Building Cypher Queries With Open-Source LLMs
summary
Shows a full pipeline that crawls news with Fundus, extracts entities via GLiNER and relations via Relic, clusters topics and writes triples into Neo4j, then uses Haystack plus an open source LLM (Snowflake Arctic mentioned) to auto-generate Cypher from a natural language prompt. Demonstrates prompt templates, schema injection, retrieval of similar entities, a Jupyter demo, and live execution of generated Cypher against the graph to produce grounded answers.
AI-written summary · about
chapters (6)
- 0:00Introduction and motivation
- 3:44RAG with knowledge graphs
- 8:25Building a toy knowledge graph
- 16:00Query building with LLMs
- 19:56Live demo and results
- 21:04Q&A
related talks
28mGrounded Intelligence Boosting LLMs with Real-Time Graph Context
22mBuilding Contextual Knowledge Graphs to Adapt, Evaluate, and Leverage LLMs
36mGraphRAG Explained 🔥 Building Smarter LLMs
10mTalk to Your Graph: A Practical Guide to Building a Dual-LLM Q&A System for a Fashion Graph
23mConnecting the Dots With Context Graphs
31mLive Q&A
34mEverything is a graph, including LLM Applications (and that’s handy)
01h 17mGraph Database and Retrieval Augmented Generation