Context Engineering with Redis and LangChain
summary
Claims concrete outcomes: a Jupyter lab with an OpenAI key that runs a LangChain/RAG baseline, a Redis for vector search backing both JSON/hash records and embeddings, and an agent memory server that exposes REST endpoints for short‑term working-session and long-term memory with automatic LLM-driven memory promotion. The Alexa demo actually writes embeddings, retrieves stored preferences (returns both “black” and “blue”), and exposes design tradeoffs around timestamps, update vs append, orchestration, caching, queues, and cost/latency.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 2:24Context engineering in AI
- 11:50Core components
- 20:40Memory systems
- 31:18Short-term vs long-term memory
- 42:14Demo: Alexa memory
- 49:02Q&A
related talks
25mLangChain with Azure AI: Building LLM powered Applications
01h 59mLLM applications with LangChain
46mCodepocalypse Now Lang Chain4j vs Spring Al
36mProduction Ready RAG
28mBuild an AI Research Agent
41mServerless LLM with AWS Lambda and LangChain: A Revolution in Application Development
48mGoing Beyond Prompt Engineering
01h 13mBuilding Production-Ready AI Systems in 90 Minutes