mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 22:18:00 +00:00
feat: add batches API with OpenAI compatibility
Add complete batches API implementation with protocol, providers, and tests: Core Infrastructure: - Add batches API protocol using OpenAI Batch types directly - Add Api.batches enum value and protocol mapping in resolver - Add OpenAI "batch" file purpose support - Include proper error handling (ConflictError, ResourceNotFoundError) Reference Provider: - Add ReferenceBatchesImpl with full CRUD operations (create, retrieve, cancel, list) - Implement background batch processing with configurable concurrency - Add SQLite KVStore backend for persistence - Support /v1/chat/completions endpoint with request validation Comprehensive Test Suite: - Add unit tests for provider implementation with validation - Add integration tests for end-to-end batch processing workflows - Add error handling tests for validation, malformed inputs, and edge cases Configuration: - Add max_concurrent_batches and max_concurrent_requests_per_batch options - Add provider documentation with sample configurations Test with - ``` $ uv run llama stack build --image-type venv --providers inference=YOU_PICK,files=inline::localfs,batches=inline::reference --run & $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/unit/providers/batches tests/integration/batches --text-model YOU_PICK ```
This commit is contained in:
parent
1677d6bffd
commit
8e678912ec
21 changed files with 2664 additions and 2 deletions
|
@ -31,6 +31,7 @@ from fastapi.responses import JSONResponse, StreamingResponse
|
|||
from openai import BadRequestError
|
||||
from pydantic import BaseModel, ValidationError
|
||||
|
||||
from llama_stack.apis.common.errors import ConflictError, ResourceNotFoundError
|
||||
from llama_stack.apis.common.responses import PaginatedResponse
|
||||
from llama_stack.cli.utils import add_config_distro_args, get_config_from_args
|
||||
from llama_stack.core.access_control.access_control import AccessDeniedError
|
||||
|
@ -127,6 +128,10 @@ def translate_exception(exc: Exception) -> HTTPException | RequestValidationErro
|
|||
]
|
||||
},
|
||||
)
|
||||
elif isinstance(exc, ConflictError):
|
||||
return HTTPException(status_code=409, detail=str(exc))
|
||||
elif isinstance(exc, ResourceNotFoundError):
|
||||
return HTTPException(status_code=404, detail=str(exc))
|
||||
elif isinstance(exc, ValueError):
|
||||
return HTTPException(status_code=400, detail=f"Invalid value: {str(exc)}")
|
||||
elif isinstance(exc, BadRequestError):
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue