Build an Advanced RAG Chatbot with Neo4j Knowledge Graph

preview_player
Показать описание
Advanced RAG (Retrieval-Augmented Generation) and knowledge graphs make AI chatbots more powerful and context-aware. Your chatbot can digest more data sources than just one document. We feed the chatbot with different text data regarding the event of Sam Altman's surprising exit and return to OpenAI. This video walks you through how to build the system with LLM tools.

0:00 Intro
0:42 Load wiki articles
1:23 Load news data
1:46 Steps of entity and relationship extraction
2:04 What is spaCy-llm?
2:41 Why I chose spaCy-llm?
3:15 Summarize articles with LangChain
4:28 spaCy-llm for entities and relationships
5:55 GPT-4 refining results and cypher queries
6:40 Neo4j Knowledge graph + advanced RAG
7:24 Outro

What the video covers:

- Constructing a Neo4j knowledge graph with the help of spacy-llm for labeling entities and relationships.
- Building advanced RAG on top of knowledge graph.
- Besides chatting with the AI chatbot, interact with the graph interface on the Streamlit app.

Check out the full code here:

#generativeai #llm #neo4j #aichatbot #knowledgegraph #datascienceprojects

Music: Medicine by WinnieTheMoog
Рекомендации по теме
Комментарии
Автор

Very good walkthrough. I like how you integrated NER, GraphDB, and LLM together.

johnhelewa
Автор

what an awesome explanation. not sure if I can follow all the steps, but great overview of the process and logic.

bparlan
Автор

Hi Leann
Thank you! Your videos are an amazing source of inspiration! keep up the good work!

mandraketupi
Автор

I’m new to knowledge graph and you make it simple to understand

firm
Автор

This is really great, can you please create another video with another LLM using hugging face? Great stuff!!

niikhiilbankar
Автор

Incredible video! Can’t thank you enough for your tutorial. I’ve been trying to decide whether a vector database or knowledge graph would be the most interesting/most efficient way to scale complexity. Answer: BOTH!! Research complete. ❤🎉

thezwave
Автор

Thanks Leann. This is sure a lot of help for me to get into RAG.
Thanks Again.

tayyabchadhar
Автор

A good start. Thank You. We look forward to your next video in January 2024!

davidtindell
Автор

Easy to understand. Thank you for posting this video. I'm rooting for your channel; you got a new sub.

douglasdrumond
Автор

Great content. Please hang some pics on the wall to suppress echo it will be easier to listen:)

tomwawer
Автор

This is so good, Leann!

I'm just jumping into the field of Knowledge Graphs! This will be huge for RAG applications!

Why did you stop publishing videos?

krisograbek
Автор

Really awesome, Thank you for this video

Jeganbaskaran
Автор

this is great content! thanks much for sharing!

jtran
Автор

Great content! I am a complete beginner: I have a Neo4j db already populated, I want to "only" do the chatbot portion connected with GPT4. Would you mind guiding me on which .py I should use in this usecase?

In the meantime, I am getting a "UnboundLocalError: local variable 'nodes' referenced before assignment". Not sure what to do... Thanks!!

alexandreturlier
Автор

Thanks for this video, subscribed! :)

enkhbatenkhjargal
Автор

Can we implement the azure open ai creds like api key, model name, endpoint, type and version in the ipynb file and run it? Also please mention the dependency libraries of the functions.py file as visual, Node, Edge, Cypher_graph are not getting initialised in VSC while running the file....

ramdeeproy
Автор

Hi Thank you for this amazing video. 

I have a question about KG creation on Neo4J. 
May I know the prompt you used to refine and cypher query generation for the results generated of openaiKG.ipynb at 5:56

MachineLearningZuu
Автор

thank you for the crisp view on KG+RAG, can we create KG on multiple csv files, currently csv agents were lacking behind to answer questions based on content, they only search for matching column for the question rather content passed.

kingmouli
Автор

I feel like a Noob in the field of AI, after seeing your video. But the video is great

AIGOAT-zm
Автор

Great video! A question I had: Are knowledge graphs good at taking a user query, such as “What happened to Sam Altman, and also when was the OpenAI board created”? Because I’ve been working with RAG and vector db for last 5 months, and when you run that query with similarity search, it sometimes doesn’t give you both topics in your retrieved documents. Is thr knowledge graph good for this or also suffers some issues, I know there’s some step back prompting ideas to cover this but wanted to know your thoughts.

lavamonkeymc