JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(qdrant): implement client-side BM25 sparse vectors via fastembed

Browse Source 
- Add sparse_vectors_config with 'bm25' named vector to create_col()
- Compute BM25 sparse vectors from text_lemmatized during insert/update
- Use client-side fastembed Qdrant/bm25 encoder instead of server-side inference
- Graceful fallback if fastembed not installed
- Fixes keyword_search() returning None on self-hosted Qdrant
This commit is contained in:
Soumil Rathi
2026-04-02 10:23:17 -07:00
parent 80749b92bf
commit 4534acdfbe
1 changed files with 80 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mem0/vector_stores/qdrant.py
+80 -21
View File
@@ -2,7 +2,7 @@ import logging
import os
import shutil
from qdrant_client import QdrantClient
from qdrant_client import QdrantClient, models
from qdrant_client.models import (
Distance,
FieldCondition,
@@ -11,6 +11,8 @@ from qdrant_client.models import (
PointIdsList,
PointStruct,
Range,
SparseVector,
SparseVectorParams,
VectorParams,
)
@@ -58,7 +60,7 @@ class Qdrant(VectorStoreBase):
if host and port:
params["host"] = host
params["port"] = port
if not params:
params["path"] = path
self.is_local = True
@@ -73,11 +75,44 @@ class Qdrant(VectorStoreBase):
self.collection_name = collection_name
self.embedding_model_dims = embedding_model_dims
self.on_disk = on_disk
self._bm25_encoder = None
self.create_col(embedding_model_dims, on_disk)
def _get_bm25_encoder(self):
"""Lazy-load the BM25 sparse text encoder (fastembed)."""
if self._bm25_encoder is None:
try:
from fastembed import SparseTextEmbedding
self._bm25_encoder = SparseTextEmbedding(model_name="Qdrant/bm25")
logger.info("BM25 encoder loaded (fastembed Qdrant/bm25)")
except ImportError:
logger.warning("fastembed not installed — BM25 keyword search disabled. Install with: pip install fastembed")
self._bm25_encoder = False # sentinel: tried and failed
except Exception as e:
logger.warning(f"Failed to load BM25 encoder: {e}")
self._bm25_encoder = False
return self._bm25_encoder if self._bm25_encoder is not False else None
def _encode_bm25(self, text: str) -> SparseVector | None:
"""Encode text into a BM25 sparse vector."""
encoder = self._get_bm25_encoder()
if encoder is None:
return None
try:
results = list(encoder.embed([text]))
if results:
sparse = results[0]
return SparseVector(
indices=sparse.indices.tolist(),
values=sparse.values.tolist(),
)
except Exception as e:
logger.debug(f"BM25 encoding failed: {e}")
return None
def create_col(self, vector_size: int, on_disk: bool, distance: Distance = Distance.COSINE):
"""
Create a new collection.
Create a new collection with dense vectors and BM25 sparse vectors.
Args:
vector_size (int): Size of the vectors to be stored.
@@ -95,6 +130,11 @@ class Qdrant(VectorStoreBase):
self.client.create_collection(
collection_name=self.collection_name,
vectors_config=VectorParams(size=vector_size, distance=distance, on_disk=on_disk),
sparse_vectors_config={
"bm25": SparseVectorParams(
modifier=models.Modifier.IDF,
),
},
)
self._create_filter_indexes()
@@ -104,9 +144,9 @@ class Qdrant(VectorStoreBase):
if self.is_local:
logger.debug("Skipping payload index creation for local Qdrant (not supported)")
return
common_fields = ["user_id", "agent_id", "run_id", "actor_id"]
for field in common_fields:
try:
self.client.create_payload_index(
@@ -120,7 +160,8 @@ class Qdrant(VectorStoreBase):
def insert(self, vectors: list, payloads: list = None, ids: list = None):
"""
Insert vectors into a collection.
Insert vectors into a collection, including BM25 sparse vectors
computed from the text_lemmatized payload field.
Args:
vectors (list): List of vectors to insert.
@@ -128,14 +169,21 @@ class Qdrant(VectorStoreBase):
ids (list, optional): List of IDs corresponding to vectors. Defaults to None.
"""
logger.info(f"Inserting {len(vectors)} vectors into collection {self.collection_name}")
points = [
PointStruct(
id=idx if ids is None else ids[idx],
vector=vector,
payload=payloads[idx] if payloads else {},
)
for idx, vector in enumerate(vectors)
]
points = []
for idx, vector in enumerate(vectors):
payload = payloads[idx] if payloads else {}
point_id = idx if ids is None else ids[idx]
# Build named vectors: dense + optional BM25 sparse
named_vectors = {"": vector}
text_for_bm25 = payload.get("text_lemmatized") or payload.get("data", "")
if text_for_bm25:
sparse = self._encode_bm25(text_for_bm25)
if sparse is not None:
named_vectors["bm25"] = sparse
points.append(PointStruct(id=point_id, vector=named_vectors, payload=payload))
self.client.upsert(collection_name=self.collection_name, points=points)
def _create_filter(self, filters: dict) -> Filter:
@@ -150,7 +198,7 @@ class Qdrant(VectorStoreBase):
"""
if not filters:
return None
conditions = []
for key, value in filters.items():
if isinstance(value, dict) and "gte" in value and "lte" in value:
@@ -191,22 +239,24 @@ class Qdrant(VectorStoreBase):
filters (dict, optional): Filters to apply to the search. Defaults to None.
Returns:
list: Search results, or None if the collection does not support sparse vectors.
list: Search results, or None if BM25 is not available.
"""
try:
from qdrant_client import models
sparse_query = self._encode_bm25(query)
if sparse_query is None:
return None
try:
query_filter = self._create_filter(filters) if filters else None
hits = self.client.query_points(
collection_name=self.collection_name,
query=models.Document(text=query, model="Qdrant/bm25"),
query=sparse_query,
using="bm25",
query_filter=query_filter,
limit=limit,
)
return hits.points
except Exception as e:
logger.debug(f"BM25 keyword search failed (collection may lack sparse vector config): {e}")
logger.debug(f"BM25 keyword search failed: {e}")
return None
def delete(self, vector_id: int):
@@ -232,7 +282,16 @@ class Qdrant(VectorStoreBase):
vector (list, optional): Updated vector. Defaults to None.
payload (dict, optional): Updated payload. Defaults to None.
"""
point = PointStruct(id=vector_id, vector=vector, payload=payload)
# Build named vectors with BM25 if payload has text
named_vectors = {"": vector} if vector else vector
if payload and vector:
text_for_bm25 = payload.get("text_lemmatized") or payload.get("data", "")
if text_for_bm25:
sparse = self._encode_bm25(text_for_bm25)
if sparse is not None:
named_vectors["bm25"] = sparse
point = PointStruct(id=vector_id, vector=named_vectors, payload=payload)
self.client.upsert(collection_name=self.collection_name, points=[point])
def get(self, vector_id: int) -> dict: