Empowering Voice AI Agents with Real-Time Knowledge from Neo4j
summary
Demonstrates a production system that grounds voice agents in Neo4j for real‑time retrieval using Neo4j as real-time knowledge store and graph RAG; documents upload to S3, get chunked and vectorized, then flow S3 → SQS → Lambda → container to insert nodes and metadata into Neo4j (S3 → Lambda → Neo4j ingestion). Agents query via the Python driver, return top five nodes returned with linked context, power live booking dialogs (party of 20 demo) and mostly avoid hallucination while running on AWS/ECS/App Runner.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 0:24Why use Graph RAG
- 1:25Benefits of graph structure
- 3:17Knowledge base portal demo
- 5:03Ingestion pipeline architecture
- 6:29Real-time query process
- 7:11Live agent demo
- 11:30Production implementation summary
- 11:52Tool logging and Q&A
related talks
21mUI in The Age of AI
35mCloud-Native Knowledge Graph Automation to Deliver AI Agents API
29mAgentic AI with Knowledge Graphs on the JVM: A Music Graph in Practice
12mLeveraging Neo4j Graph Data and AI Across the App Development and Deployment Lifecycle
01h 26mBuilding voice agents with OpenAI
20m10 Things I Learned Building Voice Agents in 2025
30mGenAI Beyond Chat with RAG, Knowledge Graphs, and Python
26mStore Your AI Agent's Memory and Context in a Knowledge Graph