Invoice Extraction

[SinghSuryaDeep]

PR Checklist

Model Interaction

• Flexible LLM platform support The platform should be easily switchable. Use LangChain or LlamaIndex.
• Use prompt guide corresponding to the model For example for Granite 3.x Language Models

Data

• Example data: Follow the example data guidance.

Notebook requirements

• Notebook outputs cleared: Ensure all notebook outputs are cleared.
• Automated testing: Add the recipe to the automated tests as described here
• Test in Google Colab:
  • Test that it works in Google Colab (Python 3.10.12).
  • Colab has its own package set and Python version, so ensure compatibility.
• Test locally:
  • Ensure the code works in a fresh Python virtual environment (venv).
• Standard access to secrets and variables Include !pip install git+https://github.com/ibm-granite-community/utils in the first code cell in order to make get_env_var available to accessing secrets and variables in the recipe.

Incoming References

• README.md updates:
  • Add a link to the recipe in the Table of Contents (ToC).
  • Include a Colab button after that link.

GitHub

• Commits signed: All commits must be GPG or SSH signed.
• DCO Compliance: Developer Certificate of Origin (DCO) applies to the code, documentation, and any example data provided. Ensure commits are signed off.

[bjhargrave]

Thanks for the update. I have some comments here. Also, please add this notebook's path to .github/notebook_lists/vanilla_notebooks.txt so the notebooks will be tested in the build.

Also, please rebase upon the tip of the main branch.

[bjhargrave]

Also, please add this notebook's path to .github/notebook_lists/vanilla_notebooks.txt so the notebook will be tested in the build.

[SinghSuryaDeep]

I have changed the invoice path as mentioned above and added the notebook path to the vanilla_notebooks.txt file.

[github-actions]

Testing Notebooks workflow launched on this PR: View run

[bjhargrave]

@adampingel I think this is ready to merge.

[adampingel]

@SinghSuryaDeep

1. Where are the invoice pdfs from? We need to be able to distribute all data under CDLA Permissive 2.0
2. Please create an entry in the top-level README.md for these -- I think under the first section of recipes

[SinghSuryaDeep]

@adampingel

1. The invoice PDF contains mocked-up data. The numbers and names are not real.
2. I have added an entry in the README.md file for invoice extraction.

[github-actions]

Testing Notebooks workflow launched on this PR: View run

[github-actions]

Testing Notebooks workflow launched on this PR: View run

[bjhargrave]

@SinghSuryaDeep The latest ci test fails with

FileNotFoundError: Missing ONNX file: /home/runner/.cache/huggingface/hub/models--ds4sd--docling-models/snapshots/a8a57426c20d9f7bc0343cfd84e8b439425e5561/model_artifacts/layout/beehive_v0.0.5/model.pt

I am not sure exactly what is going on, but it seems to be a problem with docling.

[SinghSuryaDeep]

Hi @bjhargrave and @adampingel
I tested the invoice extraction notebook and updated the GitHub repository as well. Could you please try rerunning the pipeline again. Thanks

[github-actions]

Testing Notebooks workflow launched on this PR: View run

[SinghSuryaDeep]

@adampingel and @bjhargrave

Just a gentle reminder regarding the PR. Please let me know if any action or additional information is required from my side. If not, may we proceed with merging?

Thanks in advance!

[bjhargrave]

Thanks @SinghSuryaDeep!