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.
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.
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?
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!
How does this compare to what MS is doing in the GraphRAG paper, it seems like MS was really jazzed on using the LLM, GPT4, (in some way it wasn't clear) to create the relationships, the edges/weights etc, and this was the secret sauce, I assume this is different from what Neo4j is doing, but could you expand?
this was a bit before GraphRAG become a term - check out the latest episodes from GoingMeta ( neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/ ) where go into GraphRAG a bit more as well
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
@@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.
@@neo4j sry... That was a UA-cam issue. They have been rolling out new layout for UA-cam desktop and it is disgusting. I thought it was you guys having a specific layout for your videos. I have new question... Can we not use docker? And still use neo4j
Like the guy below @mtprovasti I'd love to see variations. Maybe a ... part two with additional technical detail w/ an eye towards permanence (i.e., development and deployment)
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.
Thank you very much!
Thank you for publishing this type of content. This is absolutely amazing!
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.
Thank you very much! we have some more in-depth material on our blog. Check the links in the video description
Def. Interested seeing variations of this. Seems super easy.
Thanks for this robust example.
Thank you!
Loved this video and the pace!
Thank you very much!
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?
Thanks for sharing the video @neo4j.
By the way, both responses provided in the video were inaccurate.
Why wasn't the correct answer generated? 🤔
sorry - can you share the timestamp where you think the answers were wrong?
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!
Thank you for the suggestion!
Thank you for the deep explanation
Thank you!
Excellent video. Thank you.
Thank you!
Does the node embedding include information of node/relations? or just the text of the answer/question.
Brilliant, thank you!
Thanks! Glad you like it
How does this compare to what MS is doing in the GraphRAG paper, it seems like MS was really jazzed on using the LLM, GPT4, (in some way it wasn't clear) to create the relationships, the edges/weights etc, and this was the secret sauce, I assume this is different from what Neo4j is doing, but could you expand?
this was a bit before GraphRAG become a term - check out the latest episodes from GoingMeta ( neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/ ) where go into GraphRAG a bit more as well
Trying to run this on Linux in my home lab and it's erroring out on the genai-stack-database when I run docer compose --profile linux-gpu up.
the pull mode is not in the hub anymore... what happened?
Is there any loader ready to insert own data (csv or else - not pdf) instead of stackOverflow?
not as such, but the repo is available and you can modify the loader to take on other data: github.com/docker/genai-stack
How many users can interact simultaneously ?
Great video! What would be the minimum recommended system specs for this to work?
Thank you! Any relatively modern laptop should work to give it a go and do a test-run.
About how long can we expect the StackOverflow loader to import using the settings in the video to run?
Great video, I have Windows and ollama is not for windows yet. Can I run the docker under wsl2?
I have wsl2 docker setup in my windows and I am able to run ollama successfully.
This is only demo of some commercial product?
Can I use it within company to build some service?
the stack is based on open-source components which you can use to build your own product/servcice
Thank you so much
Glad it is helpful!
How can I load PDF, markdown, into Neo4j?
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
Thank you ❤
You're welcome! Glad it is helpful
Hi! It is possible to use an own neo4j graph?
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/ )
did u try? if yes, then how
Amazing! Planning on integrating this with my neo4j db which has 1 billion relationships, might be pushing the limits a bit 🤣🤣
let us know how it goes :)
did it work ?
@@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.
what is up with the page...? looks weird!
which one?
@@neo4j sry... That was a UA-cam issue. They have been rolling out new layout for UA-cam desktop and it is disgusting. I thought it was you guys having a specific layout for your videos.
I have new question... Can we not use docker? And still use neo4j
Like the guy below @mtprovasti I'd love to see variations. Maybe a ... part two with additional technical detail w/ an eye towards permanence (i.e., development and deployment)