Is there an incremental way to use Embedding to generate a FAISS vector DB or load multiple vectorstores at the same time?

[westlinkin]

First of all, langchain ROCKS!

Is there an incremental way to use Embedding to generate a FAISS vector DB if new documents need to be added to the context every week. Or just generate new additional FAISS vector DB each week, use a chain that loads multiple vectorestore at the same time. Currently VectorDBQAWithSourcesChain can only load one vectorstore

[hwchase17]

i just added some instructions for adding texts - https://langchain.readthedocs.io/en/latest/modules/utils/combine_docs_examples/vectorstores.html#add-texts

does this help?

[westlinkin]

Thanks. This helps a little. but how can I use multiple vectorstores in VectorDBQAWithSourcesChain.from_llm?

[dosubot[bot]]

Hi, @westlinkin! I'm here to help the LangChain team manage their backlog and I wanted to let you know that we are marking this issue as stale.

From what I understand, you were asking if it is possible to use Embedding to generate a FAISS vector DB incrementally or load multiple vectorstores at the same time using a chain. User "hwchase17" provided instructions for adding texts, which you found helpful. However, you still have a question about using multiple vectorstores in VectorDBQAWithSourcesChain.from_llm.

Could you please let us know if this issue is still relevant to the latest version of the LangChain repository? If it is, please comment on the issue to let us know. Otherwise, feel free to close the issue yourself or it will be automatically closed in 7 days.

Thank you for your understanding and contribution to the LangChain project!