This article provides a step-by-step walkthrough for building a Retrieval Augmented Generation (RAG) application from PDF documents using GenAI-Stack and OpenAI. It covers topics such as PDF document parsing, using Neo4j AuraDB for knowledge storage, data ingestion with the Python + Neo4j driver, semantic search with Neo4j
Table of contents
A Step-by-step Walkthrough With GenAI-Stack and OpenAIGitHub - Joshua-Yu/graph-rag: Graph based retrieval + GenAI = Better RAG in productionDocuments Are Property GraphWhy Vectors Should Be Stored Together with Knowledge Graph?1. PDF Document Parsing & Content Extraction2. Neo4j AuraDB for Knowledge StoreAdding Q&A Features to Your Knowledge Graph in 3 Simple Steps3. Python + Neo4j Driver for Data Ingestion4. Neo4j Vector Index for Semantic SearchText Embedding — What, Why and How?5. GenAI-Stack for Fast PrototypingFast Track to Mastery: Neo4j GenAI Stack for Efficient LLM Applications6. OpenAI Models for Embedding & Text GenerationSort: