mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 14:08:00 +00:00
8e678912ec
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 ```
26 lines
909 B
Python
26 lines
909 B
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 llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec
|
|
|
|
|
|
def available_providers() -> list[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
api=Api.batches,
|
|
provider_type="inline::reference",
|
|
pip_packages=["openai"],
|
|
module="llama_stack.providers.inline.batches.reference",
|
|
config_class="llama_stack.providers.inline.batches.reference.config.ReferenceBatchesImplConfig",
|
|
api_dependencies=[
|
|
Api.inference,
|
|
Api.files,
|
|
Api.models,
|
|
],
|
|
description="Reference implementation of batches API with KVStore persistence.",
|
|
),
|
|
]
|