phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 00:09:34 +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

4
llama_stack/providers/inline/tool_runtime/rag/__init__.py
View file

@ -6,12 +6,12 @@
from typing import Any
from llama_stack.providers.datatypes import Api
from llama_stack.providers.datatypes import Api, ProviderContext
from .config import RagToolRuntimeConfig
async def get_provider_impl(config: RagToolRuntimeConfig, deps: dict[Api, Any]):
async def get_provider_impl(context: ProviderContext, config: RagToolRuntimeConfig, deps: dict[Api, Any]):
from .memory import MemoryToolRuntimeImpl
impl = MemoryToolRuntimeImpl(config, deps[Api.vector_io], deps[Api.inference])