Llm For Generative Qa
by Kavita Ganeshan
LLM for Generative QA on Long Documents
Recently I was working on a problem statement that needed to explore LLM for Question Answering context. The problem was to use opensource LLM model (not Open AI gpt) and host in a local system for QA on custom data. I found very interesting set of articles and code repo that helped through this process. This is a fast moving topic and hence the code I wrote or the articles might get outdated in a weeks time. My LLM Code repo
- This is an amazing article by Abonia Sojasingarayar
- Author gives basic architecture for a QA system to process Long and verbose documents eg: Contracts, Legal agreements, clinical research papers etc.
- Link to author’s codebase gives starter help on Langchain, Chroma. Though the code is a little outdated considering the speed in which Langchain community is updating the repo so fast to keep up with latest trends.Code
- This article by Mick gives a good view on constraints of using LLM models directly for a Long document QA system Link
- Matt Boegner talks about a generic knowledge retrieval architecture Link
- Amazing blog by Langchain contributors. Talks about how they updated their framework for better retrieval by providing more classes and connectors. Link
- Couple of Youtube Creators who I follow to get amazing code samples and explanations on Langchain and LLM in general are
- Interesting projects to track. There are more projects in each space. The above articles can give a varied list. The ones which I have used are listed down.
- LLM framework - Langchain
- Vector Stores - Chromadb, FAISS, Elastic Search, Milvus, Weaviate, Pinecone, Quadrant. Lot of traction I see is for Pinecone now. I saw a stack called OPL (Open AI, Pinecone and Langchain)
- Connect data to LLMs - LLamaIndex
- Models to try from HuggingFace - Google Flan T5 - XXL, Facebook Blenderbot 1B distill, Facebook Opt 66B, BigScience Bloom 560m
- To demo a quick version - Gradio, Streamlit
- To learn more prompt templates - James Briggs playlist
Subscribe via RSS