phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 04:00:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

format

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-20 19:27:38 -07:00
parent 44f104baae
commit c7eed3ef80
16 changed files with 35 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/core/datatypes.py
View file

@ -23,8 +23,8 @@ from llama_stack.apis.scoring import Scoring
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnInput
from llama_stack.apis.shields import Shield, ShieldInput
from llama_stack.apis.tools import ToolGroup, ToolGroupInput, ToolRuntime
from llama_stack.apis.vector_stores import VectorStore, VectorStoreInput
from llama_stack.apis.vector_io import VectorIO
from llama_stack.apis.vector_stores import VectorStore, VectorStoreInput
from llama_stack.core.access_control.datatypes import AccessRule
from llama_stack.core.storage.datatypes import (
KVStoreReference,

2
llama_stack/core/resolver.py
View file

@ -29,8 +29,8 @@ from llama_stack.apis.scoring_functions import ScoringFunctions
from llama_stack.apis.shields import Shields
from llama_stack.apis.telemetry import Telemetry
from llama_stack.apis.tools import ToolGroups, ToolRuntime
from llama_stack.apis.vector_stores import VectorStores
from llama_stack.apis.vector_io import VectorIO
from llama_stack.apis.vector_stores import VectorStores
from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA
from llama_stack.core.client import get_client_impl
from llama_stack.core.datatypes import (

2
llama_stack/providers/inline/vector_io/faiss/faiss.py
View file

@ -17,8 +17,8 @@ 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.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import HealthResponse, HealthStatus, VectorStoresProtocolPrivate
from llama_stack.providers.utils.kvstore import kvstore_impl

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

@ -17,8 +17,8 @@ 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.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import VectorStoresProtocolPrivate
from llama_stack.providers.utils.kvstore import kvstore_impl
@ -412,7 +412,9 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresPro
return [v.vector_store for v in self.cache.values()]
async def register_vector_store(self, vector_store: VectorStore) -> None:
index = await SQLiteVecIndex.create(vector_store.embedding_dimension, self.config.db_path, vector_store.identifier)
index = await SQLiteVecIndex.create(
vector_store.embedding_dimension, self.config.db_path, vector_store.identifier
)
self.cache[vector_store.identifier] = VectorStoreWithIndex(vector_store, index, self.inference_api)
async def _get_and_cache_vector_store_index(self, vector_store_id: str) -> VectorStoreWithIndex | None:

2
llama_stack/providers/remote/vector_io/chroma/chroma.py
View file

@ -13,8 +13,8 @@ from numpy.typing import NDArray
from llama_stack.apis.files import Files
from llama_stack.apis.inference import Inference, InterleavedContent
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import VectorStoresProtocolPrivate
from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig

2
llama_stack/providers/remote/vector_io/milvus/milvus.py
View file

@ -14,8 +14,8 @@ from pymilvus import AnnSearchRequest, DataType, Function, FunctionType, MilvusC
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.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import VectorStoresProtocolPrivate
from llama_stack.providers.inline.vector_io.milvus import MilvusVectorIOConfig as InlineMilvusVectorIOConfig

2
llama_stack/providers/remote/vector_io/pgvector/pgvector.py
View file

@ -16,8 +16,8 @@ from pydantic import BaseModel, TypeAdapter
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.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import VectorStoresProtocolPrivate
from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str

10
llama_stack/providers/remote/vector_io/qdrant/qdrant.py
View file

@ -16,7 +16,6 @@ from qdrant_client.models import PointStruct
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.vector_stores import VectorStore
from llama_stack.apis.vector_io import (
Chunk,
QueryChunksResponse,
@ -24,6 +23,7 @@ from llama_stack.apis.vector_io import (
VectorStoreChunkingStrategy,
VectorStoreFileObject,
)
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import VectorStoresProtocolPrivate
from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
@ -171,7 +171,9 @@ class QdrantVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc
for vector_store_data in stored_vector_stores:
vector_store = VectorStore.model_validate_json(vector_store_data)
index = VectorStoreWithIndex(vector_store, QdrantIndex(self.client, vector_store.identifier), self.inference_api)
index = VectorStoreWithIndex(
vector_store, QdrantIndex(self.client, vector_store.identifier), self.inference_api
)
self.cache[vector_store.identifier] = index
self.openai_vector_stores = await self._load_openai_vector_stores()
@ -186,7 +188,9 @@ class QdrantVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc
await self.kvstore.set(key=key, value=vector_store.model_dump_json())
index = VectorStoreWithIndex(
vector_store=vector_store, index=QdrantIndex(self.client, vector_store.identifier), inference_api=self.inference_api
vector_store=vector_store,
index=QdrantIndex(self.client, vector_store.identifier),
inference_api=self.inference_api,
)
self.cache[vector_store.identifier] = index

2
llama_stack/providers/remote/vector_io/weaviate/weaviate.py
View file

@ -16,8 +16,8 @@ from llama_stack.apis.common.content_types import InterleavedContent
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.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.core.request_headers import NeedsRequestProviderData
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import VectorStoresProtocolPrivate

2
llama_stack/providers/utils/memory/openai_vector_store_mixin.py
View file

@ -17,7 +17,6 @@ from pydantic import TypeAdapter
from llama_stack.apis.common.errors import VectorStoreNotFoundError
from llama_stack.apis.files import Files, OpenAIFileObject
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.apis.vector_io import (
Chunk,
OpenAICreateVectorStoreFileBatchRequestWithExtraBody,
@ -43,6 +42,7 @@ from llama_stack.apis.vector_io import (
VectorStoreSearchResponse,
VectorStoreSearchResponsePage,
)
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.core.id_generation import generate_object_id
from llama_stack.log import get_logger
from llama_stack.providers.utils.kvstore.api import KVStore

2
llama_stack/providers/utils/memory/vector_store.py
View file

@ -23,8 +23,8 @@ from llama_stack.apis.common.content_types import (
)
from llama_stack.apis.inference import OpenAIEmbeddingsRequestWithExtraBody
from llama_stack.apis.tools import RAGDocument
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
from llama_stack.models.llama.llama3.tokenizer import Tokenizer
from llama_stack.providers.datatypes import Api

8
tests/integration/vector_io/test_vector_io.py
View file

@ -49,7 +49,9 @@ def client_with_empty_registry(client_with_models):
@vector_provider_wrapper
def test_vector_store_retrieve(client_with_empty_registry, embedding_model_id, embedding_dimension, vector_io_provider_id):
def test_vector_store_retrieve(
client_with_empty_registry, embedding_model_id, embedding_dimension, vector_io_provider_id
):
vector_store_name = "test_vector_store"
create_response = client_with_empty_registry.vector_stores.create(
name=vector_store_name,
@ -69,7 +71,9 @@ def test_vector_store_retrieve(client_with_empty_registry, embedding_model_id, e
@vector_provider_wrapper
def test_vector_store_register(client_with_empty_registry, embedding_model_id, embedding_dimension, vector_io_provider_id):
def test_vector_store_register(
client_with_empty_registry, embedding_model_id, embedding_dimension, vector_io_provider_id
):
vector_store_name = "test_vector_store"
response = client_with_empty_registry.vector_stores.create(
name=vector_store_name,

2
tests/unit/providers/vector_io/conftest.py
View file

@ -10,8 +10,8 @@ from unittest.mock import AsyncMock, MagicMock, patch
import numpy as np
import pytest
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.inline.vector_io.faiss.faiss import FaissIndex, FaissVectorIOAdapter

2
tests/unit/providers/vector_io/test_faiss.py
View file

@ -11,8 +11,8 @@ import numpy as np
import pytest
from llama_stack.apis.files import Files
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.providers.datatypes import HealthStatus
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.inline.vector_io.faiss.faiss import (

2
tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py
View file

@ -12,7 +12,6 @@ import numpy as np
import pytest
from llama_stack.apis.common.errors import VectorStoreNotFoundError
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.apis.vector_io import (
Chunk,
OpenAICreateVectorStoreFileBatchRequestWithExtraBody,
@ -21,6 +20,7 @@ from llama_stack.apis.vector_io import (
VectorStoreChunkingStrategyAuto,
VectorStoreFileObject,
)
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import VECTOR_DBS_PREFIX
# This test is a unit test for the inline VectorIO providers. This should only contain

8
tests/unit/registry/test_registry.py
View file

@ -134,7 +134,9 @@ async def test_duplicate_provider_registration(cached_disk_dist_registry):
provider_resource_id="test_vector_store_2",
provider_id="baz", # Same provider_id
)
with pytest.raises(ValueError, match="Object of type 'vector_store' and identifier 'test_vector_store_2' already exists"):
with pytest.raises(
ValueError, match="Object of type 'vector_store' and identifier 'test_vector_store_2' already exists"
):
await cached_disk_dist_registry.register(duplicate_vector_store)
result = await cached_disk_dist_registry.get("vector_store", "test_vector_store_2")
@ -289,7 +291,9 @@ async def test_double_registration_different_objects(disk_dist_registry):
assert result1 is True
# Second registration with different data should fail
with pytest.raises(ValueError, match="Object of type 'vector_store' and identifier 'test_vector_store' already exists"):
with pytest.raises(
ValueError, match="Object of type 'vector_store' and identifier 'test_vector_store' already exists"
):
await disk_dist_registry.register(vector_store2)
# Verify original object is unchanged