mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
chore: add batches to openapi schema (#3980)
# What does this PR do? While working on https://github.com/llamastack/llama-stack/pull/3944 I realized that the batches API wasn't generated. Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han
GitHub
parent
19d85003de
commit
b4ea05ada9
8 changed files with 3812 additions and 0 deletions
638
docs/static/llama-stack-spec.html
vendored
638
docs/static/llama-stack-spec.html
vendored
|
|
@ -40,6 +40,193 @@
|
|||
}
|
||||
],
|
||||
"paths": {
|
||||
"/v1/batches": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A list of batch objects.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ListBatchesResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Batches"
|
||||
],
|
||||
"summary": "List all batches for the current user.",
|
||||
"description": "List all batches for the current user.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "after",
|
||||
"in": "query",
|
||||
"description": "A cursor for pagination; returns batches after this batch ID.",
|
||||
"required": false,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "limit",
|
||||
"in": "query",
|
||||
"description": "Number of batches to return (default 20, max 100).",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "integer"
|
||||
}
|
||||
}
|
||||
],
|
||||
"deprecated": false
|
||||
},
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The created batch object.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Batch"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Batches"
|
||||
],
|
||||
"summary": "Create a new batch for processing multiple API requests.",
|
||||
"description": "Create a new batch for processing multiple API requests.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/CreateBatchRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
},
|
||||
"deprecated": false
|
||||
}
|
||||
},
|
||||
"/v1/batches/{batch_id}": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The batch object.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Batch"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Batches"
|
||||
],
|
||||
"summary": "Retrieve information about a specific batch.",
|
||||
"description": "Retrieve information about a specific batch.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "batch_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the batch to retrieve.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"deprecated": false
|
||||
}
|
||||
},
|
||||
"/v1/batches/{batch_id}/cancel": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The updated batch object.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Batch"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Batches"
|
||||
],
|
||||
"summary": "Cancel a batch that is in progress.",
|
||||
"description": "Cancel a batch that is in progress.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "batch_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the batch to cancel.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"deprecated": false
|
||||
}
|
||||
},
|
||||
"/v1/chat/completions": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -4005,6 +4192,451 @@
|
|||
"title": "Error",
|
||||
"description": "Error response from the API. Roughly follows RFC 7807."
|
||||
},
|
||||
"ListBatchesResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "list",
|
||||
"default": "list"
|
||||
},
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"completion_window": {
|
||||
"type": "string"
|
||||
},
|
||||
"created_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"endpoint": {
|
||||
"type": "string"
|
||||
},
|
||||
"input_file_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "batch"
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"validating",
|
||||
"failed",
|
||||
"in_progress",
|
||||
"finalizing",
|
||||
"completed",
|
||||
"expired",
|
||||
"cancelling",
|
||||
"cancelled"
|
||||
]
|
||||
},
|
||||
"cancelled_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"cancelling_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"completed_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"error_file_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"errors": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string"
|
||||
},
|
||||
"line": {
|
||||
"type": "integer"
|
||||
},
|
||||
"message": {
|
||||
"type": "string"
|
||||
},
|
||||
"param": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"title": "BatchError"
|
||||
}
|
||||
},
|
||||
"object": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"title": "Errors"
|
||||
},
|
||||
"expired_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"expires_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"failed_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"finalizing_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"in_progress_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"model": {
|
||||
"type": "string"
|
||||
},
|
||||
"output_file_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"request_counts": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"completed": {
|
||||
"type": "integer"
|
||||
},
|
||||
"failed": {
|
||||
"type": "integer"
|
||||
},
|
||||
"total": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"completed",
|
||||
"failed",
|
||||
"total"
|
||||
],
|
||||
"title": "BatchRequestCounts"
|
||||
},
|
||||
"usage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"input_tokens": {
|
||||
"type": "integer"
|
||||
},
|
||||
"input_tokens_details": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"cached_tokens": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"cached_tokens"
|
||||
],
|
||||
"title": "InputTokensDetails"
|
||||
},
|
||||
"output_tokens": {
|
||||
"type": "integer"
|
||||
},
|
||||
"output_tokens_details": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"reasoning_tokens": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"reasoning_tokens"
|
||||
],
|
||||
"title": "OutputTokensDetails"
|
||||
},
|
||||
"total_tokens": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"input_tokens",
|
||||
"input_tokens_details",
|
||||
"output_tokens",
|
||||
"output_tokens_details",
|
||||
"total_tokens"
|
||||
],
|
||||
"title": "BatchUsage"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"completion_window",
|
||||
"created_at",
|
||||
"endpoint",
|
||||
"input_file_id",
|
||||
"object",
|
||||
"status"
|
||||
],
|
||||
"title": "Batch"
|
||||
}
|
||||
},
|
||||
"first_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"last_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"has_more": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"object",
|
||||
"data",
|
||||
"has_more"
|
||||
],
|
||||
"title": "ListBatchesResponse",
|
||||
"description": "Response containing a list of batch objects."
|
||||
},
|
||||
"CreateBatchRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"input_file_id": {
|
||||
"type": "string",
|
||||
"description": "The ID of an uploaded file containing requests for the batch."
|
||||
},
|
||||
"endpoint": {
|
||||
"type": "string",
|
||||
"description": "The endpoint to be used for all requests in the batch."
|
||||
},
|
||||
"completion_window": {
|
||||
"type": "string",
|
||||
"const": "24h",
|
||||
"description": "The time window within which the batch should be processed."
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Optional metadata for the batch."
|
||||
},
|
||||
"idempotency_key": {
|
||||
"type": "string",
|
||||
"description": "Optional idempotency key. When provided, enables idempotent behavior."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"input_file_id",
|
||||
"endpoint",
|
||||
"completion_window"
|
||||
],
|
||||
"title": "CreateBatchRequest"
|
||||
},
|
||||
"Batch": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"completion_window": {
|
||||
"type": "string"
|
||||
},
|
||||
"created_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"endpoint": {
|
||||
"type": "string"
|
||||
},
|
||||
"input_file_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "batch"
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"validating",
|
||||
"failed",
|
||||
"in_progress",
|
||||
"finalizing",
|
||||
"completed",
|
||||
"expired",
|
||||
"cancelling",
|
||||
"cancelled"
|
||||
]
|
||||
},
|
||||
"cancelled_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"cancelling_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"completed_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"error_file_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"errors": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string"
|
||||
},
|
||||
"line": {
|
||||
"type": "integer"
|
||||
},
|
||||
"message": {
|
||||
"type": "string"
|
||||
},
|
||||
"param": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"title": "BatchError"
|
||||
}
|
||||
},
|
||||
"object": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"title": "Errors"
|
||||
},
|
||||
"expired_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"expires_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"failed_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"finalizing_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"in_progress_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"model": {
|
||||
"type": "string"
|
||||
},
|
||||
"output_file_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"request_counts": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"completed": {
|
||||
"type": "integer"
|
||||
},
|
||||
"failed": {
|
||||
"type": "integer"
|
||||
},
|
||||
"total": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"completed",
|
||||
"failed",
|
||||
"total"
|
||||
],
|
||||
"title": "BatchRequestCounts"
|
||||
},
|
||||
"usage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"input_tokens": {
|
||||
"type": "integer"
|
||||
},
|
||||
"input_tokens_details": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"cached_tokens": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"cached_tokens"
|
||||
],
|
||||
"title": "InputTokensDetails"
|
||||
},
|
||||
"output_tokens": {
|
||||
"type": "integer"
|
||||
},
|
||||
"output_tokens_details": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"reasoning_tokens": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"reasoning_tokens"
|
||||
],
|
||||
"title": "OutputTokensDetails"
|
||||
},
|
||||
"total_tokens": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"input_tokens",
|
||||
"input_tokens_details",
|
||||
"output_tokens",
|
||||
"output_tokens_details",
|
||||
"total_tokens"
|
||||
],
|
||||
"title": "BatchUsage"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"completion_window",
|
||||
"created_at",
|
||||
"endpoint",
|
||||
"input_file_id",
|
||||
"object",
|
||||
"status"
|
||||
],
|
||||
"title": "Batch"
|
||||
},
|
||||
"Order": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
|
|
@ -13289,6 +13921,11 @@
|
|||
"description": "APIs for creating and interacting with agentic systems.\n\n## Responses API\n\nThe Responses API provides OpenAI-compatible functionality with enhanced capabilities for dynamic, stateful interactions.\n\n> **✅ STABLE**: This API is production-ready with backward compatibility guarantees. Recommended for production applications.\n\n### ✅ Supported Tools\n\nThe Responses API supports the following tool types:\n\n- **`web_search`**: Search the web for current information and real-time data\n- **`file_search`**: Search through uploaded files and vector stores\n - Supports dynamic `vector_store_ids` per call\n - Compatible with OpenAI file search patterns\n- **`function`**: Call custom functions with JSON schema validation\n- **`mcp_tool`**: Model Context Protocol integration\n\n### ✅ Supported Fields & Features\n\n**Core Capabilities:**\n- **Dynamic Configuration**: Switch models, vector stores, and tools per request without pre-configuration\n- **Conversation Branching**: Use `previous_response_id` to branch conversations and explore different paths\n- **Rich Annotations**: Automatic file citations, URL citations, and container file citations\n- **Status Tracking**: Monitor tool call execution status and handle failures gracefully\n\n### 🚧 Work in Progress\n\n- Full real-time response streaming support\n- `tool_choice` parameter\n- `max_tool_calls` parameter\n- Built-in tools (code interpreter, containers API)\n- Safety & guardrails\n- `reasoning` capabilities\n- `service_tier`\n- `logprobs`\n- `max_output_tokens`\n- `metadata` handling\n- `instructions`\n- `incomplete_details`\n- `background`",
|
||||
"x-displayName": "Agents"
|
||||
},
|
||||
{
|
||||
"name": "Batches",
|
||||
"description": "The API is designed to allow use of openai client libraries for seamless integration.\n\nThis API provides the following extensions:\n - idempotent batch creation\n\nNote: This API is currently under active development and may undergo changes.",
|
||||
"x-displayName": "The Batches API enables efficient processing of multiple requests in a single operation, particularly useful for processing large datasets, batch evaluation workflows, and cost-effective inference at scale."
|
||||
},
|
||||
{
|
||||
"name": "Conversations",
|
||||
"description": "Protocol for conversation management operations.",
|
||||
|
|
@ -13362,6 +13999,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Conversations",
|
||||
"Files",
|
||||
"Inference",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue