forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
"""Utility functions for working with vectors and vectorstores."""
|
|
|
|
from typing import List
|
|
|
|
import numpy as np
|
|
|
|
from langchain.math_utils import cosine_similarity
|
|
|
|
|
|
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 []
|
|
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
|