42cd6439 100644 --- a/docs/docs/api/get-a-dataset-by-its-id.api.mdx +++ b/docs/docs/api/get-a-dataset-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/datasets/{dataset_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a dataset by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-model-by-its-identifier.api.mdx b/docs/docs/api/get-a-model-by-its-identifier.api.mdx index 675cf5764..fd768d9b3 100644 --- a/docs/docs/api/get-a-model-by-its-identifier.api.mdx +++ b/docs/docs/api/get-a-model-by-its-identifier.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/models/{model_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a model by its identifier. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-paginated-list-of-rows-from-a-dataset.api.mdx b/docs/docs/api/get-a-paginated-list-of-rows-from-a-dataset.api.mdx index 1ec33a120..72f499646 100644 --- a/docs/docs/api/get-a-paginated-list-of-rows-from-a-dataset.api.mdx +++ b/docs/docs/api/get-a-paginated-list-of-rows-from-a-dataset.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/datasetio/iterrows/{dataset_id}"} context={"endpoint"} > - + @@ -56,14 +56,14 @@ The response includes: - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-prompt-by-its-identifier-and-optional-version.api.mdx b/docs/docs/api/get-a-prompt-by-its-identifier-and-optional-version.api.mdx index eac3d3206..2e707bf1c 100644 --- a/docs/docs/api/get-a-prompt-by-its-identifier-and-optional-version.api.mdx +++ b/docs/docs/api/get-a-prompt-by-its-identifier-and-optional-version.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts/{prompt_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a prompt by its identifier and optional version. - + - + '"},"variables":{"type":"array","items":{"type":"string"},"description":"List of prompt variable names that can be used in the prompt template"},"is_default":{"type":"boolean","default":false,"description":"Boolean indicating whether this version is the default version for this prompt"}},"additionalProperties":false,"required":["version","prompt_id","variables","is_default"],"title":"Prompt","description":"A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-scoring-function-by-its-id.api.mdx b/docs/docs/api/get-a-scoring-function-by-its-id.api.mdx index 994f74c92..d100aa9f5 100644 --- a/docs/docs/api/get-a-scoring-function-by-its-id.api.mdx +++ b/docs/docs/api/get-a-scoring-function-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/scoring-functions/{scoring_fn_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a scoring function by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-shield-by-its-identifier.api.mdx b/docs/docs/api/get-a-shield-by-its-identifier.api.mdx index 75228baf6..52bc5978f 100644 --- a/docs/docs/api/get-a-shield-by-its-identifier.api.mdx +++ b/docs/docs/api/get-a-shield-by-its-identifier.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/shields/{identifier}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a shield by its identifier. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-span-by-its-id.api.mdx b/docs/docs/api/get-a-span-by-its-id.api.mdx index e10ff2ed5..7e24e0a44 100644 --- a/docs/docs/api/get-a-span-by-its-id.api.mdx +++ b/docs/docs/api/get-a-span-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/traces/{trace_id}/spans/{span_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a span by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-span-tree-by-its-id.api.mdx b/docs/docs/api/get-a-span-tree-by-its-id.api.mdx index 1afa513c9..18bcdc606 100644 --- a/docs/docs/api/get-a-span-tree-by-its-id.api.mdx +++ b/docs/docs/api/get-a-span-tree-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/spans/{span_id}/tree"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a span tree by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-tool-by-its-name.api.mdx b/docs/docs/api/get-a-tool-by-its-name.api.mdx index 4b0d19c0e..07923dbe2 100644 --- a/docs/docs/api/get-a-tool-by-its-name.api.mdx +++ b/docs/docs/api/get-a-tool-by-its-name.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/tools/{tool_name}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a tool by its name. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-tool-group-by-its-id.api.mdx b/docs/docs/api/get-a-tool-group-by-its-id.api.mdx index 8dea71363..0e1c52dce 100644 --- a/docs/docs/api/get-a-tool-group-by-its-id.api.mdx +++ b/docs/docs/api/get-a-tool-group-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/toolgroups/{toolgroup_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a tool group by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-trace-by-its-id.api.mdx b/docs/docs/api/get-a-trace-by-its-id.api.mdx index dca6b0a95..794fee0dc 100644 --- a/docs/docs/api/get-a-trace-by-its-id.api.mdx +++ b/docs/docs/api/get-a-trace-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/traces/{trace_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a trace by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-a-vector-database-by-its-identifier.api.mdx b/docs/docs/api/get-a-vector-database-by-its-identifier.api.mdx index f78fa3d8b..2748e0401 100644 --- a/docs/docs/api/get-a-vector-database-by-its-identifier.api.mdx +++ b/docs/docs/api/get-a-vector-database-by-its-identifier.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/vector-dbs/{vector_db_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get a vector database by its identifier. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-all-training-jobs.api.mdx b/docs/docs/api/get-all-training-jobs.api.mdx index 50a1f1011..4f7b08dc6 100644 --- a/docs/docs/api/get-all-training-jobs.api.mdx +++ b/docs/docs/api/get-all-training-jobs.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/post-training/jobs"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get all training jobs. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-detailed-information-about-a-specific-provider.api.mdx b/docs/docs/api/get-detailed-information-about-a-specific-provider.api.mdx index a4d4de4ee..5a6b2ae4b 100644 --- a/docs/docs/api/get-detailed-information-about-a-specific-provider.api.mdx +++ b/docs/docs/api/get-detailed-information-about-a-specific-provider.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/providers/{provider_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get detailed information about a specific provider. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-the-artifacts-of-a-training-job.api.mdx b/docs/docs/api/get-the-artifacts-of-a-training-job.api.mdx index a37b2160d..c1d12b7aa 100644 --- a/docs/docs/api/get-the-artifacts-of-a-training-job.api.mdx +++ b/docs/docs/api/get-the-artifacts-of-a-training-job.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/post-training/job/artifacts"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get the artifacts of a training job. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-the-current-health-status-of-the-service.api.mdx b/docs/docs/api/get-the-current-health-status-of-the-service.api.mdx index 4eb72b031..e1712d447 100644 --- a/docs/docs/api/get-the-current-health-status-of-the-service.api.mdx +++ b/docs/docs/api/get-the-current-health-status-of-the-service.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/health"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get the current health status of the service. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-the-result-of-a-job.api.mdx b/docs/docs/api/get-the-result-of-a-job.api.mdx index 39170e359..fb015b843 100644 --- a/docs/docs/api/get-the-result-of-a-job.api.mdx +++ b/docs/docs/api/get-the-result-of-a-job.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get the result of a job. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-the-status-of-a-job.api.mdx b/docs/docs/api/get-the-status-of-a-job.api.mdx index cc338c5c8..69c80b1fc 100644 --- a/docs/docs/api/get-the-status-of-a-job.api.mdx +++ b/docs/docs/api/get-the-status-of-a-job.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get the status of a job. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-the-status-of-a-training-job.api.mdx b/docs/docs/api/get-the-status-of-a-training-job.api.mdx index 53774574f..bc63b6e40 100644 --- a/docs/docs/api/get-the-status-of-a-training-job.api.mdx +++ b/docs/docs/api/get-the-status-of-a-training-job.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/post-training/job/status"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get the status of a training job. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/get-the-version-of-the-service.api.mdx b/docs/docs/api/get-the-version-of-the-service.api.mdx index b7f598749..cdfef041f 100644 --- a/docs/docs/api/get-the-version-of-the-service.api.mdx +++ b/docs/docs/api/get-the-version-of-the-service.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/version"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Get the version of the service. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/index-documents-so-they-can-be-used-by-the-rag-system.api.mdx b/docs/docs/api/index-documents-so-they-can-be-used-by-the-rag-system.api.mdx index 702eeec24..db9045289 100644 --- a/docs/docs/api/index-documents-so-they-can-be-used-by-the-rag-system.api.mdx +++ b/docs/docs/api/index-documents-so-they-can-be-used-by-the-rag-system.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/tool-runtime/rag-tool/insert"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Index documents so they can be used by the RAG system. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/inference.tag.mdx b/docs/docs/api/inference.tag.mdx index 28ec4e5a5..a5b39f619 100644 --- a/docs/docs/api/inference.tag.mdx +++ b/docs/docs/api/inference.tag.mdx @@ -19,4 +19,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/insert-chunks-into-a-vector-database.api.mdx b/docs/docs/api/insert-chunks-into-a-vector-database.api.mdx index 06eb07eb6..a07cd8e95 100644 --- a/docs/docs/api/insert-chunks-into-a-vector-database.api.mdx +++ b/docs/docs/api/insert-chunks-into-a-vector-database.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/vector-io/insert"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Insert chunks into a vector database. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/inspect.tag.mdx b/docs/docs/api/inspect.tag.mdx index 096442d45..6b9309c4b 100644 --- a/docs/docs/api/inspect.tag.mdx +++ b/docs/docs/api/inspect.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/list-all-agents.api.mdx b/docs/docs/api/list-all-agents.api.mdx index 144bfa4f5..81b9457bd 100644 --- a/docs/docs/api/list-all-agents.api.mdx +++ b/docs/docs/api/list-all-agents.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all agents. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-available-api-routes-with-their-methods-and-implementing-providers.api.mdx b/docs/docs/api/list-all-available-api-routes-with-their-methods-and-implementing-providers.api.mdx index 466d6746d..9aaab103d 100644 --- a/docs/docs/api/list-all-available-api-routes-with-their-methods-and-implementing-providers.api.mdx +++ b/docs/docs/api/list-all-available-api-routes-with-their-methods-and-implementing-providers.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inspect/routes"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all available API routes with their methods and implementing providers. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-available-providers.api.mdx b/docs/docs/api/list-all-available-providers.api.mdx index 28b4737c3..21b80eaa6 100644 --- a/docs/docs/api/list-all-available-providers.api.mdx +++ b/docs/docs/api/list-all-available-providers.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/providers"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all available providers. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-benchmarks.api.mdx b/docs/docs/api/list-all-benchmarks.api.mdx index eaef498f4..b35e6fdaa 100644 --- a/docs/docs/api/list-all-benchmarks.api.mdx +++ b/docs/docs/api/list-all-benchmarks.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all benchmarks. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-chat-completions.api.mdx b/docs/docs/api/list-all-chat-completions.api.mdx index 8719ee4f6..84e14087b 100644 --- a/docs/docs/api/list-all-chat-completions.api.mdx +++ b/docs/docs/api/list-all-chat-completions.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/chat/completions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all chat completions. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-datasets.api.mdx b/docs/docs/api/list-all-datasets.api.mdx index 53cb1bcc3..4b2239b5e 100644 --- a/docs/docs/api/list-all-datasets.api.mdx +++ b/docs/docs/api/list-all-datasets.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/datasets"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all datasets. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-models.api.mdx b/docs/docs/api/list-all-models.api.mdx index 0d22c4066..f1b67feba 100644 --- a/docs/docs/api/list-all-models.api.mdx +++ b/docs/docs/api/list-all-models.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/models"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all models. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-open-ai-responses.api.mdx b/docs/docs/api/list-all-open-ai-responses.api.mdx index 2515233cc..08d96ae67 100644 --- a/docs/docs/api/list-all-open-ai-responses.api.mdx +++ b/docs/docs/api/list-all-open-ai-responses.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/responses"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all OpenAI responses. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-prompts.api.mdx b/docs/docs/api/list-all-prompts.api.mdx index 50d0bfe07..37c6c3765 100644 --- a/docs/docs/api/list-all-prompts.api.mdx +++ b/docs/docs/api/list-all-prompts.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all prompts. - + - + '"},"variables":{"type":"array","items":{"type":"string"},"description":"List of prompt variable names that can be used in the prompt template"},"is_default":{"type":"boolean","default":false,"description":"Boolean indicating whether this version is the default version for this prompt"}},"additionalProperties":false,"required":["version","prompt_id","variables","is_default"],"title":"Prompt","description":"A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."}}},"additionalProperties":false,"required":["data"],"title":"ListPromptsResponse","description":"Response model to list prompts."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-scoring-functions.api.mdx b/docs/docs/api/list-all-scoring-functions.api.mdx index b21e700fe..df1cfc623 100644 --- a/docs/docs/api/list-all-scoring-functions.api.mdx +++ b/docs/docs/api/list-all-scoring-functions.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/scoring-functions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all scoring functions. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-session-s-of-a-given-agent.api.mdx b/docs/docs/api/list-all-session-s-of-a-given-agent.api.mdx index 250392cd7..d2518ef5d 100644 --- a/docs/docs/api/list-all-session-s-of-a-given-agent.api.mdx +++ b/docs/docs/api/list-all-session-s-of-a-given-agent.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/sessions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all session(s) of a given agent. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-shields.api.mdx b/docs/docs/api/list-all-shields.api.mdx index f788fe92f..767b5ae16 100644 --- a/docs/docs/api/list-all-shields.api.mdx +++ b/docs/docs/api/list-all-shields.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/shields"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all shields. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-tools-in-the-runtime.api.mdx b/docs/docs/api/list-all-tools-in-the-runtime.api.mdx index 4ad941227..33a4332f4 100644 --- a/docs/docs/api/list-all-tools-in-the-runtime.api.mdx +++ b/docs/docs/api/list-all-tools-in-the-runtime.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/tool-runtime/list-tools"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all tools in the runtime. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-vector-databases.api.mdx b/docs/docs/api/list-all-vector-databases.api.mdx index 199426317..819f9a248 100644 --- a/docs/docs/api/list-all-vector-databases.api.mdx +++ b/docs/docs/api/list-all-vector-databases.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/vector-dbs"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all vector databases. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-all-versions-of-a-specific-prompt.api.mdx b/docs/docs/api/list-all-versions-of-a-specific-prompt.api.mdx index d3a317cb8..1465377c9 100644 --- a/docs/docs/api/list-all-versions-of-a-specific-prompt.api.mdx +++ b/docs/docs/api/list-all-versions-of-a-specific-prompt.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts/{prompt_id}/versions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List all versions of a specific prompt. - + - + '"},"variables":{"type":"array","items":{"type":"string"},"description":"List of prompt variable names that can be used in the prompt template"},"is_default":{"type":"boolean","default":false,"description":"Boolean indicating whether this version is the default version for this prompt"}},"additionalProperties":false,"required":["version","prompt_id","variables","is_default"],"title":"Prompt","description":"A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."}}},"additionalProperties":false,"required":["data"],"title":"ListPromptsResponse","description":"Response model to list prompts."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-files-in-a-vector-store.api.mdx b/docs/docs/api/list-files-in-a-vector-store.api.mdx index 488104504..47d10e7ea 100644 --- a/docs/docs/api/list-files-in-a-vector-store.api.mdx +++ b/docs/docs/api/list-files-in-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/files"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List files in a vector store. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-input-items-for-a-given-open-ai-response.api.mdx b/docs/docs/api/list-input-items-for-a-given-open-ai-response.api.mdx index c92e313db..1ff7513c8 100644 --- a/docs/docs/api/list-input-items-for-a-given-open-ai-response.api.mdx +++ b/docs/docs/api/list-input-items-for-a-given-open-ai-response.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/responses/{response_id}/input_items"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List input items for a given OpenAI response. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-models-using-the-open-ai-api.api.mdx b/docs/docs/api/list-models-using-the-open-ai-api.api.mdx index 747355a64..98f75d975 100644 --- a/docs/docs/api/list-models-using-the-open-ai-api.api.mdx +++ b/docs/docs/api/list-models-using-the-open-ai-api.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/models"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List models using the OpenAI API. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-tool-groups-with-optional-provider.api.mdx b/docs/docs/api/list-tool-groups-with-optional-provider.api.mdx index 08b8d678d..21a53afd2 100644 --- a/docs/docs/api/list-tool-groups-with-optional-provider.api.mdx +++ b/docs/docs/api/list-tool-groups-with-optional-provider.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/toolgroups"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List tool groups with optional provider. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/list-tools-with-optional-tool-group.api.mdx b/docs/docs/api/list-tools-with-optional-tool-group.api.mdx index d2e1a12c6..2ee513440 100644 --- a/docs/docs/api/list-tools-with-optional-tool-group.api.mdx +++ b/docs/docs/api/list-tools-with-optional-tool-group.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/tools"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ List tools with optional tool group. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/llama-stack-specification.info.mdx b/docs/docs/api/llama-stack-specification.info.mdx index ee6278e5b..e979bccfe 100644 --- a/docs/docs/api/llama-stack-specification.info.mdx +++ b/docs/docs/api/llama-stack-specification.info.mdx @@ -24,7 +24,7 @@ import Export from "@theme/ApiExplorer/Export"; url={"https://raw.githubusercontent.com/meta-llama/llama-stack/main/docs/static/llama-stack-spec.yaml"} proxy={undefined} > - + - + @@ -49,14 +49,14 @@ Log an event. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/models.tag.mdx b/docs/docs/api/models.tag.mdx index 88f1833b0..355cfc0cb 100644 --- a/docs/docs/api/models.tag.mdx +++ b/docs/docs/api/models.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/post-training-coming-soon.tag.mdx b/docs/docs/api/post-training-coming-soon.tag.mdx index f950b4c51..ff77c132d 100644 --- a/docs/docs/api/post-training-coming-soon.tag.mdx +++ b/docs/docs/api/post-training-coming-soon.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/prompts.tag.mdx b/docs/docs/api/prompts.tag.mdx index ed3266928..668884fdc 100644 --- a/docs/docs/api/prompts.tag.mdx +++ b/docs/docs/api/prompts.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/providers.tag.mdx b/docs/docs/api/providers.tag.mdx index a7d24bac4..d4b418326 100644 --- a/docs/docs/api/providers.tag.mdx +++ b/docs/docs/api/providers.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/query-chunks-from-a-vector-database.api.mdx b/docs/docs/api/query-chunks-from-a-vector-database.api.mdx index 1962c1843..051ae995b 100644 --- a/docs/docs/api/query-chunks-from-a-vector-database.api.mdx +++ b/docs/docs/api/query-chunks-from-a-vector-database.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/vector-io/query"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Query chunks from a vector database. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/query-metrics.api.mdx b/docs/docs/api/query-metrics.api.mdx index 640e7cbd4..68e85d103 100644 --- a/docs/docs/api/query-metrics.api.mdx +++ b/docs/docs/api/query-metrics.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/metrics/{metric_name}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Query metrics. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/query-spans.api.mdx b/docs/docs/api/query-spans.api.mdx index e515a6fb4..e62e3bc1c 100644 --- a/docs/docs/api/query-spans.api.mdx +++ b/docs/docs/api/query-spans.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/spans"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Query spans. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/query-the-rag-system-for-context-typically-invoked-by-the-agent.api.mdx b/docs/docs/api/query-the-rag-system-for-context-typically-invoked-by-the-agent.api.mdx index bb4d8268d..f43d1a7c1 100644 --- a/docs/docs/api/query-the-rag-system-for-context-typically-invoked-by-the-agent.api.mdx +++ b/docs/docs/api/query-the-rag-system-for-context-typically-invoked-by-the-agent.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/tool-runtime/rag-tool/query"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Query the RAG system for context; typically invoked by the agent. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/query-traces.api.mdx b/docs/docs/api/query-traces.api.mdx index f39801fee..a12cafad4 100644 --- a/docs/docs/api/query-traces.api.mdx +++ b/docs/docs/api/query-traces.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/traces"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Query traces. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-benchmark.api.mdx b/docs/docs/api/register-a-benchmark.api.mdx index 5a8e66885..4a7eaa250 100644 --- a/docs/docs/api/register-a-benchmark.api.mdx +++ b/docs/docs/api/register-a-benchmark.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a benchmark. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-model.api.mdx b/docs/docs/api/register-a-model.api.mdx index 9fb8e2d01..44254072f 100644 --- a/docs/docs/api/register-a-model.api.mdx +++ b/docs/docs/api/register-a-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/models"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a model. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-new-dataset.api.mdx b/docs/docs/api/register-a-new-dataset.api.mdx index ff46036ea..94f28adc5 100644 --- a/docs/docs/api/register-a-new-dataset.api.mdx +++ b/docs/docs/api/register-a-new-dataset.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/datasets"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a new dataset. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-scoring-function.api.mdx b/docs/docs/api/register-a-scoring-function.api.mdx index ffab8f3d8..a0a6a8c39 100644 --- a/docs/docs/api/register-a-scoring-function.api.mdx +++ b/docs/docs/api/register-a-scoring-function.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/scoring-functions"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a scoring function. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-shield.api.mdx b/docs/docs/api/register-a-shield.api.mdx index 728a44ac4..9f745cf7f 100644 --- a/docs/docs/api/register-a-shield.api.mdx +++ b/docs/docs/api/register-a-shield.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/shields"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a shield. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-tool-group.api.mdx b/docs/docs/api/register-a-tool-group.api.mdx index 1cb99be63..0bf75b34d 100644 --- a/docs/docs/api/register-a-tool-group.api.mdx +++ b/docs/docs/api/register-a-tool-group.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/toolgroups"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a tool group. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/register-a-vector-database.api.mdx b/docs/docs/api/register-a-vector-database.api.mdx index 6d1c89893..914a30648 100644 --- a/docs/docs/api/register-a-vector-database.api.mdx +++ b/docs/docs/api/register-a-vector-database.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/vector-dbs"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Register a vector database. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/rerank-a-list-of-documents-based-on-their-relevance-to-a-query.api.mdx b/docs/docs/api/rerank-a-list-of-documents-based-on-their-relevance-to-a-query.api.mdx index d3af97bb1..764258597 100644 --- a/docs/docs/api/rerank-a-list-of-documents-based-on-their-relevance-to-a-query.api.mdx +++ b/docs/docs/api/rerank-a-list-of-documents-based-on-their-relevance-to-a-query.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/inference/rerank"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Rerank a list of documents based on their relevance to a query. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/resume-an-agent-turn-with-executed-tool-call-responses.api.mdx b/docs/docs/api/resume-an-agent-turn-with-executed-tool-call-responses.api.mdx index e3e5fc9dc..4074c8074 100644 --- a/docs/docs/api/resume-an-agent-turn-with-executed-tool-call-responses.api.mdx +++ b/docs/docs/api/resume-an-agent-turn-with-executed-tool-call-responses.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume"} context={"endpoint"} > - + @@ -50,14 +50,14 @@ When a Turn has the status `awaiting_input` due to pending input from client sid - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieve-an-agent-session-by-its-id.api.mdx b/docs/docs/api/retrieve-an-agent-session-by-its-id.api.mdx index baf34dd40..9d0fbaad8 100644 --- a/docs/docs/api/retrieve-an-agent-session-by-its-id.api.mdx +++ b/docs/docs/api/retrieve-an-agent-session-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session/{session_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieve an agent session by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieve-an-agent-step-by-its-id.api.mdx b/docs/docs/api/retrieve-an-agent-step-by-its-id.api.mdx index 922d72895..2ffd370b3 100644 --- a/docs/docs/api/retrieve-an-agent-step-by-its-id.api.mdx +++ b/docs/docs/api/retrieve-an-agent-step-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieve an agent step by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieve-an-agent-turn-by-its-id.api.mdx b/docs/docs/api/retrieve-an-agent-turn-by-its-id.api.mdx index fed139fab..c3ea4e4ce 100644 --- a/docs/docs/api/retrieve-an-agent-turn-by-its-id.api.mdx +++ b/docs/docs/api/retrieve-an-agent-turn-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieve an agent turn by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieve-an-open-ai-response-by-its-id.api.mdx b/docs/docs/api/retrieve-an-open-ai-response-by-its-id.api.mdx index 195082c9f..54ffb2e4f 100644 --- a/docs/docs/api/retrieve-an-open-ai-response-by-its-id.api.mdx +++ b/docs/docs/api/retrieve-an-open-ai-response-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/responses/{response_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieve an OpenAI response by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieves-a-vector-store-file.api.mdx b/docs/docs/api/retrieves-a-vector-store-file.api.mdx index db95ad909..d42ab2d9d 100644 --- a/docs/docs/api/retrieves-a-vector-store-file.api.mdx +++ b/docs/docs/api/retrieves-a-vector-store-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieves a vector store file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieves-a-vector-store.api.mdx b/docs/docs/api/retrieves-a-vector-store.api.mdx index f3b5a0a24..167de5086 100644 --- a/docs/docs/api/retrieves-a-vector-store.api.mdx +++ b/docs/docs/api/retrieves-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieves a vector store. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/retrieves-the-contents-of-a-vector-store-file.api.mdx b/docs/docs/api/retrieves-the-contents-of-a-vector-store-file.api.mdx index 9633e3af1..f09856771 100644 --- a/docs/docs/api/retrieves-the-contents-of-a-vector-store-file.api.mdx +++ b/docs/docs/api/retrieves-the-contents-of-a-vector-store-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Retrieves the contents of a vector store file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/returns-a-list-of-files-that-belong-to-the-users-organization.api.mdx b/docs/docs/api/returns-a-list-of-files-that-belong-to-the-users-organization.api.mdx index 659281a9c..17fe7084d 100644 --- a/docs/docs/api/returns-a-list-of-files-that-belong-to-the-users-organization.api.mdx +++ b/docs/docs/api/returns-a-list-of-files-that-belong-to-the-users-organization.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/files"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Returns a list of files that belong to the user's organization. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/returns-a-list-of-vector-stores.api.mdx b/docs/docs/api/returns-a-list-of-vector-stores.api.mdx index 0ed69e664..1bb923d1e 100644 --- a/docs/docs/api/returns-a-list-of-vector-stores.api.mdx +++ b/docs/docs/api/returns-a-list-of-vector-stores.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Returns a list of vector stores. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/returns-information-about-a-specific-file.api.mdx b/docs/docs/api/returns-information-about-a-specific-file.api.mdx index b42e0dee6..351153b33 100644 --- a/docs/docs/api/returns-information-about-a-specific-file.api.mdx +++ b/docs/docs/api/returns-information-about-a-specific-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/files/{file_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Returns information about a specific file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/returns-the-contents-of-the-specified-file.api.mdx b/docs/docs/api/returns-the-contents-of-the-specified-file.api.mdx index cb7ec20a7..e4ef53a71 100644 --- a/docs/docs/api/returns-the-contents-of-the-specified-file.api.mdx +++ b/docs/docs/api/returns-the-contents-of-the-specified-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/files/{file_id}/content"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Returns the contents of the specified file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/run-a-shield.api.mdx b/docs/docs/api/run-a-shield.api.mdx index 41f59674c..0a631c73f 100644 --- a/docs/docs/api/run-a-shield.api.mdx +++ b/docs/docs/api/run-a-shield.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/safety/run-shield"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Run a shield. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/run-a-tool-with-the-given-arguments.api.mdx b/docs/docs/api/run-a-tool-with-the-given-arguments.api.mdx index d033ece7e..5ec2e741f 100644 --- a/docs/docs/api/run-a-tool-with-the-given-arguments.api.mdx +++ b/docs/docs/api/run-a-tool-with-the-given-arguments.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/tool-runtime/invoke"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Run a tool with the given arguments. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/run-an-evaluation-on-a-benchmark.api.mdx b/docs/docs/api/run-an-evaluation-on-a-benchmark.api.mdx index 21f87ed9d..75540f561 100644 --- a/docs/docs/api/run-an-evaluation-on-a-benchmark.api.mdx +++ b/docs/docs/api/run-an-evaluation-on-a-benchmark.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}/jobs"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Run an evaluation on a benchmark. - + = p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"system_message":{"type":"object","properties":{"role":{"type":"string","const":"system","default":"system","description":"Must be \"system\" to identify this as a system message"},"content":{"description":"The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions).","oneOf":[{"type":"string"},{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"}}],"title":"InterleavedContent"}},"additionalProperties":false,"required":["role","content"],"title":"SystemMessage","description":"A system message providing instructions or context to the model."}},"additionalProperties":false,"required":["type","model","sampling_params"],"title":"ModelCandidate","description":"A model candidate for evaluation."},{"type":"object","properties":{"type":{"type":"string","const":"agent","default":"agent"},"config":{"description":"The configuration for the agent candidate.","type":"object","properties":{"sampling_params":{"type":"object","properties":{"strategy":{"description":"The sampling strategy.","oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"input_shields":{"type":"array","items":{"type":"string"}},"output_shields":{"type":"array","items":{"type":"string"}},"toolgroups":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","properties":{"name":{"type":"string"},"args":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}}},"additionalProperties":false,"required":["name","args"],"title":"AgentToolGroupWithArgs"}],"title":"AgentTool"}},"client_tools":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool"},"description":{"type":"string","description":"(Optional) Human-readable description of what the tool does"},"parameters":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the parameter"},"parameter_type":{"type":"string","description":"Type of the parameter (e.g., string, integer)"},"description":{"type":"string","description":"Human-readable description of what the parameter does"},"required":{"type":"boolean","default":true,"description":"Whether this parameter is required for tool invocation"},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}],"description":"(Optional) Default value for the parameter if not provided"}},"additionalProperties":false,"required":["name","parameter_type","description","required"],"title":"ToolParameter","description":"Parameter definition for a tool."},"description":"(Optional) List of parameters this tool accepts"},"metadata":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"(Optional) Additional metadata about the tool"}},"additionalProperties":false,"required":["name"],"title":"ToolDef","description":"Tool definition used in runtime contexts."}},"tool_choice":{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.","deprecated":true},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"title":"ToolPromptFormat","description":"Prompt format for calling custom / zero shot tools.","deprecated":true},"tool_config":{"type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."},"max_infer_iters":{"type":"integer","default":10},"model":{"type":"string","description":"The model identifier to use for the agent"},"instructions":{"type":"string","description":"The system instructions for the agent"},"name":{"type":"string","description":"Optional name for the agent, used in telemetry and identification"},"enable_session_persistence":{"type":"boolean","default":false,"description":"Optional flag indicating whether session data has to be persisted"},"response_format":{"description":"Optional response format configuration","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"}},"additionalProperties":false,"required":["model","instructions"],"title":"AgentConfig"}},"additionalProperties":false,"required":["type","config"],"title":"AgentCandidate","description":"An agent candidate for evaluation."}],"discriminator":{"propertyName":"type","mapping":{"model":{"type":"object","properties":{"type":{"type":"string","const":"model","default":"model"},"model":{"type":"string","description":"The model ID to evaluate."},"sampling_params":{"type":"object","properties":{"strategy":{"description":"The sampling strategy.","oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"system_message":{"type":"object","properties":{"role":{"type":"string","const":"system","default":"system","description":"Must be \"system\" to identify this as a system message"},"content":{"description":"The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions).","oneOf":[{"type":"string"},{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"},{"type":"array","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}],"discriminator":{"propertyName":"type","mapping":{"image":{"type":"object","properties":{"type":{"type":"string","const":"image","default":"image","description":"Discriminator type of the content item. Always \"image\""},"image":{"type":"object","properties":{"url":{"description":"A URL of the image or data URL in the format of data:image/{type};base64,{data}. Note that URL could have length limits.","type":"object","properties":{"uri":{"type":"string","description":"The URL string pointing to the resource"}},"additionalProperties":false,"required":["uri"],"title":"URL"},"data":{"type":"string","contentEncoding":"base64","description":"base64 encoded image data as string"}},"additionalProperties":false,"description":"Image as a base64 encoded string or an URL"}},"additionalProperties":false,"required":["type","image"],"title":"ImageContentItem","description":"A image content item"},"text":{"type":"object","properties":{"type":{"type":"string","const":"text","default":"text","description":"Discriminator type of the content item. Always \"text\""},"text":{"type":"string","description":"Text content"}},"additionalProperties":false,"required":["type","text"],"title":"TextContentItem","description":"A text content item"}}},"title":"InterleavedContentItem"}}],"title":"InterleavedContent"}},"additionalProperties":false,"required":["role","content"],"title":"SystemMessage","description":"A system message providing instructions or context to the model."}},"additionalProperties":false,"required":["type","model","sampling_params"],"title":"ModelCandidate","description":"A model candidate for evaluation."},"agent":{"type":"object","properties":{"type":{"type":"string","const":"agent","default":"agent"},"config":{"description":"The configuration for the agent candidate.","type":"object","properties":{"sampling_params":{"type":"object","properties":{"strategy":{"description":"The sampling strategy.","oneOf":[{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}],"discriminator":{"propertyName":"type","mapping":{"greedy":{"type":"object","properties":{"type":{"type":"string","const":"greedy","default":"greedy","description":"Must be \"greedy\" to identify this sampling strategy"}},"additionalProperties":false,"required":["type"],"title":"GreedySamplingStrategy","description":"Greedy sampling strategy that selects the highest probability token at each step."},"top_p":{"type":"object","properties":{"type":{"type":"string","const":"top_p","default":"top_p","description":"Must be \"top_p\" to identify this sampling strategy"},"temperature":{"type":"number","description":"Controls randomness in sampling. Higher values increase randomness"},"top_p":{"type":"number","default":0.95,"description":"Cumulative probability threshold for nucleus sampling. Defaults to 0.95"}},"additionalProperties":false,"required":["type"],"title":"TopPSamplingStrategy","description":"Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."},"top_k":{"type":"object","properties":{"type":{"type":"string","const":"top_k","default":"top_k","description":"Must be \"top_k\" to identify this sampling strategy"},"top_k":{"type":"integer","description":"Number of top tokens to consider for sampling. Must be at least 1"}},"additionalProperties":false,"required":["type","top_k"],"title":"TopKSamplingStrategy","description":"Top-k sampling strategy that restricts sampling to the k most likely tokens."}}},"title":"SamplingStrategy"},"max_tokens":{"type":"integer","default":0,"description":"The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."},"repetition_penalty":{"type":"number","default":1,"description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."},"stop":{"type":"array","items":{"type":"string"},"description":"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"additionalProperties":false,"required":["strategy"],"title":"SamplingParams","description":"Sampling parameters."},"input_shields":{"type":"array","items":{"type":"string"}},"output_shields":{"type":"array","items":{"type":"string"}},"toolgroups":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","properties":{"name":{"type":"string"},"args":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]}}},"additionalProperties":false,"required":["name","args"],"title":"AgentToolGroupWithArgs"}],"title":"AgentTool"}},"client_tools":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the tool"},"description":{"type":"string","description":"(Optional) Human-readable description of what the tool does"},"parameters":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Name of the parameter"},"parameter_type":{"type":"string","description":"Type of the parameter (e.g., string, integer)"},"description":{"type":"string","description":"Human-readable description of what the parameter does"},"required":{"type":"boolean","default":true,"description":"Whether this parameter is required for tool invocation"},"default":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}],"description":"(Optional) Default value for the parameter if not provided"}},"additionalProperties":false,"required":["name","parameter_type","description","required"],"title":"ToolParameter","description":"Parameter definition for a tool."},"description":"(Optional) List of parameters this tool accepts"},"metadata":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"(Optional) Additional metadata about the tool"}},"additionalProperties":false,"required":["name"],"title":"ToolDef","description":"Tool definition used in runtime contexts."}},"tool_choice":{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.","deprecated":true},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"title":"ToolPromptFormat","description":"Prompt format for calling custom / zero shot tools.","deprecated":true},"tool_config":{"type":"object","properties":{"tool_choice":{"oneOf":[{"type":"string","enum":["auto","required","none"],"title":"ToolChoice","description":"Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."},{"type":"string"}],"default":"auto","description":"(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."},"tool_prompt_format":{"type":"string","enum":["json","function_tag","python_list"],"description":"(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."},"system_message_behavior":{"type":"string","enum":["append","replace"],"description":"(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.","default":"append"}},"additionalProperties":false,"title":"ToolConfig","description":"Configuration for tool use."},"max_infer_iters":{"type":"integer","default":10},"model":{"type":"string","description":"The model identifier to use for the agent"},"instructions":{"type":"string","description":"The system instructions for the agent"},"name":{"type":"string","description":"Optional name for the agent, used in telemetry and identification"},"enable_session_persistence":{"type":"boolean","default":false,"description":"Optional flag indicating whether session data has to be persisted"},"response_format":{"description":"Optional response format configuration","oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}],"discriminator":{"propertyName":"type","mapping":{"json_schema":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"json_schema\" to identify this format type","const":"json_schema","default":"json_schema"},"json_schema":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model."}},"additionalProperties":false,"required":["type","json_schema"],"title":"JsonSchemaResponseFormat","description":"Configuration for JSON schema-guided response generation."},"grammar":{"type":"object","properties":{"type":{"type":"string","enum":["json_schema","grammar"],"description":"Must be \"grammar\" to identify this format type","const":"grammar","default":"grammar"},"bnf":{"type":"object","additionalProperties":{"oneOf":[{"type":"null"},{"type":"boolean"},{"type":"number"},{"type":"string"},{"type":"array"},{"type":"object"}]},"description":"The BNF grammar specification the response should conform to"}},"additionalProperties":false,"required":["type","bnf"],"title":"GrammarResponseFormat","description":"Configuration for grammar-guided response generation."}}},"title":"ResponseFormat"}},"additionalProperties":false,"required":["model","instructions"],"title":"AgentConfig"}},"additionalProperties":false,"required":["type","config"],"title":"AgentCandidate","description":"An agent candidate for evaluation."}}},"title":"EvalCandidate"},"scoring_params":{"type":"object","additionalProperties":{"oneOf":[{"type":"object","properties":{"type":{"const":"llm_as_judge","default":"llm_as_judge","description":"The type of scoring function parameters, always llm_as_judge","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"judge_model":{"type":"string","description":"Identifier of the LLM model to use as a judge for scoring"},"prompt_template":{"type":"string","description":"(Optional) Custom prompt template for the judge model"},"judge_score_regexes":{"type":"array","items":{"type":"string"},"description":"Regexes to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","judge_model","judge_score_regexes","aggregation_functions"],"title":"LLMAsJudgeScoringFnParams","description":"Parameters for LLM-as-judge scoring function configuration."},{"type":"object","properties":{"type":{"const":"regex_parser","default":"regex_parser","description":"The type of scoring function parameters, always regex_parser","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"parsing_regexes":{"type":"array","items":{"type":"string"},"description":"Regex to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","parsing_regexes","aggregation_functions"],"title":"RegexParserScoringFnParams","description":"Parameters for regex parser scoring function configuration."},{"type":"object","properties":{"type":{"const":"basic","default":"basic","description":"The type of scoring function parameters, always basic","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","aggregation_functions"],"title":"BasicScoringFnParams","description":"Parameters for basic scoring function configuration."}],"discriminator":{"propertyName":"type","mapping":{"llm_as_judge":{"type":"object","properties":{"type":{"const":"llm_as_judge","default":"llm_as_judge","description":"The type of scoring function parameters, always llm_as_judge","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"judge_model":{"type":"string","description":"Identifier of the LLM model to use as a judge for scoring"},"prompt_template":{"type":"string","description":"(Optional) Custom prompt template for the judge model"},"judge_score_regexes":{"type":"array","items":{"type":"string"},"description":"Regexes to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","judge_model","judge_score_regexes","aggregation_functions"],"title":"LLMAsJudgeScoringFnParams","description":"Parameters for LLM-as-judge scoring function configuration."},"regex_parser":{"type":"object","properties":{"type":{"const":"regex_parser","default":"regex_parser","description":"The type of scoring function parameters, always regex_parser","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"parsing_regexes":{"type":"array","items":{"type":"string"},"description":"Regex to extract the answer from generated response"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","parsing_regexes","aggregation_functions"],"title":"RegexParserScoringFnParams","description":"Parameters for regex parser scoring function configuration."},"basic":{"type":"object","properties":{"type":{"const":"basic","default":"basic","description":"The type of scoring function parameters, always basic","type":"string","enum":["llm_as_judge","regex_parser","basic"],"title":"ScoringFnParamsType"},"aggregation_functions":{"type":"array","items":{"type":"string","enum":["average","weighted_average","median","categorical_count","accuracy"],"title":"AggregationFunctionType","description":"Types of aggregation functions for scoring results."},"description":"Aggregation functions to apply to the scores of each row"}},"additionalProperties":false,"required":["type","aggregation_functions"],"title":"BasicScoringFnParams","description":"Parameters for basic scoring function configuration."}}},"title":"ScoringFnParams"},"description":"Map between scoring function id and parameters for each scoring function you want to run"},"num_examples":{"type":"integer","description":"(Optional) The number of examples to evaluate. If not provided, all examples in the dataset will be evaluated"}},"additionalProperties":false,"required":["eval_candidate","scoring_params"],"title":"BenchmarkConfig"}},"additionalProperties":false,"required":["benchmark_config"],"title":"RunEvalRequest"}}},"required":true}} > - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/run-preference-optimization-of-a-model.api.mdx b/docs/docs/api/run-preference-optimization-of-a-model.api.mdx index b8528eaba..5b87bda75 100644 --- a/docs/docs/api/run-preference-optimization-of-a-model.api.mdx +++ b/docs/docs/api/run-preference-optimization-of-a-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/post-training/preference-optimize"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Run preference optimization of a model. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/run-supervised-fine-tuning-of-a-model.api.mdx b/docs/docs/api/run-supervised-fine-tuning-of-a-model.api.mdx index ad7b6be5e..f7caeb0aa 100644 --- a/docs/docs/api/run-supervised-fine-tuning-of-a-model.api.mdx +++ b/docs/docs/api/run-supervised-fine-tuning-of-a-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/post-training/supervised-fine-tune"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Run supervised fine-tuning of a model. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/safety.tag.mdx b/docs/docs/api/safety.tag.mdx index cace48bd8..2d509b670 100644 --- a/docs/docs/api/safety.tag.mdx +++ b/docs/docs/api/safety.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/save-spans-to-a-dataset.api.mdx b/docs/docs/api/save-spans-to-a-dataset.api.mdx index 32ea8595a..c64bed807 100644 --- a/docs/docs/api/save-spans-to-a-dataset.api.mdx +++ b/docs/docs/api/save-spans-to-a-dataset.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/telemetry/spans/export"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Save spans to a dataset. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/score-a-batch-of-rows.api.mdx b/docs/docs/api/score-a-batch-of-rows.api.mdx index bcef0a084..f39911880 100644 --- a/docs/docs/api/score-a-batch-of-rows.api.mdx +++ b/docs/docs/api/score-a-batch-of-rows.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/scoring/score-batch"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Score a batch of rows. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/score-a-list-of-rows.api.mdx b/docs/docs/api/score-a-list-of-rows.api.mdx index 60b7e2849..75b2f35ed 100644 --- a/docs/docs/api/score-a-list-of-rows.api.mdx +++ b/docs/docs/api/score-a-list-of-rows.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/scoring/score"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Score a list of rows. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/scoring-functions.tag.mdx b/docs/docs/api/scoring-functions.tag.mdx index 16d365057..38391ac3a 100644 --- a/docs/docs/api/scoring-functions.tag.mdx +++ b/docs/docs/api/scoring-functions.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/scoring.tag.mdx b/docs/docs/api/scoring.tag.mdx index 1b1cf65a3..fa0083014 100644 --- a/docs/docs/api/scoring.tag.mdx +++ b/docs/docs/api/scoring.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/search-for-chunks-in-a-vector-store.api.mdx b/docs/docs/api/search-for-chunks-in-a-vector-store.api.mdx index daf375e32..4d4295d6c 100644 --- a/docs/docs/api/search-for-chunks-in-a-vector-store.api.mdx +++ b/docs/docs/api/search-for-chunks-in-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/search"} context={"endpoint"} > - + @@ -50,14 +50,14 @@ Searches a vector store for relevant chunks based on a query and optional file a - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/set-which-version-of-a-prompt-should-be-the-default-in-get-prompt-latest.api.mdx b/docs/docs/api/set-which-version-of-a-prompt-should-be-the-default-in-get-prompt-latest.api.mdx index e4173f72f..a836b6592 100644 --- a/docs/docs/api/set-which-version-of-a-prompt-should-be-the-default-in-get-prompt-latest.api.mdx +++ b/docs/docs/api/set-which-version-of-a-prompt-should-be-the-default-in-get-prompt-latest.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts/{prompt_id}/set-default-version"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Set which version of a prompt should be the default in get_prompt (latest). - + - + '"},"variables":{"type":"array","items":{"type":"string"},"description":"List of prompt variable names that can be used in the prompt template"},"is_default":{"type":"boolean","default":false,"description":"Boolean indicating whether this version is the default version for this prompt"}},"additionalProperties":false,"required":["version","prompt_id","variables","is_default"],"title":"Prompt","description":"A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/shields.tag.mdx b/docs/docs/api/shields.tag.mdx index b5590a67c..4ca1df409 100644 --- a/docs/docs/api/shields.tag.mdx +++ b/docs/docs/api/shields.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/synthetic-data-generation-coming-soon.tag.mdx b/docs/docs/api/synthetic-data-generation-coming-soon.tag.mdx index d170b1454..0d1771bee 100644 --- a/docs/docs/api/synthetic-data-generation-coming-soon.tag.mdx +++ b/docs/docs/api/synthetic-data-generation-coming-soon.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/telemetry.tag.mdx b/docs/docs/api/telemetry.tag.mdx index bd1b2e08c..5ec6c2dfc 100644 --- a/docs/docs/api/telemetry.tag.mdx +++ b/docs/docs/api/telemetry.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/tool-groups.tag.mdx b/docs/docs/api/tool-groups.tag.mdx index 8a5e857f7..3fcb9cc88 100644 --- a/docs/docs/api/tool-groups.tag.mdx +++ b/docs/docs/api/tool-groups.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/tool-runtime.tag.mdx b/docs/docs/api/tool-runtime.tag.mdx index 5304b2b44..aa26332e1 100644 --- a/docs/docs/api/tool-runtime.tag.mdx +++ b/docs/docs/api/tool-runtime.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-benchmark.api.mdx b/docs/docs/api/unregister-a-benchmark.api.mdx index a061a8935..8356808bb 100644 --- a/docs/docs/api/unregister-a-benchmark.api.mdx +++ b/docs/docs/api/unregister-a-benchmark.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/eval/benchmarks/{benchmark_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a benchmark. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-dataset-by-its-id.api.mdx b/docs/docs/api/unregister-a-dataset-by-its-id.api.mdx index b79d3bc9c..d390191ec 100644 --- a/docs/docs/api/unregister-a-dataset-by-its-id.api.mdx +++ b/docs/docs/api/unregister-a-dataset-by-its-id.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/datasets/{dataset_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a dataset by its ID. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-model.api.mdx b/docs/docs/api/unregister-a-model.api.mdx index 6fe2e6eeb..a88274512 100644 --- a/docs/docs/api/unregister-a-model.api.mdx +++ b/docs/docs/api/unregister-a-model.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/models/{model_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a model. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-scoring-function.api.mdx b/docs/docs/api/unregister-a-scoring-function.api.mdx index ebada9184..b1a54323c 100644 --- a/docs/docs/api/unregister-a-scoring-function.api.mdx +++ b/docs/docs/api/unregister-a-scoring-function.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/scoring-functions/{scoring_fn_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a scoring function. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-shield.api.mdx b/docs/docs/api/unregister-a-shield.api.mdx index 921eab201..c066a7b64 100644 --- a/docs/docs/api/unregister-a-shield.api.mdx +++ b/docs/docs/api/unregister-a-shield.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/shields/{identifier}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a shield. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-tool-group.api.mdx b/docs/docs/api/unregister-a-tool-group.api.mdx index 4b193dff0..f19bd9479 100644 --- a/docs/docs/api/unregister-a-tool-group.api.mdx +++ b/docs/docs/api/unregister-a-tool-group.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/toolgroups/{toolgroup_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a tool group. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/unregister-a-vector-database.api.mdx b/docs/docs/api/unregister-a-vector-database.api.mdx index bbb8d6c95..9ec16a0db 100644 --- a/docs/docs/api/unregister-a-vector-database.api.mdx +++ b/docs/docs/api/unregister-a-vector-database.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/vector-dbs/{vector_db_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Unregister a vector database. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/update-an-existing-prompt-increments-version.api.mdx b/docs/docs/api/update-an-existing-prompt-increments-version.api.mdx index adac12b60..1bfd6913b 100644 --- a/docs/docs/api/update-an-existing-prompt-increments-version.api.mdx +++ b/docs/docs/api/update-an-existing-prompt-increments-version.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/prompts/{prompt_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Update an existing prompt (increments version). - + - + '"},"variables":{"type":"array","items":{"type":"string"},"description":"List of prompt variable names that can be used in the prompt template"},"is_default":{"type":"boolean","default":false,"description":"Boolean indicating whether this version is the default version for this prompt"}},"additionalProperties":false,"required":["version","prompt_id","variables","is_default"],"title":"Prompt","description":"A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack."}}}},"400":{"description":"The request was invalid or malformed","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":400,"title":"Bad Request","detail":"The request was invalid or malformed"}}}},"429":{"description":"The client has sent too many requests in a given amount of time","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":429,"title":"Too Many Requests","detail":"You have exceeded the rate limit. Please try again later."}}}},"500":{"description":"The server encountered an unexpected error","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":500,"title":"Internal Server Error","detail":"An unexpected error occurred. Our team has been notified."}}}},"default":{"description":"An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"status":{"type":"integer","description":"HTTP status code"},"title":{"type":"string","description":"Error title, a short summary of the error which is invariant for an error type"},"detail":{"type":"string","description":"Error detail, a longer human-readable description of the error"},"instance":{"type":"string","description":"(Optional) A URL which can be used to retrieve more information about the specific occurrence of the error"}},"additionalProperties":false,"required":["status","title","detail"],"title":"Error","description":"Error response from the API. Roughly follows RFC 7807."},"example":{"status":0,"title":"Error","detail":"An unexpected error occurred"}}}}}} > - + - - - \ No newline at end of file diff --git a/docs/docs/api/updates-a-vector-store-file.api.mdx b/docs/docs/api/updates-a-vector-store-file.api.mdx index 67cc32b94..1ec5d5756 100644 --- a/docs/docs/api/updates-a-vector-store-file.api.mdx +++ b/docs/docs/api/updates-a-vector-store-file.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Updates a vector store file. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/updates-a-vector-store.api.mdx b/docs/docs/api/updates-a-vector-store.api.mdx index 2cf20b975..723deb173 100644 --- a/docs/docs/api/updates-a-vector-store.api.mdx +++ b/docs/docs/api/updates-a-vector-store.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/vector_stores/{vector_store_id}"} context={"endpoint"} > - + @@ -49,14 +49,14 @@ Updates a vector store. - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/upload-a-file-that-can-be-used-across-various-endpoints.api.mdx b/docs/docs/api/upload-a-file-that-can-be-used-across-various-endpoints.api.mdx index b2cf521e3..67e454f3a 100644 --- a/docs/docs/api/upload-a-file-that-can-be-used-across-various-endpoints.api.mdx +++ b/docs/docs/api/upload-a-file-that-can-be-used-across-various-endpoints.api.mdx @@ -31,7 +31,7 @@ import Heading from "@theme/Heading"; path={"/v1/openai/v1/files"} context={"endpoint"} > - + @@ -53,14 +53,14 @@ The file upload should be a multipart form request with: - + - + - + - - - \ No newline at end of file diff --git a/docs/docs/api/vector-d-bs.tag.mdx b/docs/docs/api/vector-d-bs.tag.mdx index bc6812ca5..82edbd3dc 100644 --- a/docs/docs/api/vector-d-bs.tag.mdx +++ b/docs/docs/api/vector-d-bs.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file diff --git a/docs/docs/api/vector-io.tag.mdx b/docs/docs/api/vector-io.tag.mdx index b81e4bdfb..b2b5479b3 100644 --- a/docs/docs/api/vector-io.tag.mdx +++ b/docs/docs/api/vector-io.tag.mdx @@ -17,4 +17,3 @@ import {useCurrentSidebarCategory} from '@docusaurus/theme-common'; ``` - \ No newline at end of file