Best of Neo4j — September 2024

1. 1
   Article

   neo4j·2y

   GraphRAG Field Guide: Navigating the World of Advanced RAG Patterns

   GraphRAG refers to a set of Retrieval Augmented Generation (RAG) patterns using a graph structure for improved data retrieval. The post introduces various GraphRAG patterns, categorized into basic, intermediate, and advanced levels, each requiring unique pre-processing and graph patterns. GraphRAG techniques often leverage relationships within data to enhance retrieval effectiveness, usually involving client-side data structures and Python code. The post also encourages contribution to an open-source GraphRAG Pattern Catalog and provides resources for further learning and implementation.

   16

   1
2. 2
   Article

   Hacker News·2y

   getzep/graphiti: Build and query dynamic, temporally-aware Knowledge Graphs

   Graphiti builds dynamic, temporally aware Knowledge Graphs that manage evolving relationships between entities over time. It supports the ingestion of both unstructured and structured data and offers hybrid search functionality combining semantic and full-text search. Designed for scalability, Graphiti can handle large datasets and is tailored for applications in sales, customer service, health, and finance. Essential requirements include Python 3.10+, Neo4j 5.21+, and an OpenAI API key for LLM inference and embedding.

   15