mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
Merge remote-tracking branch 'upstream/main' into feat/gunicorn-production-server
This commit is contained in:
Roy Belio
commit
b060f73e6d
70 changed files with 46290 additions and 1133 deletions
1036
docs/notebooks/llamastack_agents_getting_started_examples.ipynb
Normal file
1036
docs/notebooks/llamastack_agents_getting_started_examples.ipynb
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -242,15 +242,6 @@ const sidebars: SidebarsConfig = {
|
|||
'providers/eval/remote_nvidia'
|
||||
],
|
||||
},
|
||||
{
|
||||
type: 'category',
|
||||
label: 'Telemetry',
|
||||
collapsed: true,
|
||||
items: [
|
||||
'providers/telemetry/index',
|
||||
'providers/telemetry/inline_meta-reference'
|
||||
],
|
||||
},
|
||||
{
|
||||
type: 'category',
|
||||
label: 'Batches',
|
||||
|
|
|
|||
638
docs/static/deprecated-llama-stack-spec.html
vendored
638
docs/static/deprecated-llama-stack-spec.html
vendored
|
|
@ -1414,6 +1414,193 @@
|
|||
"deprecated": true
|
||||
}
|
||||
},
|
||||
"/v1/openai/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": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Batches"
|
||||
],
|
||||
"summary": "List all batches for the current user.",
|
||||
"description": "List all batches for the current user.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "after",
|
||||
"in": "query",
|
||||
"description": "A cursor for pagination; returns batches after this batch ID.",
|
||||
"required": false,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "limit",
|
||||
"in": "query",
|
||||
"description": "Number of batches to return (default 20, max 100).",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "integer"
|
||||
}
|
||||
}
|
||||
],
|
||||
"deprecated": true
|
||||
},
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The created batch object.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$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": {
|
||||
"$ref": "#/components/schemas/CreateBatchRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
},
|
||||
"deprecated": true
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/batches/{batch_id}": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "The batch object.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$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": true
|
||||
}
|
||||
},
|
||||
"/v1/openai/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": true
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/chat/completions": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -6401,6 +6588,451 @@
|
|||
"title": "Job",
|
||||
"description": "A job execution instance with status tracking."
|
||||
},
|
||||
"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": [
|
||||
|
|
@ -13505,6 +14137,11 @@
|
|||
"description": "APIs for creating and interacting with agentic systems.\n\n## Deprecated APIs\n\n> **⚠️ DEPRECATED**: These APIs are provided for migration reference and will be removed in future versions. Not recommended for new projects.\n\n### Migration Guidance\n\nIf you are using deprecated versions of the Agents or Responses APIs, please migrate to:\n\n- **Responses API**: Use the stable v1 Responses API endpoints\n",
|
||||
"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": "Benchmarks",
|
||||
"description": ""
|
||||
|
|
@ -13555,6 +14192,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Benchmarks",
|
||||
"DatasetIO",
|
||||
"Datasets",
|
||||
|
|
|
|||
474
docs/static/deprecated-llama-stack-spec.yaml
vendored
474
docs/static/deprecated-llama-stack-spec.yaml
vendored
|
|
@ -1012,6 +1012,141 @@ paths:
|
|||
schema:
|
||||
type: string
|
||||
deprecated: true
|
||||
/v1/openai/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: true
|
||||
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: true
|
||||
/v1/openai/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: true
|
||||
/v1/openai/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: true
|
||||
/v1/openai/v1/chat/completions:
|
||||
get:
|
||||
responses:
|
||||
|
|
@ -4736,6 +4871,331 @@ components:
|
|||
title: Job
|
||||
description: >-
|
||||
A job execution instance with status tracking.
|
||||
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:
|
||||
|
|
@ -10263,6 +10723,19 @@ tags:
|
|||
|
||||
- **Responses API**: Use the stable v1 Responses API endpoints
|
||||
x-displayName: Agents
|
||||
- name: Batches
|
||||
description: >-
|
||||
The API is designed to allow use of openai client libraries for seamless integration.
|
||||
|
||||
|
||||
This API provides the following extensions:
|
||||
- idempotent batch creation
|
||||
|
||||
Note: 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: Benchmarks
|
||||
description: ''
|
||||
- name: DatasetIO
|
||||
|
|
@ -10308,6 +10781,7 @@ x-tagGroups:
|
|||
- name: Operations
|
||||
tags:
|
||||
- Agents
|
||||
- Batches
|
||||
- Benchmarks
|
||||
- DatasetIO
|
||||
- Datasets
|
||||
|
|
|
|||
647
docs/static/llama-stack-spec.html
vendored
647
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": [
|
||||
|
|
@ -11897,6 +12529,10 @@
|
|||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The content of the chunk, which can be interleaved text, images, or other types."
|
||||
},
|
||||
"chunk_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier for the chunk. Must be provided explicitly."
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
|
|
@ -11930,10 +12566,6 @@
|
|||
},
|
||||
"description": "Optional embedding for the chunk. If not provided, it will be computed later."
|
||||
},
|
||||
"stored_chunk_id": {
|
||||
"type": "string",
|
||||
"description": "The chunk ID that is stored in the vector database. Used for backend functionality."
|
||||
},
|
||||
"chunk_metadata": {
|
||||
"$ref": "#/components/schemas/ChunkMetadata",
|
||||
"description": "Metadata for the chunk that will NOT be used in the context during inference. The `chunk_metadata` is required backend functionality."
|
||||
|
|
@ -11942,6 +12574,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"content",
|
||||
"chunk_id",
|
||||
"metadata"
|
||||
],
|
||||
"title": "Chunk",
|
||||
|
|
@ -13288,6 +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.",
|
||||
|
|
@ -13361,6 +13999,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Conversations",
|
||||
"Files",
|
||||
"Inference",
|
||||
|
|
|
|||
483
docs/static/llama-stack-spec.yaml
vendored
483
docs/static/llama-stack-spec.yaml
vendored
|
|
@ -12,6 +12,141 @@ info:
|
|||
servers:
|
||||
- url: http://any-hosted-llama-stack.com
|
||||
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:
|
||||
|
|
@ -2999,6 +3134,331 @@ components:
|
|||
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:
|
||||
|
|
@ -9045,6 +9505,10 @@ components:
|
|||
description: >-
|
||||
The content of the chunk, which can be interleaved text, images, or other
|
||||
types.
|
||||
chunk_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier for the chunk. Must be provided explicitly.
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
|
|
@ -9065,10 +9529,6 @@ components:
|
|||
description: >-
|
||||
Optional embedding for the chunk. If not provided, it will be computed
|
||||
later.
|
||||
stored_chunk_id:
|
||||
type: string
|
||||
description: >-
|
||||
The chunk ID that is stored in the vector database. Used for backend functionality.
|
||||
chunk_metadata:
|
||||
$ref: '#/components/schemas/ChunkMetadata'
|
||||
description: >-
|
||||
|
|
@ -9077,6 +9537,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- content
|
||||
- chunk_id
|
||||
- metadata
|
||||
title: Chunk
|
||||
description: >-
|
||||
|
|
@ -10143,6 +10604,19 @@ tags:
|
|||
|
||||
- `background`
|
||||
x-displayName: Agents
|
||||
- name: Batches
|
||||
description: >-
|
||||
The API is designed to allow use of openai client libraries for seamless integration.
|
||||
|
||||
|
||||
This API provides the following extensions:
|
||||
- idempotent batch creation
|
||||
|
||||
Note: This API is currently under active development and may undergo changes.
|
||||
x-displayName: >-
|
||||
The Batches API enables efficient processing of multiple requests in a single
|
||||
operation, particularly useful for processing large datasets, batch evaluation
|
||||
workflows, and cost-effective inference at scale.
|
||||
- name: Conversations
|
||||
description: >-
|
||||
Protocol for conversation management operations.
|
||||
|
|
@ -10205,6 +10679,7 @@ x-tagGroups:
|
|||
- name: Operations
|
||||
tags:
|
||||
- Agents
|
||||
- Batches
|
||||
- Conversations
|
||||
- Files
|
||||
- Inference
|
||||
|
|
|
|||
647
docs/static/stainless-llama-stack-spec.html
vendored
647
docs/static/stainless-llama-stack-spec.html
vendored
|
|
@ -40,6 +40,193 @@
|
|||
}
|
||||
],
|
||||
"paths": {
|
||||
"/v1/batches": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A list of batch objects.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$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": {
|
||||
|
|
@ -5677,6 +5864,451 @@
|
|||
"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": [
|
||||
|
|
@ -13569,6 +14201,10 @@
|
|||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The content of the chunk, which can be interleaved text, images, or other types."
|
||||
},
|
||||
"chunk_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier for the chunk. Must be provided explicitly."
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
|
|
@ -13602,10 +14238,6 @@
|
|||
},
|
||||
"description": "Optional embedding for the chunk. If not provided, it will be computed later."
|
||||
},
|
||||
"stored_chunk_id": {
|
||||
"type": "string",
|
||||
"description": "The chunk ID that is stored in the vector database. Used for backend functionality."
|
||||
},
|
||||
"chunk_metadata": {
|
||||
"$ref": "#/components/schemas/ChunkMetadata",
|
||||
"description": "Metadata for the chunk that will NOT be used in the context during inference. The `chunk_metadata` is required backend functionality."
|
||||
|
|
@ -13614,6 +14246,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"content",
|
||||
"chunk_id",
|
||||
"metadata"
|
||||
],
|
||||
"title": "Chunk",
|
||||
|
|
@ -17960,6 +18593,11 @@
|
|||
"description": "APIs for creating and interacting with agentic systems.",
|
||||
"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": "Benchmarks",
|
||||
"description": ""
|
||||
|
|
@ -18054,6 +18692,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Benchmarks",
|
||||
"Conversations",
|
||||
"DatasetIO",
|
||||
|
|
|
|||
483
docs/static/stainless-llama-stack-spec.yaml
vendored
483
docs/static/stainless-llama-stack-spec.yaml
vendored
|
|
@ -15,6 +15,141 @@ info:
|
|||
servers:
|
||||
- url: http://any-hosted-llama-stack.com
|
||||
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:
|
||||
|
|
@ -4212,6 +4347,331 @@ components:
|
|||
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:
|
||||
|
|
@ -10258,6 +10718,10 @@ components:
|
|||
description: >-
|
||||
The content of the chunk, which can be interleaved text, images, or other
|
||||
types.
|
||||
chunk_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier for the chunk. Must be provided explicitly.
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
|
|
@ -10278,10 +10742,6 @@ components:
|
|||
description: >-
|
||||
Optional embedding for the chunk. If not provided, it will be computed
|
||||
later.
|
||||
stored_chunk_id:
|
||||
type: string
|
||||
description: >-
|
||||
The chunk ID that is stored in the vector database. Used for backend functionality.
|
||||
chunk_metadata:
|
||||
$ref: '#/components/schemas/ChunkMetadata'
|
||||
description: >-
|
||||
|
|
@ -10290,6 +10750,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- content
|
||||
- chunk_id
|
||||
- metadata
|
||||
title: Chunk
|
||||
description: >-
|
||||
|
|
@ -13527,6 +13988,19 @@ tags:
|
|||
description: >-
|
||||
APIs for creating and interacting with agentic systems.
|
||||
x-displayName: Agents
|
||||
- name: Batches
|
||||
description: >-
|
||||
The API is designed to allow use of openai client libraries for seamless integration.
|
||||
|
||||
|
||||
This API provides the following extensions:
|
||||
- idempotent batch creation
|
||||
|
||||
Note: 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: Benchmarks
|
||||
description: ''
|
||||
- name: Conversations
|
||||
|
|
@ -13601,6 +14075,7 @@ x-tagGroups:
|
|||
- name: Operations
|
||||
tags:
|
||||
- Agents
|
||||
- Batches
|
||||
- Benchmarks
|
||||
- Conversations
|
||||
- DatasetIO
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue