-
Notifications
You must be signed in to change notification settings - Fork 163
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
Code for evaluating open source embedding models #305
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I got stuck sadly :( But it does look promising overall.
examples/finding_best_open_source_embedding_model/best_embedding_model_rag_app.ipynb
Outdated
Show resolved
Hide resolved
examples/finding_best_open_source_embedding_model/best_embedding_model_rag_app.ipynb
Outdated
Show resolved
Hide resolved
examples/finding_best_open_source_embedding_model/best_embedding_model_rag_app.ipynb
Outdated
Show resolved
Hide resolved
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"with connect_db() as conn:\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Instead of loading the data from a csv file (and leaving the user to figure that out), try this:
SELECT ai.load_dataset('sgoel9/paul_graham_essays', table_name => 'essays');
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Addendum:
SELECT ai.load_dataset('sgoel9/paul_graham_essays', table_name => 'essays', if_table_exists => 'append');
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 for using this but this then also needs pgai 0.6.0 not 0.5.0
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I actually couldn't find the function when using pgai 0.6.0 yesterday. @JamesGuthrie
examples/finding_best_open_source_embedding_model/best_embedding_model_rag_app.ipynb
Outdated
Show resolved
Hide resolved
…ng_model_rag_app.ipynb Co-authored-by: James Guthrie <[email protected]> Signed-off-by: Hervé Ishimwe <[email protected]>
examples/finding_best_open_source_embedding_model/best_embedding_model_rag_app.ipynb
Show resolved
Hide resolved
examples/finding_best_open_source_embedding_model/best_embedding_model_rag_app.ipynb
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sweet, thanks for incorporating all the feedback
The ci pipeline complains because we use conventional commits btw: https://www.conventionalcommits.org/en/v1.0.0/
You might wanna change your commit message to be in line as well as the PR title
This is the code for the blog post about finding the best open-source embedding model. Please start with the Jupyter notebook for explanations on how to run the code.
Thank you for the review!