Information retrieval and knowledge extraction is a growing field, which has witnessed a notable shift with the advent of Large Language Models (LLMs) and knowledge graphs, particularly within the context of multi-hop question answering.
In this session, we’ll walk you through a project that leverages the robust capabilities of Neo4j Vector Index and Neo4j Graph Database to implement a retrieval-augmented generation system, aiming to provide precise and contextually rich answers to user queries.
Guest: Saurav Joshi
GenAI Landing
https://bit.ly/4eRHS6g
Blog: https://medium.com/neo4j/enhanced-qa-integrating-unstructured-and-graph-knowledge-using-neo4j-and-langchain-6abf6fc24c27
Code: https://github.com/sauravjoshi23/towards-agi/tree/main/retrieval%20augmented%20generation/integrated-qa-neo4j-langchain-semi-structured-data
Google Gemini: https://deepmind.google/technologies/gemini/
Multi Modal RAG: https://blog.llamaindex.ai/multimodal-rag-pipeline-with-llamaindex-and-neo4j-a2c542eb0206
Slides: https://docs.google.com/presentation/d/1RaTCegq1nOAwRS821kbI29k3dv--NHxHvd2WwE3aHRQ
0:00 Intro
9:55 Enhanced QA
10:33 Neo4j x LangChain
12:30 Benefits of Knowledge Graphs
14:54 RAG Workflow
19:58 Vector Search
22:28 Graph Search
28:30 Q&A
32:50 Code: RAG
42:45 Code: Knowledge Graph
47:05 Code: RAG (continued)
50:55 Q&A
1:03:33 WrapUp
#neo4j #graphdatabase #langchain #llm #knowledgegraph #rag #largelanguagemodels #chatbot