diff --git a/llama_stack/apis/telemetry/telemetry.py b/llama_stack/apis/telemetry/telemetry.py index 5622aaeac..63ae1dc73 100644 --- a/llama_stack/apis/telemetry/telemetry.py +++ b/llama_stack/apis/telemetry/telemetry.py @@ -13,8 +13,8 @@ from typing import ( Literal, Optional, Protocol, - runtime_checkable, Union, + runtime_checkable, ) from llama_models.llama3.api.datatypes import Primitive diff --git a/llama_stack/providers/inline/vector_io/chroma/__init__.py b/llama_stack/providers/inline/vector_io/chroma/__init__.py index 56a4ac21c..abaf01097 100644 --- a/llama_stack/providers/inline/vector_io/chroma/__init__.py +++ b/llama_stack/providers/inline/vector_io/chroma/__init__.py @@ -8,10 +8,10 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec -from .config import ChromaInlineImplConfig +from .config import ChromaVectorIOConfig -async def get_provider_impl(config: ChromaInlineImplConfig, deps: Dict[Api, ProviderSpec]): +async def get_provider_impl(config: ChromaVectorIOConfig, deps: Dict[Api, ProviderSpec]): from llama_stack.providers.remote.vector_io.chroma.chroma import ( ChromaVectorIOAdapter, ) diff --git a/llama_stack/providers/inline/vector_io/chroma/config.py b/llama_stack/providers/inline/vector_io/chroma/config.py index efbd77faf..a1fb60fa6 100644 --- a/llama_stack/providers/inline/vector_io/chroma/config.py +++ b/llama_stack/providers/inline/vector_io/chroma/config.py @@ -9,7 +9,7 @@ from typing import Any, Dict from pydantic import BaseModel -class ChromaInlineImplConfig(BaseModel): +class ChromaVectorIOConfig(BaseModel): db_path: str @classmethod diff --git a/llama_stack/providers/inline/vector_io/faiss/__init__.py b/llama_stack/providers/inline/vector_io/faiss/__init__.py index 8c075a0f8..f23e1fa4f 100644 --- a/llama_stack/providers/inline/vector_io/faiss/__init__.py +++ b/llama_stack/providers/inline/vector_io/faiss/__init__.py @@ -8,14 +8,14 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec -from .config import FaissImplConfig +from .config import FaissVectorIOConfig -async def get_provider_impl(config: FaissImplConfig, deps: Dict[Api, ProviderSpec]): - from .faiss import FaissVectorIOImpl +async def get_provider_impl(config: FaissVectorIOConfig, deps: Dict[Api, ProviderSpec]): + from .faiss import FaissVectorIOAdapter - assert isinstance(config, FaissImplConfig), f"Unexpected config type: {type(config)}" + assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}" - impl = FaissVectorIOImpl(config, deps[Api.inference]) + impl = FaissVectorIOAdapter(config, deps[Api.inference]) await impl.initialize() return impl diff --git a/llama_stack/providers/inline/vector_io/faiss/config.py b/llama_stack/providers/inline/vector_io/faiss/config.py index d82104477..ae859842d 100644 --- a/llama_stack/providers/inline/vector_io/faiss/config.py +++ b/llama_stack/providers/inline/vector_io/faiss/config.py @@ -16,7 +16,7 @@ from llama_stack.providers.utils.kvstore.config import ( @json_schema_type -class FaissImplConfig(BaseModel): +class FaissVectorIOConfig(BaseModel): kvstore: KVStoreConfig @classmethod diff --git a/llama_stack/providers/inline/vector_io/faiss/faiss.py b/llama_stack/providers/inline/vector_io/faiss/faiss.py index 565afdcf6..b52fb074c 100644 --- a/llama_stack/providers/inline/vector_io/faiss/faiss.py +++ b/llama_stack/providers/inline/vector_io/faiss/faiss.py @@ -24,7 +24,7 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorDBWithIndex, ) -from .config import FaissImplConfig +from .config import FaissVectorIOConfig logger = logging.getLogger(__name__) @@ -112,8 +112,8 @@ class FaissIndex(EmbeddingIndex): return QueryChunksResponse(chunks=chunks, scores=scores) -class FaissVectorIOImpl(VectorIO, VectorDBsProtocolPrivate): - def __init__(self, config: FaissImplConfig, inference_api: Api.inference) -> None: +class FaissVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): + def __init__(self, config: FaissVectorIOConfig, inference_api: Api.inference) -> None: self.config = config self.inference_api = inference_api self.cache = {} diff --git a/llama_stack/providers/remote/vector_io/chroma/__init__.py b/llama_stack/providers/remote/vector_io/chroma/__init__.py index 9990120f5..8646b04d6 100644 --- a/llama_stack/providers/remote/vector_io/chroma/__init__.py +++ b/llama_stack/providers/remote/vector_io/chroma/__init__.py @@ -8,10 +8,10 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec -from .config import ChromaRemoteImplConfig +from .config import ChromaVectorIOConfig -async def get_adapter_impl(config: ChromaRemoteImplConfig, deps: Dict[Api, ProviderSpec]): +async def get_adapter_impl(config: ChromaVectorIOConfig, deps: Dict[Api, ProviderSpec]): from .chroma import ChromaVectorIOAdapter impl = ChromaVectorIOAdapter(config, deps[Api.inference]) diff --git a/llama_stack/providers/remote/vector_io/chroma/chroma.py b/llama_stack/providers/remote/vector_io/chroma/chroma.py index 47ef30b5a..f894a8e65 100644 --- a/llama_stack/providers/remote/vector_io/chroma/chroma.py +++ b/llama_stack/providers/remote/vector_io/chroma/chroma.py @@ -16,13 +16,12 @@ from llama_stack.apis.inference import InterleavedContent from llama_stack.apis.vector_dbs import VectorDB from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate -from llama_stack.providers.inline.vector_io.chroma import ChromaInlineImplConfig from llama_stack.providers.utils.memory.vector_store import ( EmbeddingIndex, VectorDBWithIndex, ) -from .config import ChromaRemoteImplConfig +from .config import ChromaVectorIOConfig log = logging.getLogger(__name__) @@ -89,7 +88,7 @@ class ChromaIndex(EmbeddingIndex): class ChromaVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): def __init__( self, - config: Union[ChromaRemoteImplConfig, ChromaInlineImplConfig], + config: Union[ChromaVectorIOConfig, ChromaVectorIOConfig], inference_api: Api.inference, ) -> None: log.info(f"Initializing ChromaVectorIOAdapter with url: {config}") @@ -100,7 +99,7 @@ class ChromaVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): self.cache = {} async def initialize(self) -> None: - if isinstance(self.config, ChromaRemoteImplConfig): + if isinstance(self.config, ChromaVectorIOConfig): log.info(f"Connecting to Chroma server at: {self.config.url}") url = self.config.url.rstrip("/") parsed = urlparse(url) diff --git a/llama_stack/providers/remote/vector_io/chroma/config.py b/llama_stack/providers/remote/vector_io/chroma/config.py index 68ca2c967..cbbfa9de3 100644 --- a/llama_stack/providers/remote/vector_io/chroma/config.py +++ b/llama_stack/providers/remote/vector_io/chroma/config.py @@ -9,7 +9,7 @@ from typing import Any, Dict from pydantic import BaseModel -class ChromaRemoteImplConfig(BaseModel): +class ChromaVectorIOConfig(BaseModel): url: str @classmethod diff --git a/llama_stack/providers/remote/vector_io/pgvector/__init__.py b/llama_stack/providers/remote/vector_io/pgvector/__init__.py index bdca7acb1..089d890b7 100644 --- a/llama_stack/providers/remote/vector_io/pgvector/__init__.py +++ b/llama_stack/providers/remote/vector_io/pgvector/__init__.py @@ -8,12 +8,12 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec -from .config import PGVectorConfig +from .config import PGVectorVectorIOConfig -async def get_adapter_impl(config: PGVectorConfig, deps: Dict[Api, ProviderSpec]): - from .pgvector import PGVectorVectorDBAdapter +async def get_adapter_impl(config: PGVectorVectorIOConfig, deps: Dict[Api, ProviderSpec]): + from .pgvector import PGVectorVectorIOAdapter - impl = PGVectorVectorDBAdapter(config, deps[Api.inference]) + impl = PGVectorVectorIOAdapter(config, deps[Api.inference]) await impl.initialize() return impl diff --git a/llama_stack/providers/remote/vector_io/pgvector/config.py b/llama_stack/providers/remote/vector_io/pgvector/config.py index 41983e7b2..2a64d7c67 100644 --- a/llama_stack/providers/remote/vector_io/pgvector/config.py +++ b/llama_stack/providers/remote/vector_io/pgvector/config.py @@ -9,7 +9,7 @@ from pydantic import BaseModel, Field @json_schema_type -class PGVectorConfig(BaseModel): +class PGVectorVectorIOConfig(BaseModel): host: str = Field(default="localhost") port: int = Field(default=5432) db: str = Field(default="postgres") diff --git a/llama_stack/providers/remote/vector_io/pgvector/pgvector.py b/llama_stack/providers/remote/vector_io/pgvector/pgvector.py index 693aacd76..269cf554b 100644 --- a/llama_stack/providers/remote/vector_io/pgvector/pgvector.py +++ b/llama_stack/providers/remote/vector_io/pgvector/pgvector.py @@ -22,7 +22,7 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorDBWithIndex, ) -from .config import PGVectorConfig +from .config import PGVectorVectorIOConfig log = logging.getLogger(__name__) @@ -121,8 +121,8 @@ class PGVectorIndex(EmbeddingIndex): cur.execute(f"DROP TABLE IF EXISTS {self.table_name}") -class PGVectorVectorDBAdapter(VectorIO, VectorDBsProtocolPrivate): - def __init__(self, config: PGVectorConfig, inference_api: Api.inference) -> None: +class PGVectorVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): + def __init__(self, config: PGVectorVectorIOConfig, inference_api: Api.inference) -> None: self.config = config self.inference_api = inference_api self.conn = None diff --git a/llama_stack/providers/remote/vector_io/qdrant/__init__.py b/llama_stack/providers/remote/vector_io/qdrant/__init__.py index c584e29ef..f5bb7f84c 100644 --- a/llama_stack/providers/remote/vector_io/qdrant/__init__.py +++ b/llama_stack/providers/remote/vector_io/qdrant/__init__.py @@ -8,12 +8,12 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec -from .config import QdrantConfig +from .config import QdrantVectorIOConfig -async def get_adapter_impl(config: QdrantConfig, deps: Dict[Api, ProviderSpec]): - from .qdrant import QdrantVectorDBAdapter +async def get_adapter_impl(config: QdrantVectorIOConfig, deps: Dict[Api, ProviderSpec]): + from .qdrant import QdrantVectorIOAdapter - impl = QdrantVectorDBAdapter(config, deps[Api.inference]) + impl = QdrantVectorIOAdapter(config, deps[Api.inference]) await impl.initialize() return impl diff --git a/llama_stack/providers/remote/vector_io/qdrant/config.py b/llama_stack/providers/remote/vector_io/qdrant/config.py index a6a5a6ff6..613cfa6e4 100644 --- a/llama_stack/providers/remote/vector_io/qdrant/config.py +++ b/llama_stack/providers/remote/vector_io/qdrant/config.py @@ -11,7 +11,7 @@ from pydantic import BaseModel @json_schema_type -class QdrantConfig(BaseModel): +class QdrantVectorIOConfig(BaseModel): location: Optional[str] = None url: Optional[str] = None port: Optional[int] = 6333 diff --git a/llama_stack/providers/remote/vector_io/qdrant/qdrant.py b/llama_stack/providers/remote/vector_io/qdrant/qdrant.py index b2eae3dad..e1091e2cf 100644 --- a/llama_stack/providers/remote/vector_io/qdrant/qdrant.py +++ b/llama_stack/providers/remote/vector_io/qdrant/qdrant.py @@ -21,7 +21,7 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorDBWithIndex, ) -from .config import QdrantConfig +from .config import QdrantVectorIOConfig log = logging.getLogger(__name__) CHUNK_ID_KEY = "_chunk_id" @@ -98,8 +98,8 @@ class QdrantIndex(EmbeddingIndex): await self.client.delete_collection(collection_name=self.collection_name) -class QdrantVectorDBAdapter(VectorIO, VectorDBsProtocolPrivate): - def __init__(self, config: QdrantConfig, inference_api: Api.inference) -> None: +class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): + def __init__(self, config: QdrantVectorIOConfig, inference_api: Api.inference) -> None: self.config = config self.client = AsyncQdrantClient(**self.config.model_dump(exclude_none=True)) self.cache = {} diff --git a/llama_stack/providers/remote/vector_io/sample/__init__.py b/llama_stack/providers/remote/vector_io/sample/__init__.py index c9accdf62..221f47b1c 100644 --- a/llama_stack/providers/remote/vector_io/sample/__init__.py +++ b/llama_stack/providers/remote/vector_io/sample/__init__.py @@ -6,12 +6,12 @@ from typing import Any -from .config import SampleConfig +from .config import SampleVectorIOConfig -async def get_adapter_impl(config: SampleConfig, _deps) -> Any: - from .sample import SampleMemoryImpl +async def get_adapter_impl(config: SampleVectorIOConfig, _deps) -> Any: + from .sample import SampleVectorIOImpl - impl = SampleMemoryImpl(config) + impl = SampleVectorIOImpl(config) await impl.initialize() return impl diff --git a/llama_stack/providers/remote/vector_io/sample/config.py b/llama_stack/providers/remote/vector_io/sample/config.py index 4b7404a26..5126e5eff 100644 --- a/llama_stack/providers/remote/vector_io/sample/config.py +++ b/llama_stack/providers/remote/vector_io/sample/config.py @@ -7,6 +7,6 @@ from pydantic import BaseModel -class SampleConfig(BaseModel): +class SampleVectorIOConfig(BaseModel): host: str = "localhost" port: int = 9999 diff --git a/llama_stack/providers/remote/vector_io/sample/sample.py b/llama_stack/providers/remote/vector_io/sample/sample.py index b0ba50315..cb7193cf4 100644 --- a/llama_stack/providers/remote/vector_io/sample/sample.py +++ b/llama_stack/providers/remote/vector_io/sample/sample.py @@ -7,11 +7,11 @@ from llama_stack.apis.vector_dbs import VectorDB from llama_stack.apis.vector_io import VectorIO -from .config import SampleConfig +from .config import SampleVectorIOConfig -class SampleMemoryImpl(VectorIO): - def __init__(self, config: SampleConfig): +class SampleVectorIOImpl(VectorIO): + def __init__(self, config: SampleVectorIOConfig): self.config = config async def register_vector_db(self, vector_db: VectorDB) -> None: diff --git a/llama_stack/providers/remote/vector_io/weaviate/__init__.py b/llama_stack/providers/remote/vector_io/weaviate/__init__.py index f7120bec0..c93c628d8 100644 --- a/llama_stack/providers/remote/vector_io/weaviate/__init__.py +++ b/llama_stack/providers/remote/vector_io/weaviate/__init__.py @@ -8,12 +8,12 @@ from typing import Dict from llama_stack.providers.datatypes import Api, ProviderSpec -from .config import WeaviateConfig, WeaviateRequestProviderData # noqa: F401 +from .config import WeaviateRequestProviderData, WeaviateVectorIOConfig # noqa: F401 -async def get_adapter_impl(config: WeaviateConfig, deps: Dict[Api, ProviderSpec]): - from .weaviate import WeaviateMemoryAdapter +async def get_adapter_impl(config: WeaviateVectorIOConfig, deps: Dict[Api, ProviderSpec]): + from .weaviate import WeaviateVectorIOAdapter - impl = WeaviateMemoryAdapter(config, deps[Api.inference]) + impl = WeaviateVectorIOAdapter(config, deps[Api.inference]) await impl.initialize() return impl diff --git a/llama_stack/providers/remote/vector_io/weaviate/config.py b/llama_stack/providers/remote/vector_io/weaviate/config.py index d0811acb4..6aad9a5a6 100644 --- a/llama_stack/providers/remote/vector_io/weaviate/config.py +++ b/llama_stack/providers/remote/vector_io/weaviate/config.py @@ -12,5 +12,5 @@ class WeaviateRequestProviderData(BaseModel): weaviate_cluster_url: str -class WeaviateConfig(BaseModel): +class WeaviateVectorIOConfig(BaseModel): pass diff --git a/llama_stack/providers/remote/vector_io/weaviate/weaviate.py b/llama_stack/providers/remote/vector_io/weaviate/weaviate.py index c4d3c39ac..52aa2f3a3 100644 --- a/llama_stack/providers/remote/vector_io/weaviate/weaviate.py +++ b/llama_stack/providers/remote/vector_io/weaviate/weaviate.py @@ -23,7 +23,7 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorDBWithIndex, ) -from .config import WeaviateConfig, WeaviateRequestProviderData +from .config import WeaviateRequestProviderData, WeaviateVectorIOConfig log = logging.getLogger(__name__) @@ -85,12 +85,12 @@ class WeaviateIndex(EmbeddingIndex): collection.data.delete_many(where=Filter.by_property("id").contains_any(chunk_ids)) -class WeaviateMemoryAdapter( +class WeaviateVectorIOAdapter( VectorIO, NeedsRequestProviderData, VectorDBsProtocolPrivate, ): - def __init__(self, config: WeaviateConfig, inference_api: Api.inference) -> None: + def __init__(self, config: WeaviateVectorIOConfig, inference_api: Api.inference) -> None: self.config = config self.inference_api = inference_api self.client_cache = {} diff --git a/llama_stack/providers/tests/vector_io/fixtures.py b/llama_stack/providers/tests/vector_io/fixtures.py index 60d174d9e..30a2679d7 100644 --- a/llama_stack/providers/tests/vector_io/fixtures.py +++ b/llama_stack/providers/tests/vector_io/fixtures.py @@ -12,12 +12,12 @@ import pytest_asyncio from llama_stack.apis.models import ModelInput, ModelType from llama_stack.distribution.datatypes import Api, Provider -from llama_stack.providers.inline.vector_io.chroma import ChromaInlineImplConfig -from llama_stack.providers.inline.vector_io.faiss import FaissImplConfig +from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig +from llama_stack.providers.inline.vector_io.faiss import FaissVectorIOConfig from llama_stack.providers.inline.vector_io.sqlite_vec import SQLiteVectorIOConfig -from llama_stack.providers.remote.vector_io.chroma import ChromaRemoteImplConfig -from llama_stack.providers.remote.vector_io.pgvector import PGVectorConfig -from llama_stack.providers.remote.vector_io.weaviate import WeaviateConfig +from llama_stack.providers.remote.vector_io.chroma import ChromaVectorIOConfig +from llama_stack.providers.remote.vector_io.pgvector import PGVectorVectorIOConfig +from llama_stack.providers.remote.vector_io.weaviate import WeaviateVectorIOConfig from llama_stack.providers.tests.resolver import construct_stack_for_test from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig @@ -45,7 +45,7 @@ def vector_io_faiss() -> ProviderFixture: Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig( + config=FaissVectorIOConfig( kvstore=SqliteKVStoreConfig(db_path=temp_file.name).model_dump(), ).model_dump(), ) @@ -76,7 +76,7 @@ def vector_io_pgvector() -> ProviderFixture: Provider( provider_id="pgvector", provider_type="remote::pgvector", - config=PGVectorConfig( + config=PGVectorVectorIOConfig( host=os.getenv("PGVECTOR_HOST", "localhost"), port=os.getenv("PGVECTOR_PORT", 5432), db=get_env_or_fail("PGVECTOR_DB"), @@ -95,7 +95,7 @@ def vector_io_weaviate() -> ProviderFixture: Provider( provider_id="weaviate", provider_type="remote::weaviate", - config=WeaviateConfig().model_dump(), + config=WeaviateVectorIOConfig().model_dump(), ) ], provider_data=dict( @@ -109,12 +109,12 @@ def vector_io_weaviate() -> ProviderFixture: def vector_io_chroma() -> ProviderFixture: url = os.getenv("CHROMA_URL") if url: - config = ChromaRemoteImplConfig(url=url) + config = ChromaVectorIOConfig(url=url) provider_type = "remote::chromadb" else: if not os.getenv("CHROMA_DB_PATH"): raise ValueError("CHROMA_DB_PATH or CHROMA_URL must be set") - config = ChromaInlineImplConfig(db_path=os.getenv("CHROMA_DB_PATH")) + config = InlineChromaVectorIOConfig(db_path=os.getenv("CHROMA_DB_PATH")) provider_type = "inline::chromadb" return ProviderFixture( providers=[ diff --git a/llama_stack/templates/bedrock/bedrock.py b/llama_stack/templates/bedrock/bedrock.py index 0c8259285..af1d48b7f 100644 --- a/llama_stack/templates/bedrock/bedrock.py +++ b/llama_stack/templates/bedrock/bedrock.py @@ -10,7 +10,7 @@ from llama_models.sku_list import all_registered_models from llama_stack.apis.models import ModelInput from llama_stack.distribution.datatypes import Provider, ToolGroupInput -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.bedrock.bedrock import MODEL_ALIASES from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -37,7 +37,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()} diff --git a/llama_stack/templates/cerebras/cerebras.py b/llama_stack/templates/cerebras/cerebras.py index 2dfae04f8..870240feb 100644 --- a/llama_stack/templates/cerebras/cerebras.py +++ b/llama_stack/templates/cerebras/cerebras.py @@ -13,7 +13,7 @@ from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupIn from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -69,7 +69,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) default_tool_groups = [ ToolGroupInput( diff --git a/llama_stack/templates/fireworks/fireworks.py b/llama_stack/templates/fireworks/fireworks.py index ec350010b..e2e2ca99c 100644 --- a/llama_stack/templates/fireworks/fireworks.py +++ b/llama_stack/templates/fireworks/fireworks.py @@ -18,7 +18,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -58,7 +58,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()} diff --git a/llama_stack/templates/hf-endpoint/hf_endpoint.py b/llama_stack/templates/hf-endpoint/hf_endpoint.py index 4533fd95b..62584929c 100644 --- a/llama_stack/templates/hf-endpoint/hf_endpoint.py +++ b/llama_stack/templates/hf-endpoint/hf_endpoint.py @@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.tgi import InferenceEndpointImplConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) inference_model = ModelInput( diff --git a/llama_stack/templates/hf-serverless/hf_serverless.py b/llama_stack/templates/hf-serverless/hf_serverless.py index 8438de7a5..46efb6f0b 100644 --- a/llama_stack/templates/hf-serverless/hf_serverless.py +++ b/llama_stack/templates/hf-serverless/hf_serverless.py @@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.tgi import InferenceAPIImplConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -52,7 +52,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) inference_model = ModelInput( diff --git a/llama_stack/templates/meta-reference-gpu/meta_reference.py b/llama_stack/templates/meta-reference-gpu/meta_reference.py index a3f82b0c8..9bff981d1 100644 --- a/llama_stack/templates/meta-reference-gpu/meta_reference.py +++ b/llama_stack/templates/meta-reference-gpu/meta_reference.py @@ -19,7 +19,7 @@ from llama_stack.providers.inline.inference.meta_reference import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -58,7 +58,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) inference_model = ModelInput( diff --git a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py index 8c2a6ec9f..fca15fcc5 100644 --- a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py +++ b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py @@ -14,7 +14,7 @@ from llama_stack.providers.inline.inference.meta_reference import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -67,7 +67,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) inference_model = ModelInput( diff --git a/llama_stack/templates/ollama/ollama.py b/llama_stack/templates/ollama/ollama.py index a762e757a..f3383cd5a 100644 --- a/llama_stack/templates/ollama/ollama.py +++ b/llama_stack/templates/ollama/ollama.py @@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig from llama_stack.providers.remote.inference.ollama import OllamaImplConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -53,7 +53,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider_faiss = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) vector_io_provider_sqlite = Provider( provider_id="sqlite_vec", diff --git a/llama_stack/templates/remote-vllm/vllm.py b/llama_stack/templates/remote-vllm/vllm.py index 6c835ef86..40a2d541d 100644 --- a/llama_stack/templates/remote-vllm/vllm.py +++ b/llama_stack/templates/remote-vllm/vllm.py @@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) inference_model = ModelInput( diff --git a/llama_stack/templates/tgi/tgi.py b/llama_stack/templates/tgi/tgi.py index e49c98d72..71718a93d 100644 --- a/llama_stack/templates/tgi/tgi.py +++ b/llama_stack/templates/tgi/tgi.py @@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.tgi import TGIImplConfig from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) inference_model = ModelInput( diff --git a/llama_stack/templates/together/together.py b/llama_stack/templates/together/together.py index b7ac130ed..9ec5b38ba 100644 --- a/llama_stack/templates/together/together.py +++ b/llama_stack/templates/together/together.py @@ -18,7 +18,7 @@ from llama_stack.distribution.datatypes import ( from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.remote.inference.together import TogetherImplConfig from llama_stack.providers.remote.inference.together.together import MODEL_ALIASES from llama_stack.templates.template import DistributionTemplate, RunConfigSettings @@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) embedding_provider = Provider( provider_id="sentence-transformers", diff --git a/llama_stack/templates/vllm-gpu/vllm.py b/llama_stack/templates/vllm-gpu/vllm.py index 54ebd2d41..31900687b 100644 --- a/llama_stack/templates/vllm-gpu/vllm.py +++ b/llama_stack/templates/vllm-gpu/vllm.py @@ -10,7 +10,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) from llama_stack.providers.inline.inference.vllm import VLLMConfig -from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig +from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.templates.template import ( DistributionTemplate, RunConfigSettings, @@ -46,7 +46,7 @@ def get_distribution_template() -> DistributionTemplate: vector_io_provider = Provider( provider_id="faiss", provider_type="inline::faiss", - config=FaissImplConfig.sample_run_config(f"distributions/{name}"), + config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"), ) embedding_provider = Provider( provider_id="sentence-transformers",