new notebook: Information Extraction with Haystack and NuExtract #150
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
View / edit / reply to this conversation on ReviewNB merveenoyan commented on 2024-07-18T10:15:03Z maybe explain what it does with a very small sentence and give a link to that as people might not know about it anakin87 commented on 2024-07-18T11:36:14Z done! |
|
View / edit / reply to this conversation on ReviewNB merveenoyan commented on 2024-07-18T10:15:04Z renders nicely 😍 wonder if it will be the case for cookbook but I say we keep it |
There was a problem hiding this comment.
great PR tbh I couldn't find anything to comment on, would like to wait for @stevhliu to comment and we can merge
|
done! View entire conversation on ReviewNB |
|
@merveenoyan thx for the quick review! About visualization: while the cell outputs are displayed correctly in ReviewNB, I suspect that some of them won't be displayed in https://huggingface.co/learn/cookbook We have two options:
LMK... |
|
View / edit / reply to this conversation on ReviewNB stevhliu commented on 2024-07-22T15:22:40Z Can we try not including or changing the format of the output from |
|
View / edit / reply to this conversation on ReviewNB stevhliu commented on 2024-07-22T15:22:41Z "...you will probably see a warning saying:..." anakin87 commented on 2024-07-23T10:30:21Z fixed |
|
fixed View entire conversation on ReviewNB |
|
@stevhliu I made a change to not display |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
The doc preview is currently down but everything else looks good and ready to merge! If the visualization doesn't render, then let's go with option 2 and open a PR and add the images as outlined here |
What does this PR do?
Add a new notebook: "Information Extraction with Haystack and NuExtract".
In the notebook, we create an Information Extraction pipeline with the Haystack open-source framework and the NuExtract open model.
Then we extract structured data and derive insights from startups' funding announcements.
(@TuanaCelik)
Who can review?
@merveenoyan @stevhliu
Notes on visualization
I think some rendered outputs/visualizations are quite important to make this notebook clear and engaging (e.g., the pipeline diagram, the dataframe, and the graph visualization).
As far as I know, #48 is still valid.
If there is a way to preview what the notebook would look like in the HF site, we can check it out and then add the missing visualization using images in markdown cells.
If a preview is not possible, I would be more than happy to add those images in markdown cells to ensure that the notebook looks nice and understandable.