mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-21 09:23:13 +00:00
914c7be288
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 ``` addresses #3066 --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
|
|
|
|
|
|
class ReferenceBatchesImplConfig(BaseModel):
|
|
"""Configuration for the Reference Batches implementation."""
|
|
|
|
kvstore: KVStoreConfig = Field(
|
|
description="Configuration for the key-value store backend.",
|
|
)
|
|
|
|
max_concurrent_batches: int = Field(
|
|
default=1,
|
|
description="Maximum number of concurrent batches to process simultaneously.",
|
|
ge=1,
|
|
)
|
|
|
|
max_concurrent_requests_per_batch: int = Field(
|
|
default=10,
|
|
description="Maximum number of concurrent requests to process per batch.",
|
|
ge=1,
|
|
)
|
|
|
|
# TODO: add a max requests per second rate limiter
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, __distro_dir__: str) -> dict:
|
|
return {
|
|
"kvstore": SqliteKVStoreConfig.sample_run_config(
|
|
__distro_dir__=__distro_dir__,
|
|
db_name="batches.db",
|
|
),
|
|
}
|