Checked other resources
- I added a very descriptive title to this issue.
- I searched the LangChain documentation with the integrated search.
- I used the GitHub search to find a similar question and didn't find it.
- I am sure that this is a bug in LangChain rather than my code.
- The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
Example Code
Not applicable
Error Message and Stack Trace (if applicable)
- No response*
Description
There is no HNSW index in the pgvector vector store:
https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/vectorstores/pgvector.py
Unlike the pgembedding vectore store:
https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/vectorstores/pgembedding.py#L192
System Info
Not applicable
3条答案
按热度按时间kfgdxczn1#
你好，@holasoftware ,我想知道为什么你需要在pgvector.py中提供hnsw索引功能，而它已经在pgembedding.py中了？
velaa5lx2#
PR: langchain-ai/langchain-postgres#85
cpjpxq1n3#
你好，@holasoftware ,我想知道为什么你需要在pgvector.py中提供hnsw索引功能，而它已经在pgembedding.py中了？
pgembedding不适用于pgvector,而是适用于pg_embedding。它们是不同的Postgres扩展。实际上，还有pgvecto_rs(docs),专为第三个Postgres扩展pgvecto.rs设计：-p。
因此，这个PR是为pgvector设计的，我认为它更广泛地使用，因为该扩展受到AWS和GCP等的支持。