mozilla-ai/structured-qa

Blueprint by Mozilla.ai for answering questions about structured documents

40

stars

53

commits

Python

primary language

Mar 14, 2025

updated

mozilla-ai.github.io/structured-qa/
ai
llm
question-answering

README

Project logo

Structured-QA: a Blueprint by Mozilla.ai for answering questions about structured documents.

This Blueprint demonstrates how to use open-source models and a simple LLM workflow to answer questions based on structured documents.

It is designed to showcase a simpler alternative to more complex and/or resource-demanding alternatives, such as RAG systems that rely on vector databases and/or long-context models with large token windows.

Structured QA Diagram

Quick-start

Get started with structured-qa using one of the options below:

Google ColabHuggingFace SpacesGitHub Codespaces
Try on ColabTry on SpacesTry on Codespaces

You can also install and use the blueprint locally:

Command Line Interface

pip install structured-qa
structured-qa \
--question "What optimizer was used to train the model?" \
--input_file "example_data/1706.03762v7.pdf" \
--output_dir "example_outputs/1706.03762v7.pdf"

Graphical Interface App

git clone https://github.com/mozilla-ai/structured-qa.git
cd structured-qa
pip install -e .
python -m streamlit run demo/app.py

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Contributing

Contributions are welcome! To get started, you can check out the CONTRIBUTING.md file.

Contributors

daavoo

49 commits

stefanfrench

3 commits

alexmeckes

1 commits

mozilla-ai/structured-qa

Blueprint by Mozilla.ai for answering questions about structured documents

40

stars

53

commits

Python

primary language

Mar 14, 2025

updated

mozilla-ai.github.io/structured-qa/
ai
llm
question-answering

README

Project logo

Structured-QA: a Blueprint by Mozilla.ai for answering questions about structured documents.

This Blueprint demonstrates how to use open-source models and a simple LLM workflow to answer questions based on structured documents.

It is designed to showcase a simpler alternative to more complex and/or resource-demanding alternatives, such as RAG systems that rely on vector databases and/or long-context models with large token windows.

Structured QA Diagram

Quick-start

Get started with structured-qa using one of the options below:

Google ColabHuggingFace SpacesGitHub Codespaces
Try on ColabTry on SpacesTry on Codespaces

You can also install and use the blueprint locally:

Command Line Interface

pip install structured-qa
structured-qa \
--question "What optimizer was used to train the model?" \
--input_file "example_data/1706.03762v7.pdf" \
--output_dir "example_outputs/1706.03762v7.pdf"

Graphical Interface App

git clone https://github.com/mozilla-ai/structured-qa.git
cd structured-qa
pip install -e .
python -m streamlit run demo/app.py

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Contributing

Contributions are welcome! To get started, you can check out the CONTRIBUTING.md file.

Contributors

daavoo

49 commits

stefanfrench

3 commits

alexmeckes

1 commits

Languages

Python

97.7%

Dockerfile

2.3%