phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 10:09:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: Add ProviderContext for a flexible storage directory

Browse source 
- Introduce ProviderContext class to decouple provider storage paths from absolute paths
- Add storage_dir attribute to StackRunConfig to accept CLI options
- Implement storage directory resolution with prioritized fallbacks:
  1. CLI option (--state-directory)
  2. Environment variable (LLAMA_STACK_STATE_DIR)
  3. Default distribution directory
- Standardize provider signatures to follow context, config, deps pattern
- Update provider implementations to use the new context-based approach
- Add comprehensive tests to verify state directory resolution
This commit is contained in:
Roland Huß 2025-05-12 11:44:21 +02:00
parent dd07c7a5b5
commit e6c9aebe47
41 changed files with 242 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/inline/vector_io/faiss/__init__.py
View file

@ -6,16 +6,16 @@
from typing import Any
from llama_stack.providers.datatypes import Api
from llama_stack.providers.datatypes import Api, ProviderContext
from .config import FaissVectorIOConfig
async def get_provider_impl(config: FaissVectorIOConfig, deps: dict[Api, Any]):
async def get_provider_impl(context: ProviderContext, config: FaissVectorIOConfig, deps: dict[Api, Any]):
from .faiss import FaissVectorIOAdapter
assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}"
impl = FaissVectorIOAdapter(config, deps[Api.inference])
impl = FaissVectorIOAdapter(context, config, deps[Api.inference])
await impl.initialize()
return impl

6
llama_stack/providers/inline/vector_io/faiss/faiss.py
View file

@ -19,7 +19,7 @@ from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference.inference import Inference
from llama_stack.apis.vector_dbs import VectorDB
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.providers.datatypes import VectorDBsProtocolPrivate
from llama_stack.providers.datatypes import ProviderContext, VectorDBsProtocolPrivate
from llama_stack.providers.utils.kvstore import kvstore_impl
from llama_stack.providers.utils.kvstore.api import KVStore
from llama_stack.providers.utils.memory.vector_store import (
@ -114,9 +114,11 @@ class FaissIndex(EmbeddingIndex):
class FaissVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
def __init__(self, config: FaissVectorIOConfig, inference_api: Inference) -> None:
def __init__(self, context: ProviderContext, config: FaissVectorIOConfig, inference_api: Inference) -> None:
self.context = context
self.config = config
self.inference_api = inference_api
self.storage_dir = context.storage_dir if context else None
self.cache: dict[str, VectorDBWithIndex] = {}
self.kvstore: KVStore | None = None