We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Relates to #7
If you click Embed and Upsert on the India topic and then ask a simple question like what is going on with Solar Power in India?
Both the RAG and Non-RAG pipeline to illustrate the original point we're trying to.
The Non-RAG pipeline should underperform relative to the RAG pipeline.
Ask simple questions on the app after embedding the Solar in India topic
No response
- **OS**: - **Language version**: - **Pinecone client version**:
The text was updated successfully, but these errors were encountered:
Why doesn't the non-rag underperform?
Sorry, something went wrong.
It's likely due to the gpt model already having been trained in that data and can retrieve the answer without needing RAG based context.
No branches or pull requests
Is this a new bug?
Current Behavior
Relates to #7
If you click Embed and Upsert on the India topic and then ask a simple question like what is going on with Solar Power in India?
Both the RAG and Non-RAG pipeline to illustrate the original point we're trying to.
Expected Behavior
The Non-RAG pipeline should underperform relative to the RAG pipeline.
Steps To Reproduce
Ask simple questions on the app after embedding the Solar in India topic
Relevant log output
No response
Environment
Additional Context
No response
The text was updated successfully, but these errors were encountered: