Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Very bad reasoning accuracy #849

Open
hmirheydari opened this issue Nov 7, 2024 · 4 comments
Open

Very bad reasoning accuracy #849

hmirheydari opened this issue Nov 7, 2024 · 4 comments
Assignees
Labels
bug Something isn't working question Further information is requested

Comments

@hmirheydari
Copy link

hmirheydari commented Nov 7, 2024

I've fed some Persian MS Word files into llm-graph-builder.neo4jlabs.com and asked some question, it answered 1 out of 5 questions while simple RAG solutions like chatize.com answered all 5 questions correctly, I doubt is its performance less than legacy RAGs or I made a mistake

@kartikpersistent
Copy link
Collaborator

Hi @hmirheydari Can you share the Persian MS Word files we will try at our end and let you know what happening behind the scenes that is impacting the accuracy.

@kartikpersistent kartikpersistent added bug Something isn't working question Further information is requested labels Nov 7, 2024
@hmirheydari
Copy link
Author

@kaustubh-darekar
Copy link
Collaborator

@hmirheydari thank you for sharing the file. Can you also share sample questions you tried, we will test same at our end.

@jexp
Copy link
Contributor

jexp commented Dec 11, 2024

PIng @hmirheydari

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working question Further information is requested
Projects
None yet
Development

No branches or pull requests

5 participants