Best of Neo4j — June 2024

1. 1
   Article

   neo4j·2y

   Graph vs. Vector RAG — Benchmarking, Optimization Levers, and a Financial Analysis Example

   Exploring the use of graph and vector search in retrieval-augmented generation (RAG) systems, focusing on their application in financial analysis. Discusses the differences between graph and vector search, optimization levers for graph search, and the combination of both methods in RAG. Highlights the benefits of graph databases for modeling complex relationships and dependencies, as well as the limitations and complementarity of vector search. Demonstrates the application of graph and vector search in a financial report RAG example.

   46
2. 2
   Article

   neo4j·2y

   Get Started With GraphRAG: Neo4j’s Ecosystem Tools

   Neo4j’s GraphRAG Ecosystem Tools provide open-source resources to enhance GenAI applications using knowledge graphs. GraphRAG addresses issues like hallucination and lack of domain-specific context by combining retrieval-augmented generation with structured and semi-structured data. The tools include the LLM Knowledge Graph Builder for transforming unstructured text into knowledge graphs, and NeoConverse for generating Cypher graph queries from natural language questions. These tools integrate seamlessly with various programming languages and frameworks, making it easier to build and optimize GenAI applications.

   26
3. 3
   Article

   neo4j·2y

   LLM Knowledge Graph Builder: From Zero to GraphRAG in Five Minutes

   The LLM Knowledge Graph Builder by Neo4j transforms unstructured data into knowledge graphs using machine learning models and a no-code interface. It supports various data sources, including PDFs, web pages, and YouTube videos. The application identifies entities, constructs graphs, and provides an intuitive web interface for interaction. Users can visualize the generated graphs and query data using a Retrieval-Augmented Generation (RAG) chatbot.

   24