Olicorne
Olicorne
I'm hardly in a position to lead anything but sure, absolutely. Thanks a lot. I can happily give an opinion and light review of the code though. Thanks again!
I think you just have to familiarize yourself with the [contributing guidelines](https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md) and make a PR :)
I think so yeah.
Yes this is still relevant
I still do think it's a valuable feature to incorporate chapters as metadata. Or even if someone manages : to include chapter transition into the text directly using timestamps.
Similarity search not working well when number of ingested documents is great, say over one hundred.
I posted a question to another thread but think this might be useful here too. The sentence transformers have a truncation length and I suspect that if the text splitter...
Similarity search not working well when number of ingested documents is great, say over one hundred.
(copying my message from [there](https://github.com/simonw/llm-sentence-transformers/issues/8#issuecomment-1732618592) ) I'm sharing my own 'rolling' sbert script to avoid clipping the sentences. It's seemingly functionnal but not very elegent, a class would be better...
Also relevant in this issue so copy pasting : Surprisingly, the exact feature we seem to be looking for is mentionned here in langchain : https://python.langchain.com/en/latest/modules/indexes/vectorstores/examples/faiss.html
Hi! I'm sorry I meant response_mode instead of answer_mode. Correcting this. I saw the page you linked multiple times and still think it is not informative enough. For example I'm...
Stumbled into this very issue. Turns out that I was using `scroll_exists` instead of `scroll_exit`, and also forgot to add the `[keys]` before! Looks simple enough to add too