mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 15:09:49 +00:00
6620b625f1
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chore: Enable keyword search for Milvus inline (#3073) With https://github.com/milvus-io/milvus-lite/pull/294 - Milvus Lite supports keyword search using BM25. While introducing keyword search we had explicitly disabled it for inline milvus. This PR removes the need for the check, and enables `inline::milvus` for tests. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Run llama stack with `inline::milvus` enabled: ``` pytest tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes --stack-config=http://localhost:8321 --embedding-model=all-MiniLM-L6-v2 -v ``` ``` INFO 2025-08-07 17:06:20,932 tests.integration.conftest:64 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS =========================================================================================== test session starts ============================================================================================ platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 3 items tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-vector] PASSED [ 33%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-keyword] PASSED [ 66%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-hybrid] PASSED [100%] ============================================================================================ 3 passed in 4.75s ============================================================================================= ``` Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> chore: Fixup main pre commit (#3204) build: Bump version to 0.2.18 chore: Faster npm pre-commit (#3206) Adds npm to pre-commit.yml installation and caches ui Removes node installation during pre-commit. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chiecking in for tonight, wip moving to agents api Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> remove log Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updated Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix: disable ui-prettier & ui-eslint (#3207) chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) This PR adds a step in pre-commit to enforce using `llama_stack` logger. Currently, various parts of the code base uses different loggers. As a custom `llama_stack` logger exist and used in the codebase, it is better to standardize its utilization. Signed-off-by: Mustafa Elbehery <melbeher@redhat.com> Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> fix: fix ```openai_embeddings``` for asymmetric embedding NIMs (#3205) NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. This PR adds the `input_type="query"` as default and updates the documentation to suggest using the `embedding` API for passage embeddings. <!-- If resolving an issue, uncomment and update the line below --> Resolves #2892 ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ``` cleaning up Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating session manager to cache messages locally Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix linter Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> more cleanup Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
75 lines
2.9 KiB
Python
75 lines
2.9 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 llama_stack.log import get_logger
|
|
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import OpenAIConfig
|
|
from .models import MODEL_ENTRIES
|
|
|
|
logger = get_logger(name=__name__, category="inference")
|
|
|
|
|
|
#
|
|
# This OpenAI adapter implements Inference methods using two mixins -
|
|
#
|
|
# | Inference Method | Implementation Source |
|
|
# |----------------------------|--------------------------|
|
|
# | completion | LiteLLMOpenAIMixin |
|
|
# | chat_completion | LiteLLMOpenAIMixin |
|
|
# | embedding | LiteLLMOpenAIMixin |
|
|
# | batch_completion | LiteLLMOpenAIMixin |
|
|
# | batch_chat_completion | LiteLLMOpenAIMixin |
|
|
# | openai_completion | OpenAIMixin |
|
|
# | openai_chat_completion | OpenAIMixin |
|
|
# | openai_embeddings | OpenAIMixin |
|
|
#
|
|
class OpenAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
|
"""
|
|
OpenAI Inference Adapter for Llama Stack.
|
|
|
|
Note: The inheritance order is important here. OpenAIMixin must come before
|
|
LiteLLMOpenAIMixin to ensure that OpenAIMixin.check_model_availability()
|
|
is used instead of ModelRegistryHelper.check_model_availability().
|
|
|
|
- OpenAIMixin.check_model_availability() queries the OpenAI API to check if a model exists
|
|
- ModelRegistryHelper.check_model_availability() (inherited by LiteLLMOpenAIMixin) just returns False and shows a warning
|
|
"""
|
|
|
|
def __init__(self, config: OpenAIConfig) -> None:
|
|
LiteLLMOpenAIMixin.__init__(
|
|
self,
|
|
MODEL_ENTRIES,
|
|
litellm_provider_name="openai",
|
|
api_key_from_config=config.api_key,
|
|
provider_data_api_key_field="openai_api_key",
|
|
)
|
|
self.config = config
|
|
# we set is_openai_compat so users can use the canonical
|
|
# openai model names like "gpt-4" or "gpt-3.5-turbo"
|
|
# and the model name will be translated to litellm's
|
|
# "openai/gpt-4" or "openai/gpt-3.5-turbo" transparently.
|
|
# if we do not set this, users will be exposed to the
|
|
# litellm specific model names, an abstraction leak.
|
|
self.is_openai_compat = True
|
|
|
|
# Delegate the client data handling get_api_key method to LiteLLMOpenAIMixin
|
|
get_api_key = LiteLLMOpenAIMixin.get_api_key
|
|
|
|
def get_base_url(self) -> str:
|
|
"""
|
|
Get the OpenAI API base URL.
|
|
|
|
Returns the OpenAI API base URL from the configuration.
|
|
"""
|
|
return self.config.base_url
|
|
|
|
async def initialize(self) -> None:
|
|
await super().initialize()
|
|
|
|
async def shutdown(self) -> None:
|
|
await super().shutdown()
|