The community member is experiencing slow retrieval speed, about 1 minute per query, when using the AutoMergingRetriever with a Pinecone vector database. Other community members suggest trying to use the base vector store instead of Pinecone to see if that improves the speed. They also mention that embedding can take a while if there are a lot of documents, and provide a link to a Discord channel with tips to speed it up. The community members discuss potential reasons for the slow speed, such as latency with the Pinecone index, and the community member says they will try to work out a solution.
Hey! Has anyone experience with the retrieval speed of the AutoMergingRetriever? It is taking for me about 1 min/query, with pinecone vector db. I am wondering if it's only for me so slow.
Hmm nothing really that special, my only guess is there is some latency with the pinecone index 🤔 Pinecone is only used once during the initial retrieve
