Тёмный

RAG with a Neo4j Knowledge Graph: How it Works and How to Set It Up 

Neo4j
Подписаться 48 тыс.
Просмотров 24 тыс.
50% 1

In this video, Philipp Brunenberg explains how RAG (retrieval augmented generation) with a Neo4j Knowledge Graph works and how we can set it up on your laptop. He’ll also give a brief introduction on how we can customize the code from the Gen-AI Stack.
We’ll cover:
What is RAG?
How does RAG with a Neo4j Knowledge Graph work?
What are the benefits of using RAG & Neo4j?
How can I set up RAG with Neo4j using a Llama2 model and the GenAI Stack?
Links:
GenAI Walkthrough: neo4j.com/developer-blog/gena...
Neo4j & GenAI: neo4j.com/generativeai/
Github Repo: github.com/docker/genai-stack
RAG Blogs: neo4j.com/developer-blog/tagg...
LLM Blogs: neo4j.com/developer-blog/tagg...
@philippbrunenberg www.philipp-brunenberg.de/
00:00 Introduction
00:29 What is RAG?
02:09 The Neo4j Vector Store
03:03 Augmenting LLM answers with RAG
04:50 Using the GenAI-Stack
06:37 GenAI-Stack Configuration
08:08 The compose file
09:47 Loading data into Neo4j
11:59 Using the chat frontend
15:30 Conclusion
#neo4j #graphdatabase #knowledgegraph #langchain #genai #rag #ollama

Наука

Опубликовано:

 

8 май 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 42   
@aaen9417
@aaen9417 4 месяца назад
Thank you for publishing this type of content. This is absolutely amazing!
@AAL3087
@AAL3087 2 месяца назад
Great whirlwind tour to present a concrete understading of RAG with knowledge graphs in Neo4j. Thanks. Looking forward to exploring this channel more to learn more about RAG/KGs/GenAIStack etc.
@neo4j
@neo4j 2 месяца назад
Thank you very much!
@NelsLindahl
@NelsLindahl 4 месяца назад
Loved this video and the pace!
@neo4j
@neo4j 4 месяца назад
Thank you very much!
@roy.awderby
@roy.awderby 4 месяца назад
Thank you for the deep explanation
@neo4j
@neo4j 4 месяца назад
Thank you!
@deepbayes6808
@deepbayes6808 4 месяца назад
This was really useful., also the presentor did an amazing job. But it was too short. I wish to see a longer more tutorial like version of it too. Or to have links to relevant knowledge and tutorials.
@neo4j
@neo4j 4 месяца назад
Thank you very much! we have some more in-depth material on our blog. Check the links in the video description
@kenchang3456
@kenchang3456 4 месяца назад
Thanks for this robust example.
@neo4j
@neo4j 4 месяца назад
Thank you!
@joshuacunningham7912
@joshuacunningham7912 3 месяца назад
Excellent video. Thank you.
@neo4j
@neo4j 3 месяца назад
Thank you!
@jacobschuster5261
@jacobschuster5261 4 месяца назад
Brilliant, thank you!
@neo4j
@neo4j 4 месяца назад
Thanks! Glad you like it
@armelhyacinthe6173
@armelhyacinthe6173 4 месяца назад
Thank you ❤
@neo4j
@neo4j 4 месяца назад
You're welcome! Glad it is helpful
@alimahmoudmansour9681
@alimahmoudmansour9681 4 месяца назад
Thank you so much
@neo4j
@neo4j 4 месяца назад
Glad it is helpful!
@tecnopadre
@tecnopadre 25 дней назад
It would be really useful to do this video adding how to convert the unstructured data to KG and the use it on a RAG. Step by step it's what makes people use Neo4j more. Thank you!
@neo4j
@neo4j 24 дня назад
Thank you for the suggestion!
@RajendraKadam725
@RajendraKadam725 2 месяца назад
Thanks for sharing the video @neo4j. By the way, both responses provided in the video were inaccurate. Why wasn't the correct answer generated? 🤔
@neo4j
@neo4j 2 месяца назад
sorry - can you share the timestamp where you think the answers were wrong?
@leonh-kd3cm
@leonh-kd3cm Месяц назад
It is still not clear whether at the final stage what input do you provide to LLM to get the final question: - Original Question text - Text extracted from the KG nodes/edges - SO, you do not provide text associated with the best K answers resulted form initial generation of embeddings from the user prompt? ...and how to you compose the text extracted from the nodes? What is the technique?
@MatanItah
@MatanItah Месяц назад
About how long can we expect the StackOverflow loader to import using the settings in the video to run?
@D1zZit
@D1zZit 3 месяца назад
Amazing! Planning on integrating this with my neo4j db which has 1 billion relationships, might be pushing the limits a bit 🤣🤣
@neo4j
@neo4j 3 месяца назад
let us know how it goes :)
@samreenkhan4994
@samreenkhan4994 Месяц назад
did it work ?
@D1zZit
@D1zZit Месяц назад
@@samreenkhan4994 Querying and using RAG on the database itself worked. Generating embeddings with FAST-RP did not despite the powerful specs of hardware. Instead had to generate embeddings on a condensed data form with many missing properties. Still working it out.
@allminhuman2602
@allminhuman2602 4 месяца назад
Great video! What would be the minimum recommended system specs for this to work?
@neo4j
@neo4j 4 месяца назад
Thank you! Any relatively modern laptop should work to give it a go and do a test-run.
@henkhbit5748
@henkhbit5748 4 месяца назад
Great video, I have Windows and ollama is not for windows yet. Can I run the docker under wsl2?
@nbbhaskar3294
@nbbhaskar3294 Месяц назад
I have wsl2 docker setup in my windows and I am able to run ollama successfully.
@podunkman2709
@podunkman2709 4 месяца назад
This is only demo of some commercial product? Can I use it within company to build some service?
@neo4j
@neo4j 4 месяца назад
the stack is based on open-source components which you can use to build your own product/servcice
@podunkman2709
@podunkman2709 2 месяца назад
Is there any loader ready to insert own data (csv or else - not pdf) instead of stackOverflow?
@neo4j
@neo4j 2 месяца назад
not as such, but the repo is available and you can modify the loader to take on other data: github.com/docker/genai-stack
@davidecacozza392
@davidecacozza392 2 месяца назад
Hi! It is possible to use an own neo4j graph?
@neo4j
@neo4j 2 месяца назад
yeah, totally - check out our recent Going Meta Episodes ( neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/ ) or our Courses on GraphAcademy ( graphacademy.neo4j.com/ )
@samreenkhan4994
@samreenkhan4994 Месяц назад
did u try? if yes, then how
@Aristocle
@Aristocle Месяц назад
How can I load PDF, markdown, into Neo4j?
@neo4j
@neo4j 24 дня назад
not directly, see this community post for a few pointers: community.neo4j.com/t/loading-pdf-or-doc-content-into-neo4j/8967 this doesnt cover AI assisted tools which you can use these days for similar results
Далее
Best of NODES 2023 - GenAI
1:00:31
Просмотров 987
GraphRAG: LLM-Derived Knowledge Graphs for RAG
15:40
Просмотров 31 тыс.
RAG for LLMs explained in 3 minutes
3:15
Просмотров 9 тыс.
Reliable, fully local RAG agents with LLaMA3
21:19
Просмотров 64 тыс.
Neo4j in 100 Seconds
2:37
Просмотров 468 тыс.
LangGraph 101: it's better than LangChain
32:26
Просмотров 29 тыс.
What is Retrieval-Augmented Generation (RAG)?
6:36
Просмотров 452 тыс.
Replace Github Copilot with a Local LLM
5:43
Просмотров 123 тыс.
Knowledge Graphs - Computerphile
12:05
Просмотров 97 тыс.
СЛОМАЛСЯ ПК ЗА 2000$🤬
0:59
Просмотров 1,9 млн
СЛОМАЛСЯ ПК ЗА 2000$🤬
0:59
Просмотров 1,9 млн
LTWay ts001
1:00
Просмотров 93 тыс.