gkorland's comments

On: Ask HN: What is the best software to visualize a g...

[gkorland]

Do you just hold this number of node in the database or also need to visualize them all in one view?

[throwaway425933 → gkorland]

visualize them in one view so I can understand how data is flowing from input to output

On: Ask HN: LLM agents for structured data from databa...

[gkorland]

We've done a very similar procedure just with FalkorDB as a Graph Database. Notice if you already have a schema/ontology it might be easier might you might miss some entities in the text you did realize exist.

So in our in GraphRAG-SDK we are running two phases, the first is sampling the data to suggest a schema and the second is using this schema to ground the LLM to this schema (as you suggested)

Check https://github.com/FalkorDB/GraphRAG-SDK

On: Ask HN: How is your organization using LLMs?

[gkorland]

Would love to hear your feedback once you do try GraphRAG.

On: Show HN: Compare GraphRAG and RAG on earning call ...

[gkorland]

Nice demo! It so easy to see that Vector RAG just can't answer complex queries that are more that Sematic Search results.

We also build a similar demo based on the UFC dataset - https://github.com/FalkorDB/ufc

On: Ask HN: Is there any software you only made for yo...

[gkorland]

Nice!

On: Ask HN: Is there any software you only made for yo...

[gkorland]

That is cool! Would love to see how it works with FalkorDB as the Graph Database for the knowledge Graph https://github.com/FalkorDB/FalkorDB

On: GraphRAG is now on GitHub

[gkorland]

This is exactly why we're working on the GraphRAG-SDK to ease the process. You might want to check out https://github.com/FalkorDB/GraphRAG-SDK/ and we would love to hear your feedback

On: GraphRAG is now on GitHub

[gkorland]

Indeed, if you build the Knowledge Graph in a "naive" way but just asking the LLM to generate a Knowledge Graph you'll probably end up with a very "dirty" Knowledge Graph full with duplications.

[falcor84 → gkorland]

Can this be handled by a second (adversarial?) LLM that searches for bad entries?

On: GraphRAG is now on GitHub

[gkorland]

The GraphRAG project is great and really shows the why Vector Databases can provide a full RAG solution when it comes to none trivial search queries. But in order to build a full an accurate Knowledge Graph we found out you need more than just loading the text to LLM.

For that we wrote the GraphRAG-SDK that is also generating a stable Ontology. https://github.com/FalkorDB/GraphRAG-SDK

On: GraphRAG is now on GitHub

[gkorland]

These are Knowledge Graphs, perhaps not RDF but Knowledge Graph can also be based on properties Graphs