Building GenAI Apps with the LangChain Neo4j Package
summary
Hands‑on demo of the LangChain Neo4j Python integration showing concrete code: connect with Neo4jGraph to run Cypher, add a new actor+movie node and visualize it, use Neo4jVector to load an existing movie‑plot index and retrieve Toy Story via a “sentient cowboy doll” similarity search, create a tiny “libraries” index from two documents, run GraphCypherQAChain to generate Cypher that returns Heat’s release year (1995) and optionally skip the second LLM call, and persist conversations with Neo4jChatMessageHistory using session IDs.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 2:14What is LangChain
- 5:04LangChain Neo4j package
- 6:08Neo4j Graph class demo
- 11:11Neo4j Vector class demo
- 17:52Graph Cypher QA chain demo
- 23:12Chat message history demo
- 27:06Closing and resources
related talks
12mLeveraging Neo4j Graph Data and AI Across the App Development and Deployment Lifecycle
30mGenAI Beyond Chat with RAG, Knowledge Graphs, and Python
01h 59mLLM applications with LangChain
51mAI-Powered Development: Hands-On Techniques for Immediate Impact
23mConnecting the Dots With Context Graphs
41mBuild Next-Generation Applications with Language Models using LangChain and Python
01h 17mGraph Database and Retrieval Augmented Generation
25mFrom LangChain to LangSmith and LangGraph: the Future of AI