LLM applications with LangChain
summary
Hands-on demo builds three concrete apps: a QA bot over internal docs using FAISS vector store and OpenAI Ada embeddings (26 source pages → 346 chunks), a natural‑language-to‑Postgres tool that uses GPT-3.5-turbo-16k to generate SQL, run it, catch errors and auto‑correct, and an agent that calls tools (schedule + reserve API with ~50% simulated booking success). Code uses LangChain chains, prompt templates, chunking and retriever logic; basic memory and streaming are shown but require heavier tuning for production.
AI-written summary · about
chapters (8)
- 0:00LLM apps with LangChain
- 5:04What is LangChain
- 13:04QA over structured data
- 43:52QA over unstructured data
- 1:05:41Building RAG chain
- 1:16:31LangChain agents intro
- 1:39:48Multi-tool agent demo
- 1:51:42Q&A
related talks
01h 50mChatGPT & LLMs: A Practical Starter's Guide to Language Chains
25mLangChain with Azure AI: Building LLM powered Applications
01h 34mA Practical Starter's Guide to building LLM based projects
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
41mBuild Next-Generation Applications with Language Models using LangChain and Python
01h 04mBuilding LLM powered applications in Ruby
06mBuilding LLM Apps on App Engine
29mUsing LangChain and LlamaIndex to customize LLMs...