phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 06:42:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into agent_rewrite

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-15 09:24:26 -07:00
commit 57b3d14895
30 changed files with 869 additions and 408 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -59,6 +59,7 @@ class SentenceTransformersInferenceImpl(
provider_id=self.__provider_id__,
metadata={
"embedding_dimension": 768,
"default_configured": True,
},
model_type=ModelType.embedding,
),

7
llama_stack/providers/inline/vector_io/chroma/__init__.py
View file

@ -16,6 +16,11 @@ async def get_provider_impl(config: ChromaVectorIOConfig, deps: dict[Api, Any]):
ChromaVectorIOAdapter,
)
impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
impl = ChromaVectorIOAdapter(
config,
deps[Api.inference],
deps[Api.models],
deps.get(Api.files),
)
await impl.initialize()
return impl

7
llama_stack/providers/inline/vector_io/faiss/__init__.py
View file

@ -16,6 +16,11 @@ async def get_provider_impl(config: FaissVectorIOConfig, deps: dict[Api, Any]):
assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}"
impl = FaissVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
impl = FaissVectorIOAdapter(
config,
deps[Api.inference],
deps[Api.models],
deps.get(Api.files),
)
await impl.initialize()
return impl

10
llama_stack/providers/inline/vector_io/faiss/faiss.py
View file

@ -17,6 +17,7 @@ from numpy.typing import NDArray
from llama_stack.apis.common.errors import VectorStoreNotFoundError
from llama_stack.apis.files import Files
from llama_stack.apis.inference import Inference, InterleavedContent
from llama_stack.apis.models import Models
from llama_stack.apis.vector_dbs import VectorDB
from llama_stack.apis.vector_io import (
Chunk,
@ -199,10 +200,17 @@ class FaissIndex(EmbeddingIndex):
class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, files_api: Files | None) -> None:
def __init__(
self,
config: FaissVectorIOConfig,
inference_api: Inference,
models_api: Models,
files_api: Files | None,
) -> None:
super().__init__(files_api=files_api, kvstore=None)
self.config = config
self.inference_api = inference_api
self.models_api = models_api
self.cache: dict[str, VectorDBWithIndex] = {}
async def initialize(self) -> None:

7
llama_stack/providers/inline/vector_io/milvus/__init__.py
View file

@ -14,6 +14,11 @@ from .config import MilvusVectorIOConfig
async def get_provider_impl(config: MilvusVectorIOConfig, deps: dict[Api, Any]):
from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusVectorIOAdapter
impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
impl = MilvusVectorIOAdapter(
config,
deps[Api.inference],
deps[Api.models],
deps.get(Api.files),
)
await impl.initialize()
return impl

8
llama_stack/providers/inline/vector_io/qdrant/__init__.py
View file

@ -15,7 +15,11 @@ async def get_provider_impl(config: QdrantVectorIOConfig, deps: dict[Api, Any]):
from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
assert isinstance(config, QdrantVectorIOConfig), f"Unexpected config type: {type(config)}"
files_api = deps.get(Api.files)
impl = QdrantVectorIOAdapter(config, deps[Api.inference], files_api)
impl = QdrantVectorIOAdapter(
config,
deps[Api.inference],
deps[Api.models],
deps.get(Api.files),
)
await impl.initialize()
return impl

7
llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py
View file

@ -15,6 +15,11 @@ async def get_provider_impl(config: SQLiteVectorIOConfig, deps: dict[Api, Any]):
from .sqlite_vec import SQLiteVecVectorIOAdapter
assert isinstance(config, SQLiteVectorIOConfig), f"Unexpected config type: {type(config)}"
impl = SQLiteVecVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files, None))
impl = SQLiteVecVectorIOAdapter(
config,
deps[Api.inference],
deps[Api.models],
deps.get(Api.files),
)
await impl.initialize()
return impl

11
llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py
View file

@ -17,6 +17,7 @@ from numpy.typing import NDArray
from llama_stack.apis.common.errors import VectorStoreNotFoundError
from llama_stack.apis.files import Files
from llama_stack.apis.inference import Inference
from llama_stack.apis.models import Models
from llama_stack.apis.vector_dbs import VectorDB
from llama_stack.apis.vector_io import (
Chunk,
@ -409,11 +410,19 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
and creates a cache of VectorDBWithIndex instances (each wrapping a SQLiteVecIndex).
"""
def __init__(self, config, inference_api: Inference, files_api: Files | None) -> None:
def __init__(
self,
config,
inference_api: Inference,
models_api: Models,
files_api: Files | None,
) -> None:
super().__init__(files_api=files_api, kvstore=None)
self.config = config
self.inference_api = inference_api
self.models_api = models_api
self.cache: dict[str, VectorDBWithIndex] = {}
self.vector_db_store = None
async def initialize(self) -> None:
self.kvstore = await kvstore_impl(self.config.kvstore)