mirror of
https://github.com/hwchase17/langchain.git
synced 2026-06-09 10:17:00 +00:00
qdrant: init package (#21146)
## Description This PR introduces the new `langchain-qdrant` partner package, intending to deprecate the community package. ## Changes - Moved the Qdrant vector store implementation `/libs/partners/qdrant` with integration tests. - The conditional imports of the client library are now regular with minor implementation improvements. - Added a deprecation warning to `langchain_community.vectorstores.qdrant.Qdrant`. - Replaced references/imports from `langchain_community` with either `langchain_core` or by moving the definitions to the `langchain_qdrant` package itself. - Updated the Qdrant vector store documentation to reflect the changes. ## Testing - `QDRANT_URL` and [`QDRANT_API_KEY`](583e36bf6b) env values need to be set to [run integration tests](d608c93d1f) in the [cloud](https://cloud.qdrant.tech). - If a Qdrant instance is running at `http://localhost:6333`, the integration tests will use it too. - By default, tests use an [`in-memory`](https://github.com/qdrant/qdrant-client?tab=readme-ov-file#local-mode) instance(Not comprehensive). --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Erick Friis <erickfriis@gmail.com>
This commit is contained in:
70
libs/partners/qdrant/langchain_qdrant/_utils.py
Normal file
70
libs/partners/qdrant/langchain_qdrant/_utils.py
Normal file
@@ -0,0 +1,70 @@
|
||||
from typing import List, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
Matrix = Union[List[List[float]], List[np.ndarray], np.ndarray]
|
||||
|
||||
|
||||
def maximal_marginal_relevance(
|
||||
query_embedding: np.ndarray,
|
||||
embedding_list: list,
|
||||
lambda_mult: float = 0.5,
|
||||
k: int = 4,
|
||||
) -> List[int]:
|
||||
"""Calculate maximal marginal relevance."""
|
||||
if min(k, len(embedding_list)) <= 0:
|
||||
return []
|
||||
if query_embedding.ndim == 1:
|
||||
query_embedding = np.expand_dims(query_embedding, axis=0)
|
||||
similarity_to_query = cosine_similarity(query_embedding, embedding_list)[0]
|
||||
most_similar = int(np.argmax(similarity_to_query))
|
||||
idxs = [most_similar]
|
||||
selected = np.array([embedding_list[most_similar]])
|
||||
while len(idxs) < min(k, len(embedding_list)):
|
||||
best_score = -np.inf
|
||||
idx_to_add = -1
|
||||
similarity_to_selected = cosine_similarity(embedding_list, selected)
|
||||
for i, query_score in enumerate(similarity_to_query):
|
||||
if i in idxs:
|
||||
continue
|
||||
redundant_score = max(similarity_to_selected[i])
|
||||
equation_score = (
|
||||
lambda_mult * query_score - (1 - lambda_mult) * redundant_score
|
||||
)
|
||||
if equation_score > best_score:
|
||||
best_score = equation_score
|
||||
idx_to_add = i
|
||||
idxs.append(idx_to_add)
|
||||
selected = np.append(selected, [embedding_list[idx_to_add]], axis=0)
|
||||
return idxs
|
||||
|
||||
|
||||
def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
|
||||
"""Row-wise cosine similarity between two equal-width matrices."""
|
||||
if len(X) == 0 or len(Y) == 0:
|
||||
return np.array([])
|
||||
|
||||
X = np.array(X)
|
||||
Y = np.array(Y)
|
||||
if X.shape[1] != Y.shape[1]:
|
||||
raise ValueError(
|
||||
f"Number of columns in X and Y must be the same. X has shape {X.shape} "
|
||||
f"and Y has shape {Y.shape}."
|
||||
)
|
||||
try:
|
||||
import simsimd as simd # type: ignore
|
||||
|
||||
X = np.array(X, dtype=np.float32)
|
||||
Y = np.array(Y, dtype=np.float32)
|
||||
Z = 1 - simd.cdist(X, Y, metric="cosine")
|
||||
if isinstance(Z, float):
|
||||
return np.array([Z])
|
||||
return np.array(Z)
|
||||
except ImportError:
|
||||
X_norm = np.linalg.norm(X, axis=1)
|
||||
Y_norm = np.linalg.norm(Y, axis=1)
|
||||
# Ignore divide by zero errors run time warnings as those are handled below.
|
||||
with np.errstate(divide="ignore", invalid="ignore"):
|
||||
similarity = np.dot(X, Y.T) / np.outer(X_norm, Y_norm)
|
||||
similarity[np.isnan(similarity) | np.isinf(similarity)] = 0.0
|
||||
return similarity
|
||||
Reference in New Issue
Block a user