Build Next-Generation Applications with Language Models using LangChain and Python
summary
Shows how to build LLM features with LangChain and Python using OpenAI-style function calling, tool decorators and agent loops, plus concrete tactics: prototype with a big model then fine-tune to GPT4.1 mini fine-tune to cut token costs by ~1000x, use streaming responses for UX, use RAG with vector stores (Chroma, Pinecone or S3 vectors for cost reduction on AWS Bedrock), memory summarization every ~5 messages, and prefer a synchronous server over naive serverless for latency and cost.
AI-written summary · about
chapters (10)
- 0:00Introduction and speaker intro
- 3:55UX perspectives on LLM apps
- 8:55LLM parameters and model selection
- 13:30Why frameworks like LangChain matter
- 17:47Tools and agents with LangChain
- 22:52LangChain building blocks
- 25:50Prompt templates and memory
- 31:17Retrieval Augmented Generation basics
- 34:35Calling external APIs with LangChain
- 36:17Production tips and Q&A
related talks
01h 50mChatGPT & LLMs: A Practical Starter's Guide to Language Chains
01h 59mLLM applications with LangChain
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
01h 34mA Practical Starter's Guide to building LLM based projects
38mBuilding Generative AI Applications in Python with LangChain
01h 00mUnleashGPT: Mastering the Implementation of Large Language Models
01h 12mBuild Your Own AI Chatbot with OpenAI & LangChain
01h 43mBuilding LLM Agents (Hackathon)