mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
Fix the parameter error of 'Qdrant.maximal_marginal_relevance' (#1921)
Hi, first and foremost, I would like to express my gratitude for your outstanding work; it's truly remarkable! https://github.com/hwchase17/langchain/blob/master/langchain/vectorstores/qdrant.py#L134 It appears that there might be a minor issue with the `limit` parameter being passed incorrectly in the `Qdrant.maximal_marginal_relevance` function. This seems to be a typographical error. Signed-off-by: weiyang <weiyang.ones@gmail.com>
This commit is contained in:
parent
62e08f80de
commit
e50c1ea7fb
@ -165,7 +165,7 @@ class Qdrant(VectorStore):
|
|||||||
query_vector=embedding,
|
query_vector=embedding,
|
||||||
with_payload=True,
|
with_payload=True,
|
||||||
with_vectors=True,
|
with_vectors=True,
|
||||||
limit=k,
|
limit=fetch_k,
|
||||||
)
|
)
|
||||||
embeddings = [result.vector for result in results]
|
embeddings = [result.vector for result in results]
|
||||||
mmr_selected = maximal_marginal_relevance(embedding, embeddings, k=k)
|
mmr_selected = maximal_marginal_relevance(embedding, embeddings, k=k)
|
||||||
|
Loading…
Reference in New Issue
Block a user