metadata

title: AI Class Tutor
description: An LLM based AI class tutor with RAG on DL4DS course
emoji: 🐶
colorFrom: red
colorTo: green
sdk: docker
app_port: 7860

DL4DS Tutor 🏃

Check out the configuration reference at Hugging Face Spaces Config Reference.

You can find a "production" implementation of the Tutor running live at DL4DS Tutor from the Hugging Face Space. It is pushed automatically from the main branch of this repo by this Actions Workflow upon a push to main.

A "development" version of the Tutor is running live at DL4DS Tutor -- Dev from this Hugging Face Space. It is pushed automatically from the dev_branch branch of this repo by this Actions Workflow upon a push to dev_branch.

Setup

Please visit setup for more information on setting up the project.

Running Locally

Clone the Repository

git clone https://github.com/DL4DS/dl4ds_tutor

Put your data under the storage/data directory
- Add URLs in the urls.txt file.
- Add other PDF files in the storage/data directory.

To test Data Loading (Optional)

cd code
python -m modules.dataloader.data_loader --links "your_pdf_link"

Create the Vector Database
```
cd code
python -m modules.vectorstore.store_manager
```
- Note: You need to run the above command when you add new data to the storage/data directory, or if the storage/data/urls.txt file is updated.
Run the FastAPI App
```
cd code
uvicorn app:app --port 7860 
```

Documentation

Please visit the docs for more information.

Docker

The HuggingFace Space is built using the Dockerfile in the repository. To run it locally, use the Dockerfile.dev file.

docker build --tag dev  -f Dockerfile.dev .
docker run -it --rm -p 8000:8000 dev

Contributing

Please create an issue if you have any suggestions or improvements, and start working on it by creating a branch and by making a pull request to the dev_branch.

Please visit contribute for more information on contributing.

Future Work

For more information on future work, please visit roadmap.