Building an Expert Q&A Bot with Open Source Tools and LLMs
summary
Claims building an expert QA bot that answers questions about an open‑source project by pulling GitHub docs into a vector DB, using LangChain for loaders and chains, Chroma for embeddings storage, Gradio for the UI and Label Studio for human annotation. It uses OpenAI GPT‑3.5 embeddings + retrieval‑augmented generation, requires an OpenAI API key, outputs JSON tasks for annotation, adds vetted “good” responses back into the vector store, and demonstrably updates answers (example: reported Python requirement changes to 3.8).
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:09Talk overview
- 3:55Open source tools & LangChain
- 8:51Limitations of large language models
- 10:36Building QA chatbot
- 17:02Embeddings & vector DBs
- 20:38Setting up the workshop environment
- 35:26Improving bots with feedback
- 41:15Label Studio setup
- 57:15Incorporating feedback
related talks
01h 12mBuild Your Own AI Chatbot with OpenAI & LangChain
25mLets Build A Node.js ChatGPT-Like Bot With AI APIs
32mChatBot Learning Assistant with Large Language Models
40mDeploying Your Own Language Models: A Use Case Demo with Open Source Tools
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
51mA ChatGPT on your own data: how does it work?
24mBuilding a Viral Open Source AI Chatbot: Journey from Concept to Reality
48mBuilding AI Powered Applications with Java