Before we close this issue, we wanted to check if it is still relevant to the latest version of the LangChain repository. If it is, please let us know by commenting on this issue. Otherwise, feel free to close the issue yourself or it will be automatically closed in 7 days. Thank you...
As a potential solution, you might want to consider using a different retriever that supports this feature. For instance, theFAISSorQdrantretrievers in LangChain support thesimilarity_score_thresholdsearch type. These retrievers return not only the documents but also the similarity score of the query...
将新的枚举值添加到MultiVectorRetriever.SearchType中。
The issue you're experiencing seems to be related to the way similarity scores are calculated in the Chroma class of LangChain. In the Chroma class, the similarity_search_with_score method is used to calculate similarity scores. This method returns a list of documents most similar to the ...
File "/scratch/c7031420/.conda/envs/langchain/lib/python3.9/site-packages/langchain/vectorstores/base.py", line 395, in get_relevant_documents self.vectorstore.similarity_search_with_relevance_scores( File ".conda/envs/langchain/lib/python3.9/site-packages/langchain/vectorstores/base.py", lin...
Replace : langchain/libs/langchain/langchain/retrievers/multi_vector.py Lines 63 to 68 inb20c264 ifself.search_type==SearchType.mmr: sub_docs=self.vectorstore.max_marginal_relevance_search( query,**self.search_kwargs ) else: sub_docs=self.vectorstore.similarity_search(query,**self.search_...
I'm Dosu, and I'm here to help the LangChain team manage their backlog. I wanted to let you know that we are marking this issue as stale. From what I understand, you reported an issue regarding aTypeErrorwhen using theFAISS.similarity_search_with_score_by_vector()function with thescore...
ccurmemerged commita001037intolangchain-ai:masterJul 15, 2024 73 checks passed Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment Labels 🤖:improvementMedium size change to existing code to handle new use-caseslgtmPR looks good. Use to confirm ...
功能描述 / Feature Description 实际测试bge系列的embedding(bge-large-en为例)时,直接使用原文进行匹配,对应的最相似匹配度从0.8开始,由于SCORE_THRESHOLD的限制,人工判定最精准的原文相似度大概会落到1.1总是被过滤掉,此处不应该限死0-1,否则框架很可能无法使用
Redis vector range queries expect a radius rather than a score threshold. The existing code passed the score threshold through directly as the radius param. This means that a higher score threshold...