Building Your First Chatbot with LangChain and IBM's Granite LLM Model
summary
Builds a local chatbot using LangChain plus IBM's Granite LLM, running entirely on a downloaded model and source on GitHub; uses a C++ backend and a LangChain prompt+chain setup, adds a callback streaming feature so answers appear word-by-word, and demonstrates a 131,072 token context setting for long contexts. Shows grammarss to force JSON outputs for tests, proves a simple stateless question/answer then upgrades to a working chat with explicit chat history storage and re-sent context.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:53What is an LLM
- 3:17Chatbots and LLMs
- 4:21LangChain and Granite LLM
- 5:06Setting up the local chatbot environment
- 6:54One-question chatbot
- 7:15Grammars for LLM output
- 9:23Templates and chains
- 11:34Chat history for context
- 13:24Code and Q&A
related talks
01h 12mBuild Your Own AI Chatbot with OpenAI & LangChain
01h 59mLLM applications with LangChain
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
34mBuilding a Custom AI Chatbot with Spring Boot, React, and LangChain4j
41mBuild Next-Generation Applications with Language Models using LangChain and Python
01h 50mChatGPT & LLMs: A Practical Starter's Guide to Language Chains
48mUnlocking LLM Potential: From Exploration to Integration
25mLangChain with Azure AI: Building LLM powered Applications