Jeffrey (Dongkyu) Kim
Jeffrey (Dongkyu) Kim
I really want this feature, too. It will be awesome!
Hi, @jasonjmcghee I am making [RAGchain](https://github.com/NomaDamas/RAGchain), which is specialized framework for RAG. I think you are interested in building RAG in local apple silicon environment. But, I think it will...
@jasonjmcghee Great! I'd love to make data loader from `rem` for [`RAGchain`](https://github.com/NomaDamas/RAGchain). Use `rem` as a datasource. I'll let you know my progress.
@jasonjmcghee I make loader for RAGchain and Langchain. (Compatible with Langchain) It loads texts from sqlite3 file, and make it to Langchain `Document` schema. You can see PR [here](https://github.com/NomaDamas/RAGchain/pull/423). Now,...
> @vkehfdl1 that looks very cool! Not knowing too much about `RAGChain`, how would the data extractor pipeline be run? Would it be beneficial if the extractor is pipeline is...
@jasonjmcghee @seletz Plus, here is sample image that I run `RAGchain` with `rem`. I saw this issue tab with `rem` record was turned on 😁  for the use-case? I will try your great prompt! Plus, I will try some experiments for improving answer quality. First, it...
@seletz It will be cool! I agree `rem` will be great to keep "no network connection" as default, and user can always access their data easily with hooks or trigger....
@jasonjmcghee I try your custom prompt at [here](https://github.com/vkehfdl1/rem-RAGchain/pull/5) and the result is actually promising. There are some examples I tried. (I record `rem` issue and repo pages) ``` Question :...
Update. Now, ingest document without duplicated ones. I used token f1 score to calculate similarity. And, I use hybrid retrieval and WeightedTimeReranker for latest information. This is my [PR](https://github.com/vkehfdl1/rem-RAGchain/pull/6) here....