GraphRAG: How Lettria Unlocked 20% Accuracy Gains with Qdrant and Neo4j Daniel Azoulai shows a hybrid approach of combining Qdrant’s vector search capabilities with Neo4j’s knowledge graphs, which addresses the limitations of traditional vector-only RAG systems, particularly in handling complex, regulated documents in industries like pharma and aerospace. The result was an improvement of over 20% in accuracy and enhanced explainability and auditability in AI outputs.
Neo4j & GenerativeAI Learning Path On GraphAcademy, we have curated a GRAPHRAG Learning Path for you. Start with the just updated Neo4j & GenerativeAI Fundamentals and follow the path or just pick the lessons you are interested in, e.g. how to build Knowledge Graphs or using frameworks like LangChain or Agents with MCP.
GraphRAG Explained: AI Retrieval with Knowledge Graphs & Cypher
In this video, Meredith Syed walks you through building a GraphRAG system that extracts structured knowledge from unstructured text using LLMs and stores it in a Neo4j knowledge graph. You’ll learn how to transform text into nodes and relationships, construct Cypher queries from natural language and generate contextual answers by combining LangChain, Neo4j and IBM watsonx.ai.
Integrating Neo4j With Symfony: Profiling Queries and Centralized Logging
This guide by Ghlen Nagels demonstrates how to integrate Neo4j with Symfony’s Profiler and Logger tools to monitor Cypher query performance and centralise logging. Symfony’s debugging capabilities allow developers to gain insights into query execution times, identify bottlenecks and efficiently debug issues. The tutorial provides step-by-step instructions for setting up the Profiler and Logger, enabling a streamlined development workflow when working with Neo4j in Symfony applications.
|
