This is a Streamlit app that allows you to upload an document or audio file and ask questions about its content. It uses the Llama Index framework, powered by OpenAI's ChatGPT and Hugging Face's Sentence Transformers model, to perform semantic search and provide answers based on your queries.
- All types of raw text documents
- PDF documents
- Audio files (mp3, wav, ogg)
- Video file (mp4)
For audio transcription, you need to have ffmpeg installed on your system.
-
Clone the repository:
git clone https://github.com/navopw/streamlit-llm.git
-
Install the required dependencies:
pip install -r requirements.txt
-
Set up environment variables:
-
Create a file named
.env
in the root directory of the project. -
Add your OpenAI API key to the
.env
file:OPENAI_API_KEY=your_api_key
-
-
Run the Streamlit app:
./start.sh <host> <port>
This project is licensed under the MIT License.