Streamlit app to chat with data (RAG implementation using Orca-Mini3b, FAISS, Streamlit). Currently only *.csv type of data. You can upload any csv file and get insights out of it.
-
You need Python installed. If you don't have Python installed, install if from this link
-
Clone the repository.
git clone https://github.com/LexiestLeszek/chatwithdata.git
- Once cloned, go inside the repository or folder.
cd chatwithdata
- Thanks to the GPT4ALL guys, download the model file, create "model" folder in the main directory and put the model there
https://gpt4all.io/models/gguf/orca-mini-3b-gguf2-q4_0.gguf
- Create a virtual environment and activate it.
python3 -m venv .venv && source .venv/bin/activate
- Install the packages from the requirements.txt file.
pip install -r requirements.txt
- Run the streamlit app.
streamlit run ch.py
After running the streamlit command, you should now be able to access the app at http://localhost:XXXX/. Upload the csv file and happy chatting.