Summary

Keywords

neo4j graph databases graphs LLM retrieval augmented generation RAG vector database vector search GenAI AI Artificial intelligence nodes25

Full Transcript

From Resumes to Conversations: Building Production RAG Systems for Voice-Driven Talent Matching Discover how to build sophisticated RAG systems that go beyond simple document search to power intelligent voice agents. This session explores real-world challenges and solutions in creating production-grade RAG architectures for complex domains like talent recruitment. What You'll Learn: Multi-stage RAG architecture: Moving from basic vector similarity to intelligent, domain-aware search with hard constraints, semantic matching, and business logic validation and graph databases Voice-first data processing: Transforming conversational interviews into structured, searchable knowledge using advanced chunking strategies and multi-modal embeddings Hybrid search patterns: Combining vector similarity, keyword matching, and structured data filtering for precision at scale Production challenges: Handling 180k+ profiles with 8 types of embeddings, managing costs, and optimizing for real-time performance Speaker: Tony Xavier Resources: Get Started with Aura - https://bit.ly/3LOLrjh Deployment Center - https://bit.ly/4jOelM3 Ground AI Systems and Agents with Neo4j - https://bit.ly/4oVsnyb #nodes2025 #neo4j #graphdatabase #graphrag #knowledgegraph