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

Can't run example 55_Generate_knowledge_with_Semantic_Graphs_and_RAG.ipynb #721

Closed
kellytsorb opened this issue May 23, 2024 · 3 comments
Closed

Comments

@kellytsorb
Copy link

kellytsorb commented May 23, 2024

Hello,
I want to run the example with the Wikipedia dataset to understand the query = """
SELECT id, text FROM txtai
order by percentile desc
LIMIT 100000
"""
because when I run the code with my embeddings the query works as string and takes it as a sentence and searches through my financial texts. As a result the answers are wrong because it shows results relayted to id, text, txtai and not for example earning management, or financial risk. Also, the other issue is that the dataset of wikipedia isn't loading as shown in the screenshot below everything with the code it seems fine but it doesn't load. Is there any ideas of what it's happening?
Thank you in advance!
Screenshot 2024-05-23 at 12 56 38 PM

@davidmezzetti
Copy link
Member

Hello and thank you for writing this up.

From the sound of it, I'd guess that the new Embeddings being created doesn't have content=True. Without setting content to True, all queries are considered text queries.

I'd retry downloading the wikipedia index. It seems like you were running into a Hugging Face Hub issue.

@kellytsorb
Copy link
Author

Hello thank you for your response.
I changed the content=True and it works with my embeddings.
@davidmezzetti

@davidmezzetti
Copy link
Member

Excellent, glad it worked.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants