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

Add notebook #67

Merged
merged 2 commits into from
Mar 19, 2024
Merged

Add notebook #67

merged 2 commits into from
Mar 19, 2024

Conversation

anakin87
Copy link
Member

No description provided.

Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

notebooks/information_extraction_raven.ipynb Show resolved Hide resolved
@@ -0,0 +1,2726 @@
{
Copy link
Contributor

@bilgeyucel bilgeyucel Mar 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You used the "paid endpoint" so users cannot run this notebook if they don't have a paid HF account? I don't see you setting the "HF_TOKEN" so I'm confused

Also, thanks for giving alternative options here. Tehy are quite helpful


Reply via ReviewNB

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The paid endpoint is provided by Nexusflow to test the LLM and is free for everyone. It does not require the HF_TOKEN.

@@ -0,0 +1,2726 @@
{
Copy link
Contributor

@bilgeyucel bilgeyucel Mar 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you briefly explain here what you're trying to achieve with this prompt? Where to place "START", "TEXT" tags and why we need them etc?


Reply via ReviewNB

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This was an empirical effort to improve the prompt for my application.

@@ -0,0 +1,2726 @@
{
Copy link
Contributor

@bilgeyucel bilgeyucel Mar 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #6.    User Query: Save data from the provided text. START TEXT:{{docs[0].content|replace("\n"," ")|truncate(10000)}} END TEXT

Do you mean "extracting data" or "saving data"?


Reply via ReviewNB

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Empirical.

I think it makes more sense for the LLM to create a function call with the extracted data and pass it for saving.

notebooks/information_extraction_raven.ipynb Show resolved Hide resolved
notebooks/information_extraction_raven.ipynb Show resolved Hide resolved
notebooks/information_extraction_raven.ipynb Show resolved Hide resolved
@anakin87 anakin87 merged commit ea0f2ee into main Mar 19, 2024
@anakin87 anakin87 deleted the add-raven branch March 19, 2024 10:37
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

Successfully merging this pull request may close these issues.

None yet

2 participants