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 elasticsearch-integration
This commit is contained in:
Enrico Zimuel
commit
2407115ee8
1050 changed files with 65153 additions and 2821 deletions
|
|
@ -58,13 +58,21 @@ storage:
|
|||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/sqlstore.db
|
||||
references:
|
||||
stores:
|
||||
metadata:
|
||||
backend: kv_default
|
||||
namespace: registry
|
||||
inference:
|
||||
backend: sql_default
|
||||
table_name: inference_store
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
backend: sql_default
|
||||
table_name: openai_conversations
|
||||
prompts:
|
||||
backend: kv_default
|
||||
namespace: prompts
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -113,13 +113,21 @@ data:
|
|||
db: ${env.POSTGRES_DB:=llamastack}
|
||||
user: ${env.POSTGRES_USER:=llamastack}
|
||||
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
||||
references:
|
||||
stores:
|
||||
metadata:
|
||||
backend: kv_default
|
||||
namespace: registry
|
||||
inference:
|
||||
backend: sql_default
|
||||
table_name: inference_store
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
backend: sql_default
|
||||
table_name: openai_conversations
|
||||
prompts:
|
||||
backend: kv_default
|
||||
namespace: prompts
|
||||
models:
|
||||
- metadata:
|
||||
embedding_dimension: 768
|
||||
|
|
|
|||
|
|
@ -106,6 +106,9 @@ storage:
|
|||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
prompts:
|
||||
namespace: prompts
|
||||
backend: kv_default
|
||||
registered_resources:
|
||||
models:
|
||||
- metadata:
|
||||
|
|
|
|||
|
|
@ -79,6 +79,33 @@ docker run \
|
|||
--port $LLAMA_STACK_PORT
|
||||
```
|
||||
|
||||
### Via Docker with Custom Run Configuration
|
||||
|
||||
You can also run the Docker container with a custom run configuration file by mounting it into the container:
|
||||
|
||||
```bash
|
||||
# Set the path to your custom run.yaml file
|
||||
CUSTOM_RUN_CONFIG=/path/to/your/custom-run.yaml
|
||||
LLAMA_STACK_PORT=8321
|
||||
|
||||
docker run \
|
||||
-it \
|
||||
--pull always \
|
||||
--gpu all \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
-v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml \
|
||||
-e RUN_CONFIG_PATH=/app/custom-run.yaml \
|
||||
llamastack/distribution-meta-reference-gpu \
|
||||
--port $LLAMA_STACK_PORT
|
||||
```
|
||||
|
||||
**Note**: The run configuration must be mounted into the container before it can be used. The `-v` flag mounts your local file into the container, and the `RUN_CONFIG_PATH` environment variable tells the entrypoint script which configuration to use.
|
||||
|
||||
Available run configurations for this distribution:
|
||||
- `run.yaml`
|
||||
- `run-with-safety.yaml`
|
||||
|
||||
### Via venv
|
||||
|
||||
Make sure you have the Llama Stack CLI available.
|
||||
|
|
|
|||
|
|
@ -127,13 +127,39 @@ docker run \
|
|||
-it \
|
||||
--pull always \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
-v ~/.llama:/root/.llama \
|
||||
-e NVIDIA_API_KEY=$NVIDIA_API_KEY \
|
||||
llamastack/distribution-nvidia \
|
||||
--config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT
|
||||
```
|
||||
|
||||
### Via Docker with Custom Run Configuration
|
||||
|
||||
You can also run the Docker container with a custom run configuration file by mounting it into the container:
|
||||
|
||||
```bash
|
||||
# Set the path to your custom run.yaml file
|
||||
CUSTOM_RUN_CONFIG=/path/to/your/custom-run.yaml
|
||||
LLAMA_STACK_PORT=8321
|
||||
|
||||
docker run \
|
||||
-it \
|
||||
--pull always \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
-v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml \
|
||||
-e RUN_CONFIG_PATH=/app/custom-run.yaml \
|
||||
-e NVIDIA_API_KEY=$NVIDIA_API_KEY \
|
||||
llamastack/distribution-nvidia \
|
||||
--port $LLAMA_STACK_PORT
|
||||
```
|
||||
|
||||
**Note**: The run configuration must be mounted into the container before it can be used. The `-v` flag mounts your local file into the container, and the `RUN_CONFIG_PATH` environment variable tells the entrypoint script which configuration to use.
|
||||
|
||||
Available run configurations for this distribution:
|
||||
- `run.yaml`
|
||||
- `run-with-safety.yaml`
|
||||
|
||||
### Via venv
|
||||
|
||||
If you've set up your local development environment, you can also install the distribution dependencies using your local virtual environment.
|
||||
|
|
|
|||
27
docs/docs/providers/files/remote_openai.mdx
Normal file
27
docs/docs/providers/files/remote_openai.mdx
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
---
|
||||
description: "OpenAI Files API provider for managing files through OpenAI's native file storage service."
|
||||
sidebar_label: Remote - Openai
|
||||
title: remote::openai
|
||||
---
|
||||
|
||||
# remote::openai
|
||||
|
||||
## Description
|
||||
|
||||
OpenAI Files API provider for managing files through OpenAI's native file storage service.
|
||||
|
||||
## Configuration
|
||||
|
||||
| Field | Type | Required | Default | Description |
|
||||
|-------|------|----------|---------|-------------|
|
||||
| `api_key` | `<class 'str'>` | No | | OpenAI API key for authentication |
|
||||
| `metadata_store` | `<class 'llama_stack.core.storage.datatypes.SqlStoreReference'>` | No | | SQL store configuration for file metadata |
|
||||
|
||||
## Sample Configuration
|
||||
|
||||
```yaml
|
||||
api_key: ${env.OPENAI_API_KEY}
|
||||
metadata_store:
|
||||
table_name: openai_files_metadata
|
||||
backend: sql_default
|
||||
```
|
||||
|
|
@ -20,6 +20,7 @@ NVIDIA inference provider for accessing NVIDIA NIM models and AI services.
|
|||
| `url` | `<class 'str'>` | No | https://integrate.api.nvidia.com | A base url for accessing the NVIDIA NIM |
|
||||
| `timeout` | `<class 'int'>` | No | 60 | Timeout for the HTTP requests |
|
||||
| `append_api_version` | `<class 'bool'>` | No | True | When set to false, the API version will not be appended to the base_url. By default, it is true. |
|
||||
| `rerank_model_to_url` | `dict[str, str` | No | `{'nv-rerank-qa-mistral-4b:1': 'https://ai.api.nvidia.com/v1/retrieval/nvidia/reranking', 'nvidia/nv-rerankqa-mistral-4b-v3': 'https://ai.api.nvidia.com/v1/retrieval/nvidia/nv-rerankqa-mistral-4b-v3/reranking', 'nvidia/llama-3.2-nv-rerankqa-1b-v2': 'https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-3_2-nv-rerankqa-1b-v2/reranking'}` | Mapping of rerank model identifiers to their API endpoints. |
|
||||
|
||||
## Sample Configuration
|
||||
|
||||
|
|
|
|||
|
|
@ -72,14 +72,14 @@ description: |
|
|||
Example with hybrid search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
||||
# Using RRF ranker
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={
|
||||
"mode": "hybrid",
|
||||
|
|
@ -91,7 +91,7 @@ description: |
|
|||
|
||||
# Using weighted ranker
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={
|
||||
"mode": "hybrid",
|
||||
|
|
@ -105,7 +105,7 @@ description: |
|
|||
Example with explicit vector search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
|
@ -114,7 +114,7 @@ description: |
|
|||
Example with keyword search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
|
@ -277,14 +277,14 @@ The SQLite-vec provider supports three search modes:
|
|||
Example with hybrid search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
||||
# Using RRF ranker
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={
|
||||
"mode": "hybrid",
|
||||
|
|
@ -296,7 +296,7 @@ response = await vector_io.query_chunks(
|
|||
|
||||
# Using weighted ranker
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={
|
||||
"mode": "hybrid",
|
||||
|
|
@ -310,7 +310,7 @@ response = await vector_io.query_chunks(
|
|||
Example with explicit vector search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
|
@ -319,7 +319,7 @@ response = await vector_io.query_chunks(
|
|||
Example with keyword search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
vector_store_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
|
|
|||
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',
|
||||
|
|
|
|||
741
docs/static/deprecated-llama-stack-spec.html
vendored
741
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": {
|
||||
|
|
@ -3901,7 +4088,6 @@
|
|||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"default": 0,
|
||||
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
|
||||
},
|
||||
"repetition_penalty": {
|
||||
|
|
@ -4391,7 +4577,7 @@
|
|||
"const": "memory_retrieval",
|
||||
"default": "memory_retrieval"
|
||||
},
|
||||
"vector_db_ids": {
|
||||
"vector_store_ids": {
|
||||
"type": "string",
|
||||
"description": "The IDs of the vector databases to retrieve context from."
|
||||
},
|
||||
|
|
@ -4405,7 +4591,7 @@
|
|||
"turn_id",
|
||||
"step_id",
|
||||
"step_type",
|
||||
"vector_db_ids",
|
||||
"vector_store_ids",
|
||||
"inserted_context"
|
||||
],
|
||||
"title": "MemoryRetrievalStep",
|
||||
|
|
@ -6402,6 +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": [
|
||||
|
|
@ -8527,29 +9158,14 @@
|
|||
"OpenAIResponseInput": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutput"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputFunctionToolCallOutput"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalRequest"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMessage"
|
||||
}
|
||||
|
|
@ -8592,16 +9208,53 @@
|
|||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContentImage"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContentFile"
|
||||
}
|
||||
],
|
||||
"discriminator": {
|
||||
"propertyName": "type",
|
||||
"mapping": {
|
||||
"input_text": "#/components/schemas/OpenAIResponseInputMessageContentText",
|
||||
"input_image": "#/components/schemas/OpenAIResponseInputMessageContentImage"
|
||||
"input_image": "#/components/schemas/OpenAIResponseInputMessageContentImage",
|
||||
"input_file": "#/components/schemas/OpenAIResponseInputMessageContentFile"
|
||||
}
|
||||
}
|
||||
},
|
||||
"OpenAIResponseInputMessageContentFile": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "input_file",
|
||||
"default": "input_file",
|
||||
"description": "The type of the input item. Always `input_file`."
|
||||
},
|
||||
"file_data": {
|
||||
"type": "string",
|
||||
"description": "The data of the file to be sent to the model."
|
||||
},
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The ID of the file to be sent to the model."
|
||||
},
|
||||
"file_url": {
|
||||
"type": "string",
|
||||
"description": "The URL of the file to be sent to the model."
|
||||
},
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The name of the file to be sent to the model."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseInputMessageContentFile",
|
||||
"description": "File content for input messages in OpenAI response format."
|
||||
},
|
||||
"OpenAIResponseInputMessageContentImage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -8629,6 +9282,10 @@
|
|||
"default": "input_image",
|
||||
"description": "Content type identifier, always \"input_image\""
|
||||
},
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The ID of the file to be sent to the model."
|
||||
},
|
||||
"image_url": {
|
||||
"type": "string",
|
||||
"description": "(Optional) URL of the image content"
|
||||
|
|
@ -8992,6 +9649,10 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) ID of the previous response in a conversation"
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Reference to a prompt template and its variables."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Current status of the response generation"
|
||||
|
|
@ -9416,6 +10077,32 @@
|
|||
"title": "OpenAIResponseOutputMessageWebSearchToolCall",
|
||||
"description": "Web search tool call output message for OpenAI responses."
|
||||
},
|
||||
"OpenAIResponsePrompt": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the prompt template"
|
||||
},
|
||||
"variables": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContent"
|
||||
},
|
||||
"description": "Dictionary of variable names to OpenAIResponseInputMessageContent structure for template substitution. The substitution values can either be strings, or other Response input types like images or files."
|
||||
},
|
||||
"version": {
|
||||
"type": "string",
|
||||
"description": "Version number of the prompt to use (defaults to latest if not specified)"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id"
|
||||
],
|
||||
"title": "OpenAIResponsePrompt",
|
||||
"description": "OpenAI compatible Prompt object that is used in OpenAI responses."
|
||||
},
|
||||
"OpenAIResponseText": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -9786,6 +10473,10 @@
|
|||
"type": "string",
|
||||
"description": "The underlying LLM used for completions."
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Prompt object with ID, version, and variables."
|
||||
},
|
||||
"instructions": {
|
||||
"type": "string"
|
||||
},
|
||||
|
|
@ -9874,6 +10565,10 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) ID of the previous response in a conversation"
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Reference to a prompt template and its variables."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Current status of the response generation"
|
||||
|
|
@ -13442,6 +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": ""
|
||||
|
|
@ -13492,6 +14192,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Benchmarks",
|
||||
"DatasetIO",
|
||||
"Datasets",
|
||||
|
|
|
|||
559
docs/static/deprecated-llama-stack-spec.yaml
vendored
559
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:
|
||||
|
|
@ -2862,7 +2997,6 @@ components:
|
|||
description: The sampling strategy.
|
||||
max_tokens:
|
||||
type: integer
|
||||
default: 0
|
||||
description: >-
|
||||
The maximum number of tokens that can be generated in the completion.
|
||||
The token count of your prompt plus max_tokens cannot exceed the model's
|
||||
|
|
@ -3253,7 +3387,7 @@ components:
|
|||
description: Type of the step in an agent turn.
|
||||
const: memory_retrieval
|
||||
default: memory_retrieval
|
||||
vector_db_ids:
|
||||
vector_store_ids:
|
||||
type: string
|
||||
description: >-
|
||||
The IDs of the vector databases to retrieve context from.
|
||||
|
|
@ -3266,7 +3400,7 @@ components:
|
|||
- turn_id
|
||||
- step_id
|
||||
- step_type
|
||||
- vector_db_ids
|
||||
- vector_store_ids
|
||||
- inserted_context
|
||||
title: MemoryRetrievalStep
|
||||
description: >-
|
||||
|
|
@ -4737,6 +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:
|
||||
|
|
@ -6370,14 +6829,9 @@ components:
|
|||
Error details for failed OpenAI response requests.
|
||||
OpenAIResponseInput:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMessage'
|
||||
"OpenAIResponseInputFunctionToolCallOutput":
|
||||
type: object
|
||||
|
|
@ -6408,11 +6862,44 @@ components:
|
|||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
|
||||
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
|
||||
input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile'
|
||||
OpenAIResponseInputMessageContentFile:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: input_file
|
||||
default: input_file
|
||||
description: >-
|
||||
The type of the input item. Always `input_file`.
|
||||
file_data:
|
||||
type: string
|
||||
description: >-
|
||||
The data of the file to be sent to the model.
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The ID of the file to be sent to the model.
|
||||
file_url:
|
||||
type: string
|
||||
description: >-
|
||||
The URL of the file to be sent to the model.
|
||||
filename:
|
||||
type: string
|
||||
description: >-
|
||||
The name of the file to be sent to the model.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: OpenAIResponseInputMessageContentFile
|
||||
description: >-
|
||||
File content for input messages in OpenAI response format.
|
||||
OpenAIResponseInputMessageContentImage:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -6433,6 +6920,10 @@ components:
|
|||
default: input_image
|
||||
description: >-
|
||||
Content type identifier, always "input_image"
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The ID of the file to be sent to the model.
|
||||
image_url:
|
||||
type: string
|
||||
description: (Optional) URL of the image content
|
||||
|
|
@ -6703,6 +7194,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) ID of the previous response in a conversation
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Reference to a prompt template and its variables.
|
||||
status:
|
||||
type: string
|
||||
description: >-
|
||||
|
|
@ -7042,6 +7537,30 @@ components:
|
|||
OpenAIResponseOutputMessageWebSearchToolCall
|
||||
description: >-
|
||||
Web search tool call output message for OpenAI responses.
|
||||
OpenAIResponsePrompt:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
description: Unique identifier of the prompt template
|
||||
variables:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/OpenAIResponseInputMessageContent'
|
||||
description: >-
|
||||
Dictionary of variable names to OpenAIResponseInputMessageContent structure
|
||||
for template substitution. The substitution values can either be strings,
|
||||
or other Response input types like images or files.
|
||||
version:
|
||||
type: string
|
||||
description: >-
|
||||
Version number of the prompt to use (defaults to latest if not specified)
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
title: OpenAIResponsePrompt
|
||||
description: >-
|
||||
OpenAI compatible Prompt object that is used in OpenAI responses.
|
||||
OpenAIResponseText:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -7299,6 +7818,10 @@ components:
|
|||
model:
|
||||
type: string
|
||||
description: The underlying LLM used for completions.
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Prompt object with ID, version, and variables.
|
||||
instructions:
|
||||
type: string
|
||||
previous_response_id:
|
||||
|
|
@ -7376,6 +7899,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) ID of the previous response in a conversation
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Reference to a prompt template and its variables.
|
||||
status:
|
||||
type: string
|
||||
description: >-
|
||||
|
|
@ -10196,6 +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
|
||||
|
|
@ -10241,6 +10781,7 @@ x-tagGroups:
|
|||
- name: Operations
|
||||
tags:
|
||||
- Agents
|
||||
- Batches
|
||||
- Benchmarks
|
||||
- DatasetIO
|
||||
- Datasets
|
||||
|
|
|
|||
|
|
@ -2376,7 +2376,6 @@
|
|||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"default": 0,
|
||||
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
|
||||
},
|
||||
"repetition_penalty": {
|
||||
|
|
@ -2866,7 +2865,7 @@
|
|||
"const": "memory_retrieval",
|
||||
"default": "memory_retrieval"
|
||||
},
|
||||
"vector_db_ids": {
|
||||
"vector_store_ids": {
|
||||
"type": "string",
|
||||
"description": "The IDs of the vector databases to retrieve context from."
|
||||
},
|
||||
|
|
@ -2880,7 +2879,7 @@
|
|||
"turn_id",
|
||||
"step_id",
|
||||
"step_type",
|
||||
"vector_db_ids",
|
||||
"vector_store_ids",
|
||||
"inserted_context"
|
||||
],
|
||||
"title": "MemoryRetrievalStep",
|
||||
|
|
|
|||
|
|
@ -1695,7 +1695,6 @@ components:
|
|||
description: The sampling strategy.
|
||||
max_tokens:
|
||||
type: integer
|
||||
default: 0
|
||||
description: >-
|
||||
The maximum number of tokens that can be generated in the completion.
|
||||
The token count of your prompt plus max_tokens cannot exceed the model's
|
||||
|
|
@ -2086,7 +2085,7 @@ components:
|
|||
description: Type of the step in an agent turn.
|
||||
const: memory_retrieval
|
||||
default: memory_retrieval
|
||||
vector_db_ids:
|
||||
vector_store_ids:
|
||||
type: string
|
||||
description: >-
|
||||
The IDs of the vector databases to retrieve context from.
|
||||
|
|
@ -2099,7 +2098,7 @@ components:
|
|||
- turn_id
|
||||
- step_id
|
||||
- step_type
|
||||
- vector_db_ids
|
||||
- vector_store_ids
|
||||
- inserted_context
|
||||
title: MemoryRetrievalStep
|
||||
description: >-
|
||||
|
|
|
|||
761
docs/static/llama-stack-spec.html
vendored
761
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": [
|
||||
|
|
@ -5696,16 +6328,53 @@
|
|||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContentImage"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContentFile"
|
||||
}
|
||||
],
|
||||
"discriminator": {
|
||||
"propertyName": "type",
|
||||
"mapping": {
|
||||
"input_text": "#/components/schemas/OpenAIResponseInputMessageContentText",
|
||||
"input_image": "#/components/schemas/OpenAIResponseInputMessageContentImage"
|
||||
"input_image": "#/components/schemas/OpenAIResponseInputMessageContentImage",
|
||||
"input_file": "#/components/schemas/OpenAIResponseInputMessageContentFile"
|
||||
}
|
||||
}
|
||||
},
|
||||
"OpenAIResponseInputMessageContentFile": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "input_file",
|
||||
"default": "input_file",
|
||||
"description": "The type of the input item. Always `input_file`."
|
||||
},
|
||||
"file_data": {
|
||||
"type": "string",
|
||||
"description": "The data of the file to be sent to the model."
|
||||
},
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The ID of the file to be sent to the model."
|
||||
},
|
||||
"file_url": {
|
||||
"type": "string",
|
||||
"description": "The URL of the file to be sent to the model."
|
||||
},
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The name of the file to be sent to the model."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseInputMessageContentFile",
|
||||
"description": "File content for input messages in OpenAI response format."
|
||||
},
|
||||
"OpenAIResponseInputMessageContentImage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -5733,6 +6402,10 @@
|
|||
"default": "input_image",
|
||||
"description": "Content type identifier, always \"input_image\""
|
||||
},
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The ID of the file to be sent to the model."
|
||||
},
|
||||
"image_url": {
|
||||
"type": "string",
|
||||
"description": "(Optional) URL of the image content"
|
||||
|
|
@ -7305,29 +7978,14 @@
|
|||
"OpenAIResponseInput": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutput"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputFunctionToolCallOutput"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalRequest"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMessage"
|
||||
}
|
||||
|
|
@ -7536,6 +8194,10 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) ID of the previous response in a conversation"
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Reference to a prompt template and its variables."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Current status of the response generation"
|
||||
|
|
@ -7631,6 +8293,32 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"OpenAIResponsePrompt": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the prompt template"
|
||||
},
|
||||
"variables": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContent"
|
||||
},
|
||||
"description": "Dictionary of variable names to OpenAIResponseInputMessageContent structure for template substitution. The substitution values can either be strings, or other Response input types like images or files."
|
||||
},
|
||||
"version": {
|
||||
"type": "string",
|
||||
"description": "Version number of the prompt to use (defaults to latest if not specified)"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id"
|
||||
],
|
||||
"title": "OpenAIResponsePrompt",
|
||||
"description": "OpenAI compatible Prompt object that is used in OpenAI responses."
|
||||
},
|
||||
"OpenAIResponseText": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -8001,6 +8689,10 @@
|
|||
"type": "string",
|
||||
"description": "The underlying LLM used for completions."
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Prompt object with ID, version, and variables."
|
||||
},
|
||||
"instructions": {
|
||||
"type": "string"
|
||||
},
|
||||
|
|
@ -8089,6 +8781,10 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) ID of the previous response in a conversation"
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Reference to a prompt template and its variables."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Current status of the response generation"
|
||||
|
|
@ -11427,7 +12123,7 @@
|
|||
},
|
||||
"description": "List of documents to index in the RAG system"
|
||||
},
|
||||
"vector_db_id": {
|
||||
"vector_store_id": {
|
||||
"type": "string",
|
||||
"description": "ID of the vector database to store the document embeddings"
|
||||
},
|
||||
|
|
@ -11439,7 +12135,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"documents",
|
||||
"vector_db_id",
|
||||
"vector_store_id",
|
||||
"chunk_size_in_tokens"
|
||||
],
|
||||
"title": "InsertRequest"
|
||||
|
|
@ -11630,7 +12326,7 @@
|
|||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The query content to search for in the indexed documents"
|
||||
},
|
||||
"vector_db_ids": {
|
||||
"vector_store_ids": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
|
|
@ -11645,7 +12341,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"content",
|
||||
"vector_db_ids"
|
||||
"vector_store_ids"
|
||||
],
|
||||
"title": "QueryRequest"
|
||||
},
|
||||
|
|
@ -11833,6 +12529,10 @@
|
|||
"$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": {
|
||||
|
|
@ -11866,10 +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."
|
||||
|
|
@ -11878,6 +12574,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"content",
|
||||
"chunk_id",
|
||||
"metadata"
|
||||
],
|
||||
"title": "Chunk",
|
||||
|
|
@ -11938,7 +12635,7 @@
|
|||
"InsertChunksRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"vector_db_id": {
|
||||
"vector_store_id": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the vector database to insert the chunks into."
|
||||
},
|
||||
|
|
@ -11956,7 +12653,7 @@
|
|||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"vector_db_id",
|
||||
"vector_store_id",
|
||||
"chunks"
|
||||
],
|
||||
"title": "InsertChunksRequest"
|
||||
|
|
@ -11964,7 +12661,7 @@
|
|||
"QueryChunksRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"vector_db_id": {
|
||||
"vector_store_id": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the vector database to query."
|
||||
},
|
||||
|
|
@ -12001,7 +12698,7 @@
|
|||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"vector_db_id",
|
||||
"vector_store_id",
|
||||
"query"
|
||||
],
|
||||
"title": "QueryChunksRequest"
|
||||
|
|
@ -13224,6 +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.",
|
||||
|
|
@ -13297,6 +13999,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Conversations",
|
||||
"Files",
|
||||
"Inference",
|
||||
|
|
|
|||
579
docs/static/llama-stack-spec.yaml
vendored
579
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:
|
||||
|
|
@ -4261,11 +4721,44 @@ components:
|
|||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
|
||||
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
|
||||
input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile'
|
||||
OpenAIResponseInputMessageContentFile:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: input_file
|
||||
default: input_file
|
||||
description: >-
|
||||
The type of the input item. Always `input_file`.
|
||||
file_data:
|
||||
type: string
|
||||
description: >-
|
||||
The data of the file to be sent to the model.
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The ID of the file to be sent to the model.
|
||||
file_url:
|
||||
type: string
|
||||
description: >-
|
||||
The URL of the file to be sent to the model.
|
||||
filename:
|
||||
type: string
|
||||
description: >-
|
||||
The name of the file to be sent to the model.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: OpenAIResponseInputMessageContentFile
|
||||
description: >-
|
||||
File content for input messages in OpenAI response format.
|
||||
OpenAIResponseInputMessageContentImage:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -4286,6 +4779,10 @@ components:
|
|||
default: input_image
|
||||
description: >-
|
||||
Content type identifier, always "input_image"
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The ID of the file to be sent to the model.
|
||||
image_url:
|
||||
type: string
|
||||
description: (Optional) URL of the image content
|
||||
|
|
@ -5522,14 +6019,9 @@ components:
|
|||
Error details for failed OpenAI response requests.
|
||||
OpenAIResponseInput:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMessage'
|
||||
OpenAIResponseInputToolFileSearch:
|
||||
type: object
|
||||
|
|
@ -5685,6 +6177,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) ID of the previous response in a conversation
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Reference to a prompt template and its variables.
|
||||
status:
|
||||
type: string
|
||||
description: >-
|
||||
|
|
@ -5758,6 +6254,30 @@ components:
|
|||
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
|
||||
OpenAIResponsePrompt:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
description: Unique identifier of the prompt template
|
||||
variables:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/OpenAIResponseInputMessageContent'
|
||||
description: >-
|
||||
Dictionary of variable names to OpenAIResponseInputMessageContent structure
|
||||
for template substitution. The substitution values can either be strings,
|
||||
or other Response input types like images or files.
|
||||
version:
|
||||
type: string
|
||||
description: >-
|
||||
Version number of the prompt to use (defaults to latest if not specified)
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
title: OpenAIResponsePrompt
|
||||
description: >-
|
||||
OpenAI compatible Prompt object that is used in OpenAI responses.
|
||||
OpenAIResponseText:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -6015,6 +6535,10 @@ components:
|
|||
model:
|
||||
type: string
|
||||
description: The underlying LLM used for completions.
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Prompt object with ID, version, and variables.
|
||||
instructions:
|
||||
type: string
|
||||
previous_response_id:
|
||||
|
|
@ -6092,6 +6616,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) ID of the previous response in a conversation
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Reference to a prompt template and its variables.
|
||||
status:
|
||||
type: string
|
||||
description: >-
|
||||
|
|
@ -8654,7 +9182,7 @@ components:
|
|||
$ref: '#/components/schemas/RAGDocument'
|
||||
description: >-
|
||||
List of documents to index in the RAG system
|
||||
vector_db_id:
|
||||
vector_store_id:
|
||||
type: string
|
||||
description: >-
|
||||
ID of the vector database to store the document embeddings
|
||||
|
|
@ -8665,7 +9193,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- documents
|
||||
- vector_db_id
|
||||
- vector_store_id
|
||||
- chunk_size_in_tokens
|
||||
title: InsertRequest
|
||||
DefaultRAGQueryGeneratorConfig:
|
||||
|
|
@ -8836,7 +9364,7 @@ components:
|
|||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
The query content to search for in the indexed documents
|
||||
vector_db_ids:
|
||||
vector_store_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
|
|
@ -8849,7 +9377,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- content
|
||||
- vector_db_ids
|
||||
- vector_store_ids
|
||||
title: QueryRequest
|
||||
RAGQueryResult:
|
||||
type: object
|
||||
|
|
@ -8977,6 +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:
|
||||
|
|
@ -8997,10 +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: >-
|
||||
|
|
@ -9009,6 +9537,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- content
|
||||
- chunk_id
|
||||
- metadata
|
||||
title: Chunk
|
||||
description: >-
|
||||
|
|
@ -9073,7 +9602,7 @@ components:
|
|||
InsertChunksRequest:
|
||||
type: object
|
||||
properties:
|
||||
vector_db_id:
|
||||
vector_store_id:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the vector database to insert the chunks into.
|
||||
|
|
@ -9092,13 +9621,13 @@ components:
|
|||
description: The time to live of the chunks.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- vector_db_id
|
||||
- vector_store_id
|
||||
- chunks
|
||||
title: InsertChunksRequest
|
||||
QueryChunksRequest:
|
||||
type: object
|
||||
properties:
|
||||
vector_db_id:
|
||||
vector_store_id:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the vector database to query.
|
||||
|
|
@ -9118,7 +9647,7 @@ components:
|
|||
description: The parameters of the query.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- vector_db_id
|
||||
- vector_store_id
|
||||
- query
|
||||
title: QueryChunksRequest
|
||||
QueryChunksResponse:
|
||||
|
|
@ -10075,6 +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.
|
||||
|
|
@ -10137,6 +10679,7 @@ x-tagGroups:
|
|||
- name: Operations
|
||||
tags:
|
||||
- Agents
|
||||
- Batches
|
||||
- Conversations
|
||||
- Files
|
||||
- Inference
|
||||
|
|
|
|||
766
docs/static/stainless-llama-stack-spec.html
vendored
766
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": [
|
||||
|
|
@ -7368,16 +8000,53 @@
|
|||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContentImage"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContentFile"
|
||||
}
|
||||
],
|
||||
"discriminator": {
|
||||
"propertyName": "type",
|
||||
"mapping": {
|
||||
"input_text": "#/components/schemas/OpenAIResponseInputMessageContentText",
|
||||
"input_image": "#/components/schemas/OpenAIResponseInputMessageContentImage"
|
||||
"input_image": "#/components/schemas/OpenAIResponseInputMessageContentImage",
|
||||
"input_file": "#/components/schemas/OpenAIResponseInputMessageContentFile"
|
||||
}
|
||||
}
|
||||
},
|
||||
"OpenAIResponseInputMessageContentFile": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "input_file",
|
||||
"default": "input_file",
|
||||
"description": "The type of the input item. Always `input_file`."
|
||||
},
|
||||
"file_data": {
|
||||
"type": "string",
|
||||
"description": "The data of the file to be sent to the model."
|
||||
},
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The ID of the file to be sent to the model."
|
||||
},
|
||||
"file_url": {
|
||||
"type": "string",
|
||||
"description": "The URL of the file to be sent to the model."
|
||||
},
|
||||
"filename": {
|
||||
"type": "string",
|
||||
"description": "The name of the file to be sent to the model."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseInputMessageContentFile",
|
||||
"description": "File content for input messages in OpenAI response format."
|
||||
},
|
||||
"OpenAIResponseInputMessageContentImage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -7405,6 +8074,10 @@
|
|||
"default": "input_image",
|
||||
"description": "Content type identifier, always \"input_image\""
|
||||
},
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The ID of the file to be sent to the model."
|
||||
},
|
||||
"image_url": {
|
||||
"type": "string",
|
||||
"description": "(Optional) URL of the image content"
|
||||
|
|
@ -8977,29 +9650,14 @@
|
|||
"OpenAIResponseInput": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutput"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputFunctionToolCallOutput"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalRequest"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMCPApprovalResponse"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseMessage"
|
||||
}
|
||||
|
|
@ -9208,6 +9866,10 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) ID of the previous response in a conversation"
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Reference to a prompt template and its variables."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Current status of the response generation"
|
||||
|
|
@ -9303,6 +9965,32 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"OpenAIResponsePrompt": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the prompt template"
|
||||
},
|
||||
"variables": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"$ref": "#/components/schemas/OpenAIResponseInputMessageContent"
|
||||
},
|
||||
"description": "Dictionary of variable names to OpenAIResponseInputMessageContent structure for template substitution. The substitution values can either be strings, or other Response input types like images or files."
|
||||
},
|
||||
"version": {
|
||||
"type": "string",
|
||||
"description": "Version number of the prompt to use (defaults to latest if not specified)"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id"
|
||||
],
|
||||
"title": "OpenAIResponsePrompt",
|
||||
"description": "OpenAI compatible Prompt object that is used in OpenAI responses."
|
||||
},
|
||||
"OpenAIResponseText": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -9673,6 +10361,10 @@
|
|||
"type": "string",
|
||||
"description": "The underlying LLM used for completions."
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Prompt object with ID, version, and variables."
|
||||
},
|
||||
"instructions": {
|
||||
"type": "string"
|
||||
},
|
||||
|
|
@ -9761,6 +10453,10 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) ID of the previous response in a conversation"
|
||||
},
|
||||
"prompt": {
|
||||
"$ref": "#/components/schemas/OpenAIResponsePrompt",
|
||||
"description": "(Optional) Reference to a prompt template and its variables."
|
||||
},
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Current status of the response generation"
|
||||
|
|
@ -13099,7 +13795,7 @@
|
|||
},
|
||||
"description": "List of documents to index in the RAG system"
|
||||
},
|
||||
"vector_db_id": {
|
||||
"vector_store_id": {
|
||||
"type": "string",
|
||||
"description": "ID of the vector database to store the document embeddings"
|
||||
},
|
||||
|
|
@ -13111,7 +13807,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"documents",
|
||||
"vector_db_id",
|
||||
"vector_store_id",
|
||||
"chunk_size_in_tokens"
|
||||
],
|
||||
"title": "InsertRequest"
|
||||
|
|
@ -13302,7 +13998,7 @@
|
|||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The query content to search for in the indexed documents"
|
||||
},
|
||||
"vector_db_ids": {
|
||||
"vector_store_ids": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
|
|
@ -13317,7 +14013,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"content",
|
||||
"vector_db_ids"
|
||||
"vector_store_ids"
|
||||
],
|
||||
"title": "QueryRequest"
|
||||
},
|
||||
|
|
@ -13505,6 +14201,10 @@
|
|||
"$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": {
|
||||
|
|
@ -13538,10 +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."
|
||||
|
|
@ -13550,6 +14246,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"content",
|
||||
"chunk_id",
|
||||
"metadata"
|
||||
],
|
||||
"title": "Chunk",
|
||||
|
|
@ -13610,7 +14307,7 @@
|
|||
"InsertChunksRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"vector_db_id": {
|
||||
"vector_store_id": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the vector database to insert the chunks into."
|
||||
},
|
||||
|
|
@ -13628,7 +14325,7 @@
|
|||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"vector_db_id",
|
||||
"vector_store_id",
|
||||
"chunks"
|
||||
],
|
||||
"title": "InsertChunksRequest"
|
||||
|
|
@ -13636,7 +14333,7 @@
|
|||
"QueryChunksRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"vector_db_id": {
|
||||
"vector_store_id": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the vector database to query."
|
||||
},
|
||||
|
|
@ -13673,7 +14370,7 @@
|
|||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"vector_db_id",
|
||||
"vector_store_id",
|
||||
"query"
|
||||
],
|
||||
"title": "QueryChunksRequest"
|
||||
|
|
@ -15452,7 +16149,6 @@
|
|||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"default": 0,
|
||||
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
|
||||
},
|
||||
"repetition_penalty": {
|
||||
|
|
@ -15735,7 +16431,7 @@
|
|||
"const": "memory_retrieval",
|
||||
"default": "memory_retrieval"
|
||||
},
|
||||
"vector_db_ids": {
|
||||
"vector_store_ids": {
|
||||
"type": "string",
|
||||
"description": "The IDs of the vector databases to retrieve context from."
|
||||
},
|
||||
|
|
@ -15749,7 +16445,7 @@
|
|||
"turn_id",
|
||||
"step_id",
|
||||
"step_type",
|
||||
"vector_db_ids",
|
||||
"vector_store_ids",
|
||||
"inserted_context"
|
||||
],
|
||||
"title": "MemoryRetrievalStep",
|
||||
|
|
@ -17897,6 +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": ""
|
||||
|
|
@ -17991,6 +18692,7 @@
|
|||
"name": "Operations",
|
||||
"tags": [
|
||||
"Agents",
|
||||
"Batches",
|
||||
"Benchmarks",
|
||||
"Conversations",
|
||||
"DatasetIO",
|
||||
|
|
|
|||
584
docs/static/stainless-llama-stack-spec.yaml
vendored
584
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:
|
||||
|
|
@ -5474,11 +5934,44 @@ components:
|
|||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
|
||||
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
|
||||
input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile'
|
||||
OpenAIResponseInputMessageContentFile:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: input_file
|
||||
default: input_file
|
||||
description: >-
|
||||
The type of the input item. Always `input_file`.
|
||||
file_data:
|
||||
type: string
|
||||
description: >-
|
||||
The data of the file to be sent to the model.
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The ID of the file to be sent to the model.
|
||||
file_url:
|
||||
type: string
|
||||
description: >-
|
||||
The URL of the file to be sent to the model.
|
||||
filename:
|
||||
type: string
|
||||
description: >-
|
||||
The name of the file to be sent to the model.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: OpenAIResponseInputMessageContentFile
|
||||
description: >-
|
||||
File content for input messages in OpenAI response format.
|
||||
OpenAIResponseInputMessageContentImage:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -5499,6 +5992,10 @@ components:
|
|||
default: input_image
|
||||
description: >-
|
||||
Content type identifier, always "input_image"
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The ID of the file to be sent to the model.
|
||||
image_url:
|
||||
type: string
|
||||
description: (Optional) URL of the image content
|
||||
|
|
@ -6735,14 +7232,9 @@ components:
|
|||
Error details for failed OpenAI response requests.
|
||||
OpenAIResponseInput:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMessage'
|
||||
OpenAIResponseInputToolFileSearch:
|
||||
type: object
|
||||
|
|
@ -6898,6 +7390,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) ID of the previous response in a conversation
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Reference to a prompt template and its variables.
|
||||
status:
|
||||
type: string
|
||||
description: >-
|
||||
|
|
@ -6971,6 +7467,30 @@ components:
|
|||
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
|
||||
OpenAIResponsePrompt:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
description: Unique identifier of the prompt template
|
||||
variables:
|
||||
type: object
|
||||
additionalProperties:
|
||||
$ref: '#/components/schemas/OpenAIResponseInputMessageContent'
|
||||
description: >-
|
||||
Dictionary of variable names to OpenAIResponseInputMessageContent structure
|
||||
for template substitution. The substitution values can either be strings,
|
||||
or other Response input types like images or files.
|
||||
version:
|
||||
type: string
|
||||
description: >-
|
||||
Version number of the prompt to use (defaults to latest if not specified)
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
title: OpenAIResponsePrompt
|
||||
description: >-
|
||||
OpenAI compatible Prompt object that is used in OpenAI responses.
|
||||
OpenAIResponseText:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -7228,6 +7748,10 @@ components:
|
|||
model:
|
||||
type: string
|
||||
description: The underlying LLM used for completions.
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Prompt object with ID, version, and variables.
|
||||
instructions:
|
||||
type: string
|
||||
previous_response_id:
|
||||
|
|
@ -7305,6 +7829,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) ID of the previous response in a conversation
|
||||
prompt:
|
||||
$ref: '#/components/schemas/OpenAIResponsePrompt'
|
||||
description: >-
|
||||
(Optional) Reference to a prompt template and its variables.
|
||||
status:
|
||||
type: string
|
||||
description: >-
|
||||
|
|
@ -9867,7 +10395,7 @@ components:
|
|||
$ref: '#/components/schemas/RAGDocument'
|
||||
description: >-
|
||||
List of documents to index in the RAG system
|
||||
vector_db_id:
|
||||
vector_store_id:
|
||||
type: string
|
||||
description: >-
|
||||
ID of the vector database to store the document embeddings
|
||||
|
|
@ -9878,7 +10406,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- documents
|
||||
- vector_db_id
|
||||
- vector_store_id
|
||||
- chunk_size_in_tokens
|
||||
title: InsertRequest
|
||||
DefaultRAGQueryGeneratorConfig:
|
||||
|
|
@ -10049,7 +10577,7 @@ components:
|
|||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
The query content to search for in the indexed documents
|
||||
vector_db_ids:
|
||||
vector_store_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
|
|
@ -10062,7 +10590,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- content
|
||||
- vector_db_ids
|
||||
- vector_store_ids
|
||||
title: QueryRequest
|
||||
RAGQueryResult:
|
||||
type: object
|
||||
|
|
@ -10190,6 +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:
|
||||
|
|
@ -10210,10 +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: >-
|
||||
|
|
@ -10222,6 +10750,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- content
|
||||
- chunk_id
|
||||
- metadata
|
||||
title: Chunk
|
||||
description: >-
|
||||
|
|
@ -10286,7 +10815,7 @@ components:
|
|||
InsertChunksRequest:
|
||||
type: object
|
||||
properties:
|
||||
vector_db_id:
|
||||
vector_store_id:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the vector database to insert the chunks into.
|
||||
|
|
@ -10305,13 +10834,13 @@ components:
|
|||
description: The time to live of the chunks.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- vector_db_id
|
||||
- vector_store_id
|
||||
- chunks
|
||||
title: InsertChunksRequest
|
||||
QueryChunksRequest:
|
||||
type: object
|
||||
properties:
|
||||
vector_db_id:
|
||||
vector_store_id:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the vector database to query.
|
||||
|
|
@ -10331,7 +10860,7 @@ components:
|
|||
description: The parameters of the query.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- vector_db_id
|
||||
- vector_store_id
|
||||
- query
|
||||
title: QueryChunksRequest
|
||||
QueryChunksResponse:
|
||||
|
|
@ -11600,7 +12129,6 @@ components:
|
|||
description: The sampling strategy.
|
||||
max_tokens:
|
||||
type: integer
|
||||
default: 0
|
||||
description: >-
|
||||
The maximum number of tokens that can be generated in the completion.
|
||||
The token count of your prompt plus max_tokens cannot exceed the model's
|
||||
|
|
@ -11850,7 +12378,7 @@ components:
|
|||
description: Type of the step in an agent turn.
|
||||
const: memory_retrieval
|
||||
default: memory_retrieval
|
||||
vector_db_ids:
|
||||
vector_store_ids:
|
||||
type: string
|
||||
description: >-
|
||||
The IDs of the vector databases to retrieve context from.
|
||||
|
|
@ -11863,7 +12391,7 @@ components:
|
|||
- turn_id
|
||||
- step_id
|
||||
- step_type
|
||||
- vector_db_ids
|
||||
- vector_store_ids
|
||||
- inserted_context
|
||||
title: MemoryRetrievalStep
|
||||
description: >-
|
||||
|
|
@ -13460,6 +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
|
||||
|
|
@ -13534,6 +14075,7 @@ x-tagGroups:
|
|||
- name: Operations
|
||||
tags:
|
||||
- Agents
|
||||
- Batches
|
||||
- Benchmarks
|
||||
- Conversations
|
||||
- DatasetIO
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue