phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 22:02:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

qdrant inline provider

Browse source 
Signed-off-by: Daniele Martinoli <dmartino@redhat.com>
This commit is contained in:
Daniele Martinoli 2025-02-26 10:00:37 +01:00
parent bfc79217a8
commit 6a7fe6312e
7 changed files with 67 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/remote/vector_io/qdrant/config.py
View file

@ -23,7 +23,6 @@ class QdrantVectorIOConfig(BaseModel):
prefix: Optional[str] = None
timeout: Optional[int] = None
host: Optional[str] = None
path: Optional[str] = None
@classmethod
def sample_run_config(cls, **kwargs: Any) -> Dict[str, Any]:

9
llama_stack/providers/remote/vector_io/qdrant/qdrant.py
View file

@ -6,7 +6,7 @@
import logging
import uuid
from typing import Any, Dict, List, Optional
from typing import Any, Dict, List, Optional, Union
from numpy.typing import NDArray
from qdrant_client import AsyncQdrantClient, models
@ -16,12 +16,13 @@ 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.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
from llama_stack.providers.utils.memory.vector_store import (
EmbeddingIndex,
VectorDBWithIndex,
)
from .config import QdrantVectorIOConfig
from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig
log = logging.getLogger(__name__)
CHUNK_ID_KEY = "_chunk_id"
@ -99,7 +100,9 @@ class QdrantIndex(EmbeddingIndex):
class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
def __init__(self, config: QdrantVectorIOConfig, inference_api: Api.inference) -> None:
def __init__(
self, config: Union[RemoteQdrantVectorIOConfig, InlineQdrantVectorIOConfig], inference_api: Api.inference
) -> None:
self.config = config
self.client = AsyncQdrantClient(**self.config.model_dump(exclude_none=True))
self.cache = {}