![Python](https://img.shields.io/badge/Python-3.10%2B-blue) [![llama.cpp](https://img.shields.io/badge/llama.cpp-E76F00?logo=cplusplus&logoColor=white&labelColor=1E1E1E)](https://github.com/ggml-org/llama.cpp) [![pymupdf4llm](https://img.shields.io/badge/pymupdf4llm-blue)](https://pymupdf.readthedocs.io/en/latest/pymupdf4llm/index.html) [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE) [![](https://dcbadge.limes.pink/api/server/YuMNeuKStr?style=flat)](https://discord.gg/YuMNeuKStr) [![Docs](https://github.com/mozilla-ai/structured-qa/actions/workflows/docs.yaml/badge.svg)](https://github.com/mozilla-ai/structured-qa/actions/workflows/docs.yaml/) [![Tests](https://github.com/mozilla-ai/structured-qa/actions/workflows/tests.yaml/badge.svg)](https://github.com/mozilla-ai/structured-qa/actions/workflows/tests.yaml/) [![Ruff](https://github.com/mozilla-ai/structured-qa/actions/workflows/lint.yaml/badge.svg?label=Ruff)](https://github.com/mozilla-ai/structured-qa/actions/workflows/lint.yaml/) [Blueprints Hub](https://developer-hub.mozilla.ai/) | [Documentation](https://mozilla-ai.github.io/structured-qa/) | [Getting Started](https://mozilla-ai.github.io/structured-qa/getting-started/) | [Contributing](CONTRIBUTING.md)

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.

Quick-start

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

Google Colab	HuggingFace Spaces	GitHub 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.

structured-qa

Specs

README