How to Build Knowledge Graphs With LLMs (python tutorial)

preview_player
Показать описание
My previous video, showcasing how to use Large Language Models (LLMs) together with graph databases like Neo4J, had a lot of traction and many people were asking for details on the implementation.

So, here’s a technical walkthrough from scratch, going through how I built the demo step by step.

▬▬▬▬▬▬ T I M E S T A M P S ▬▬▬▬▬▬

0:00 - Intro
1:03 - Environment overview
2:47 - Neo4J & OpenAI Configuration
7:50 - Helper functions
9:15 - Identifying entities and relationships in data
21:49 - Generating Cypher Statements
33:20 - Running the full pipeline
38:30 - Monitoring token consumption
Рекомендации по теме
Комментарии
Автор

Thank you. Subscribed. There are so many AI channels that just talk how you can build this and that with LLMs and other word soup techniques, but don't actually show the process.

lhxperimental
Автор

thank you for sharing this! this is going to help so many organizations who can't afford teams of data analysts. to have this much insight into their data.... 🤯

w_chadly
Автор

Great video without any annoying music, thanks! Would be great to see a from-scratch video about how you actually use this in answering user questions, combining the graph data and LLM capabillities.

Epistemophilos
Автор

Thank you so much for including also the price tag. Seeing that it is only a few cents that such proof of concepts accumulate to is really encouraging to go and try it out. Also everything else in this video was absolute gold! Really complete, really A-to-Z. Thank you so much.

unhooked
Автор

That was a great share on knowledge graphs and LLMs. Thanks for putting it together.

chrisogonas
Автор

First of all, first class presentation! I've been considering building something quite similar to utilise knowledge graphs as a method of storing long term memory for ChatGPT by proxy of function calling. The vague idea I have floating in my head, is that the relationships could be automated using the LLM at inference time with some well formatted prompts. The last part of the video where you showcase cypher generation is probably the missing piece of the puzzle for connecting the storage (Neo4J) and this is great for updating the knowledge graph. I just hope you get a chance to showcase a bi-directional example of this in your part 2, as right now I'm not strong on knowledge graph ingestion in a way that makes sense for seamless LLM output when a knowledge graph is used to supplement it.

KCMNJL
Автор

Excellent video, thankyou for actually coding and showing the process, I was long stuck in this

masked
Автор

on my todo list. Was looking it, many thanks !

kamiln
Автор

Very good round up. I just started to follow you. This is as useful as papers.

kewpietonkatsu
Автор

That was incredibly interesting and inspiring! Thank you!

vivalancsweert
Автор

Great Video! One thing i would like to add: I think that for larger datasets it is faster / more efficient to use the import tool that comes with Neo4j Aura, instead of executing a separate query for each node / relation.

Musicever
Автор

Great video! I really learn a lot and enjoy the video. Thanks!

satri
Автор

Make your text as big as possible when sharing your screen. Thank you for your video.

ryanslab
Автор

Hi Johanes, thank you and congratulations for the video! On your prompts, when you instruct the LLM how to extract entities, you are kind of describing a model for the data, right? (Project, Technology, Client). On more traditional methodologies for generating knowledge graphs, this looks similar to the ontology. Do you think would be correct to think of it like this?

eduugr
Автор

Johannes - thank you for the video! what r ur thoughts on building a KG-native CRM?

chriseun
Автор

Great video Johannes, thanks!

Just wondering whether you could do a retrieval example of this?

Would be great to see how it compares to a vector store. When you read online theres a lot saying that retrieval is slower and less efficient but not sure what the think.

Would be great to get your insight with a video to explain

hassanullah
Автор

This is awsome, thanks for the work. Your setup reminds me of Windows XP :D

Doggy_Styles_Coding
Автор

Awesome man ❤❤❤🎉🎉 i love it the way you present if i have button to subscribe more i will hit it millions time

nikhilshingadiya
Автор

Great video, thanks for that!
I would also be interested in data quality here. I noticed a few inconsistencies in your input data. How did LLM cope with that? How accurate is the output knowledge graph? Can you make a more detailed comparison or share the output file pls?

michalstun
Автор

Great Job Johannes !
I'm curious to discuss about the interest of going with Azur OpenAI instead of directly to OpenAI

Thx, and once again, great job !

joffreylemery