mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-14 20:32:50 +00:00
update resolver to only pass vector_stores section of run config
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Using Router only from VectorDBs Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> removing model_api from vector store providers Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix test Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating integration tests Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> special handling for replay mode for available providers Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo
parent
24a1430c8b
commit
accc4c437e
46 changed files with 397 additions and 702 deletions
|
|
@ -6,29 +6,14 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
||||
from .config import ChromaVectorIOConfig
|
||||
|
||||
|
||||
async def get_provider_impl(
|
||||
config: ChromaVectorIOConfig, deps: dict[Api, Any], run_config: StackRunConfig | None = None
|
||||
):
|
||||
from llama_stack.providers.remote.vector_io.chroma.chroma import (
|
||||
ChromaVectorIOAdapter,
|
||||
)
|
||||
async def get_provider_impl(config: ChromaVectorIOConfig, deps: dict[Api, Any]):
|
||||
from llama_stack.providers.remote.vector_io.chroma.chroma import ChromaVectorIOAdapter
|
||||
|
||||
vector_stores_config = None
|
||||
if run_config and run_config.vector_stores:
|
||||
vector_stores_config = run_config.vector_stores
|
||||
|
||||
impl = ChromaVectorIOAdapter(
|
||||
config,
|
||||
deps[Api.inference],
|
||||
deps[Api.models],
|
||||
deps.get(Api.files),
|
||||
vector_stores_config,
|
||||
)
|
||||
impl = ChromaVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -24,7 +24,6 @@ class ChromaVectorIOConfig(BaseModel):
|
|||
return {
|
||||
"db_path": db_path,
|
||||
"kvstore": SqliteKVStoreConfig.sample_run_config(
|
||||
__distro_dir__=__distro_dir__,
|
||||
db_name="chroma_inline_registry.db",
|
||||
__distro_dir__=__distro_dir__, db_name="chroma_inline_registry.db"
|
||||
),
|
||||
}
|
||||
|
|
|
|||
|
|
@ -6,29 +6,16 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
||||
from .config import FaissVectorIOConfig
|
||||
|
||||
|
||||
async def get_provider_impl(
|
||||
config: FaissVectorIOConfig, deps: dict[Api, Any], run_config: StackRunConfig | None = None
|
||||
):
|
||||
async def get_provider_impl(config: FaissVectorIOConfig, deps: dict[Api, Any]):
|
||||
from .faiss import FaissVectorIOAdapter
|
||||
|
||||
assert isinstance(config, FaissVectorIOConfig), f"Unexpected config type: {type(config)}"
|
||||
|
||||
vector_stores_config = None
|
||||
if run_config and run_config.vector_stores:
|
||||
vector_stores_config = run_config.vector_stores
|
||||
|
||||
impl = FaissVectorIOAdapter(
|
||||
config,
|
||||
deps[Api.inference],
|
||||
deps[Api.models],
|
||||
deps.get(Api.files),
|
||||
vector_stores_config,
|
||||
)
|
||||
impl = FaissVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -8,10 +8,7 @@ from typing import Any
|
|||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from llama_stack.providers.utils.kvstore.config import (
|
||||
KVStoreConfig,
|
||||
SqliteKVStoreConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
|
||||
from llama_stack.schema_utils import json_schema_type
|
||||
|
||||
|
||||
|
|
@ -22,8 +19,5 @@ class FaissVectorIOConfig(BaseModel):
|
|||
@classmethod
|
||||
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
|
||||
return {
|
||||
"kvstore": SqliteKVStoreConfig.sample_run_config(
|
||||
__distro_dir__=__distro_dir__,
|
||||
db_name="faiss_store.db",
|
||||
)
|
||||
"kvstore": SqliteKVStoreConfig.sample_run_config(__distro_dir__=__distro_dir__, db_name="faiss_store.db")
|
||||
}
|
||||
|
|
|
|||
|
|
@ -17,28 +17,14 @@ 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,
|
||||
QueryChunksResponse,
|
||||
VectorIO,
|
||||
)
|
||||
from llama_stack.core.datatypes import VectorStoresConfig
|
||||
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import (
|
||||
HealthResponse,
|
||||
HealthStatus,
|
||||
VectorDBsProtocolPrivate,
|
||||
)
|
||||
from llama_stack.providers.datatypes import HealthResponse, HealthStatus, 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.openai_vector_store_mixin import OpenAIVectorStoreMixin
|
||||
from llama_stack.providers.utils.memory.vector_store import (
|
||||
ChunkForDeletion,
|
||||
EmbeddingIndex,
|
||||
VectorDBWithIndex,
|
||||
)
|
||||
from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorDBWithIndex
|
||||
|
||||
from .config import FaissVectorIOConfig
|
||||
|
||||
|
|
@ -156,12 +142,7 @@ class FaissIndex(EmbeddingIndex):
|
|||
|
||||
await self._save_index()
|
||||
|
||||
async def query_vector(
|
||||
self,
|
||||
embedding: NDArray,
|
||||
k: int,
|
||||
score_threshold: float,
|
||||
) -> QueryChunksResponse:
|
||||
async def query_vector(self, embedding: NDArray, k: int, score_threshold: float) -> QueryChunksResponse:
|
||||
distances, indices = await asyncio.to_thread(self.index.search, embedding.reshape(1, -1).astype(np.float32), k)
|
||||
chunks = []
|
||||
scores = []
|
||||
|
|
@ -176,12 +157,7 @@ class FaissIndex(EmbeddingIndex):
|
|||
|
||||
return QueryChunksResponse(chunks=chunks, scores=scores)
|
||||
|
||||
async def query_keyword(
|
||||
self,
|
||||
query_string: str,
|
||||
k: int,
|
||||
score_threshold: float,
|
||||
) -> QueryChunksResponse:
|
||||
async def query_keyword(self, query_string: str, k: int, score_threshold: float) -> QueryChunksResponse:
|
||||
raise NotImplementedError(
|
||||
"Keyword search is not supported - underlying DB FAISS does not support this search mode"
|
||||
)
|
||||
|
|
@ -201,19 +177,10 @@ class FaissIndex(EmbeddingIndex):
|
|||
|
||||
|
||||
class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
|
||||
def __init__(
|
||||
self,
|
||||
config: FaissVectorIOConfig,
|
||||
inference_api: Inference,
|
||||
models_api: Models,
|
||||
files_api: Files | None,
|
||||
vector_stores_config: VectorStoresConfig | None = None,
|
||||
) -> None:
|
||||
def __init__(self, config: FaissVectorIOConfig, inference_api: Inference, 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.vector_stores_config = vector_stores_config
|
||||
self.cache: dict[str, VectorDBWithIndex] = {}
|
||||
|
||||
async def initialize(self) -> None:
|
||||
|
|
@ -255,17 +222,11 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPr
|
|||
except Exception as e:
|
||||
return HealthResponse(status=HealthStatus.ERROR, message=f"Health check failed: {str(e)}")
|
||||
|
||||
async def register_vector_db(
|
||||
self,
|
||||
vector_db: VectorDB,
|
||||
) -> None:
|
||||
async def register_vector_db(self, vector_db: VectorDB) -> None:
|
||||
assert self.kvstore is not None
|
||||
|
||||
key = f"{VECTOR_DBS_PREFIX}{vector_db.identifier}"
|
||||
await self.kvstore.set(
|
||||
key=key,
|
||||
value=vector_db.model_dump_json(),
|
||||
)
|
||||
await self.kvstore.set(key=key, value=vector_db.model_dump_json())
|
||||
|
||||
# Store in cache
|
||||
self.cache[vector_db.identifier] = VectorDBWithIndex(
|
||||
|
|
@ -288,12 +249,7 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPr
|
|||
del self.cache[vector_db_id]
|
||||
await self.kvstore.delete(f"{VECTOR_DBS_PREFIX}{vector_db_id}")
|
||||
|
||||
async def insert_chunks(
|
||||
self,
|
||||
vector_db_id: str,
|
||||
chunks: list[Chunk],
|
||||
ttl_seconds: int | None = None,
|
||||
) -> None:
|
||||
async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None:
|
||||
index = self.cache.get(vector_db_id)
|
||||
if index is None:
|
||||
raise ValueError(f"Vector DB {vector_db_id} not found. found: {self.cache.keys()}")
|
||||
|
|
@ -301,10 +257,7 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPr
|
|||
await index.insert_chunks(chunks)
|
||||
|
||||
async def query_chunks(
|
||||
self,
|
||||
vector_db_id: str,
|
||||
query: InterleavedContent,
|
||||
params: dict[str, Any] | None = None,
|
||||
self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None
|
||||
) -> QueryChunksResponse:
|
||||
index = self.cache.get(vector_db_id)
|
||||
if index is None:
|
||||
|
|
|
|||
|
|
@ -6,27 +6,14 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
||||
from .config import MilvusVectorIOConfig
|
||||
|
||||
|
||||
async def get_provider_impl(
|
||||
config: MilvusVectorIOConfig, deps: dict[Api, Any], run_config: StackRunConfig | None = None
|
||||
):
|
||||
async def get_provider_impl(config: MilvusVectorIOConfig, deps: dict[Api, Any]):
|
||||
from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusVectorIOAdapter
|
||||
|
||||
vector_stores_config = None
|
||||
if run_config and run_config.vector_stores:
|
||||
vector_stores_config = run_config.vector_stores
|
||||
|
||||
impl = MilvusVectorIOAdapter(
|
||||
config,
|
||||
deps[Api.inference],
|
||||
deps.get(Api.models),
|
||||
deps.get(Api.files),
|
||||
vector_stores_config,
|
||||
)
|
||||
impl = MilvusVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -8,10 +8,7 @@ from typing import Any
|
|||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.providers.utils.kvstore.config import (
|
||||
KVStoreConfig,
|
||||
SqliteKVStoreConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
|
||||
from llama_stack.schema_utils import json_schema_type
|
||||
|
||||
|
||||
|
|
@ -26,7 +23,6 @@ class MilvusVectorIOConfig(BaseModel):
|
|||
return {
|
||||
"db_path": "${env.MILVUS_DB_PATH:=" + __distro_dir__ + "}/" + "milvus.db",
|
||||
"kvstore": SqliteKVStoreConfig.sample_run_config(
|
||||
__distro_dir__=__distro_dir__,
|
||||
db_name="milvus_registry.db",
|
||||
__distro_dir__=__distro_dir__, db_name="milvus_registry.db"
|
||||
),
|
||||
}
|
||||
|
|
|
|||
|
|
@ -6,28 +6,15 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
||||
from .config import QdrantVectorIOConfig
|
||||
|
||||
|
||||
async def get_provider_impl(
|
||||
config: QdrantVectorIOConfig, deps: dict[Api, Any], run_config: StackRunConfig | None = None
|
||||
):
|
||||
async def get_provider_impl(config: QdrantVectorIOConfig, deps: dict[Api, Any]):
|
||||
from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
|
||||
|
||||
vector_stores_config = None
|
||||
if run_config and run_config.vector_stores:
|
||||
vector_stores_config = run_config.vector_stores
|
||||
|
||||
assert isinstance(config, QdrantVectorIOConfig), f"Unexpected config type: {type(config)}"
|
||||
impl = QdrantVectorIOAdapter(
|
||||
config,
|
||||
deps[Api.inference],
|
||||
deps[Api.models],
|
||||
deps.get(Api.files),
|
||||
vector_stores_config,
|
||||
)
|
||||
impl = QdrantVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -9,10 +9,7 @@ from typing import Any
|
|||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from llama_stack.providers.utils.kvstore.config import (
|
||||
KVStoreConfig,
|
||||
SqliteKVStoreConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
|
||||
from llama_stack.schema_utils import json_schema_type
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -6,28 +6,15 @@
|
|||
|
||||
from typing import Any
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.providers.datatypes import Api
|
||||
|
||||
from .config import SQLiteVectorIOConfig
|
||||
|
||||
|
||||
async def get_provider_impl(
|
||||
config: SQLiteVectorIOConfig, deps: dict[Api, Any], run_config: StackRunConfig | None = None
|
||||
):
|
||||
async def get_provider_impl(config: SQLiteVectorIOConfig, deps: dict[Api, Any]):
|
||||
from .sqlite_vec import SQLiteVecVectorIOAdapter
|
||||
|
||||
vector_stores_config = None
|
||||
if run_config and run_config.vector_stores:
|
||||
vector_stores_config = run_config.vector_stores
|
||||
|
||||
assert isinstance(config, SQLiteVectorIOConfig), f"Unexpected config type: {type(config)}"
|
||||
impl = SQLiteVecVectorIOAdapter(
|
||||
config,
|
||||
deps[Api.inference],
|
||||
deps[Api.models],
|
||||
deps.get(Api.files),
|
||||
vector_stores_config,
|
||||
)
|
||||
impl = SQLiteVecVectorIOAdapter(config, deps[Api.inference], deps.get(Api.files))
|
||||
await impl.initialize()
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -8,10 +8,7 @@ from typing import Any
|
|||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.providers.utils.kvstore.config import (
|
||||
KVStoreConfig,
|
||||
SqliteKVStoreConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
|
||||
|
||||
|
||||
class SQLiteVectorIOConfig(BaseModel):
|
||||
|
|
@ -23,7 +20,6 @@ class SQLiteVectorIOConfig(BaseModel):
|
|||
return {
|
||||
"db_path": "${env.SQLITE_STORE_DIR:=" + __distro_dir__ + "}/" + "sqlite_vec.db",
|
||||
"kvstore": SqliteKVStoreConfig.sample_run_config(
|
||||
__distro_dir__=__distro_dir__,
|
||||
db_name="sqlite_vec_registry.db",
|
||||
__distro_dir__=__distro_dir__, db_name="sqlite_vec_registry.db"
|
||||
),
|
||||
}
|
||||
|
|
|
|||
|
|
@ -17,14 +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.models import Models
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import (
|
||||
Chunk,
|
||||
QueryChunksResponse,
|
||||
VectorIO,
|
||||
)
|
||||
from llama_stack.core.datatypes import VectorStoresConfig
|
||||
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
|
|
@ -176,32 +170,18 @@ class SQLiteVecIndex(EmbeddingIndex):
|
|||
|
||||
# Insert vector embeddings
|
||||
embedding_data = [
|
||||
(
|
||||
(
|
||||
chunk.chunk_id,
|
||||
serialize_vector(emb.tolist()),
|
||||
)
|
||||
)
|
||||
((chunk.chunk_id, serialize_vector(emb.tolist())))
|
||||
for chunk, emb in zip(batch_chunks, batch_embeddings, strict=True)
|
||||
]
|
||||
cur.executemany(
|
||||
f"INSERT INTO [{self.vector_table}] (id, embedding) VALUES (?, ?);",
|
||||
embedding_data,
|
||||
)
|
||||
cur.executemany(f"INSERT INTO [{self.vector_table}] (id, embedding) VALUES (?, ?);", embedding_data)
|
||||
|
||||
# Insert FTS content
|
||||
fts_data = [(chunk.chunk_id, chunk.content) for chunk in batch_chunks]
|
||||
# DELETE existing entries with same IDs (FTS5 doesn't support ON CONFLICT)
|
||||
cur.executemany(
|
||||
f"DELETE FROM [{self.fts_table}] WHERE id = ?;",
|
||||
[(row[0],) for row in fts_data],
|
||||
)
|
||||
cur.executemany(f"DELETE FROM [{self.fts_table}] WHERE id = ?;", [(row[0],) for row in fts_data])
|
||||
|
||||
# INSERT new entries
|
||||
cur.executemany(
|
||||
f"INSERT INTO [{self.fts_table}] (id, content) VALUES (?, ?);",
|
||||
fts_data,
|
||||
)
|
||||
cur.executemany(f"INSERT INTO [{self.fts_table}] (id, content) VALUES (?, ?);", fts_data)
|
||||
|
||||
connection.commit()
|
||||
|
||||
|
|
@ -217,12 +197,7 @@ class SQLiteVecIndex(EmbeddingIndex):
|
|||
# Run batch insertion in a background thread
|
||||
await asyncio.to_thread(_execute_all_batch_inserts)
|
||||
|
||||
async def query_vector(
|
||||
self,
|
||||
embedding: NDArray,
|
||||
k: int,
|
||||
score_threshold: float,
|
||||
) -> QueryChunksResponse:
|
||||
async def query_vector(self, embedding: NDArray, k: int, score_threshold: float) -> QueryChunksResponse:
|
||||
"""
|
||||
Performs vector-based search using a virtual table for vector similarity.
|
||||
"""
|
||||
|
|
@ -262,12 +237,7 @@ class SQLiteVecIndex(EmbeddingIndex):
|
|||
scores.append(score)
|
||||
return QueryChunksResponse(chunks=chunks, scores=scores)
|
||||
|
||||
async def query_keyword(
|
||||
self,
|
||||
query_string: str,
|
||||
k: int,
|
||||
score_threshold: float,
|
||||
) -> QueryChunksResponse:
|
||||
async def query_keyword(self, query_string: str, k: int, score_threshold: float) -> QueryChunksResponse:
|
||||
"""
|
||||
Performs keyword-based search using SQLite FTS5 for relevance-ranked full-text search.
|
||||
"""
|
||||
|
|
@ -411,19 +381,10 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
|
|||
and creates a cache of VectorDBWithIndex instances (each wrapping a SQLiteVecIndex).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config,
|
||||
inference_api: Inference,
|
||||
models_api: Models,
|
||||
files_api: Files | None,
|
||||
vector_stores_config: VectorStoresConfig | None = None,
|
||||
) -> None:
|
||||
def __init__(self, config, inference_api: Inference, 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.vector_stores_config = vector_stores_config
|
||||
self.cache: dict[str, VectorDBWithIndex] = {}
|
||||
self.vector_db_store = None
|
||||
|
||||
|
|
@ -436,9 +397,7 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
|
|||
for db_json in stored_vector_dbs:
|
||||
vector_db = VectorDB.model_validate_json(db_json)
|
||||
index = await SQLiteVecIndex.create(
|
||||
vector_db.embedding_dimension,
|
||||
self.config.db_path,
|
||||
vector_db.identifier,
|
||||
vector_db.embedding_dimension, self.config.db_path, vector_db.identifier
|
||||
)
|
||||
self.cache[vector_db.identifier] = VectorDBWithIndex(vector_db, index, self.inference_api)
|
||||
|
||||
|
|
@ -453,11 +412,7 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
|
|||
return [v.vector_db for v in self.cache.values()]
|
||||
|
||||
async def register_vector_db(self, vector_db: VectorDB) -> None:
|
||||
index = await SQLiteVecIndex.create(
|
||||
vector_db.embedding_dimension,
|
||||
self.config.db_path,
|
||||
vector_db.identifier,
|
||||
)
|
||||
index = await SQLiteVecIndex.create(vector_db.embedding_dimension, self.config.db_path, vector_db.identifier)
|
||||
self.cache[vector_db.identifier] = VectorDBWithIndex(vector_db, index, self.inference_api)
|
||||
|
||||
async def _get_and_cache_vector_db_index(self, vector_db_id: str) -> VectorDBWithIndex | None:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue