Iris is a personalized health companion bot that provides accurate medical information and advice using advanced language models, featuring conversation logging and easy-to-use default prompts for quick inquiries.
Before you can start using the IRIS Bot, make sure you have the following prerequisites installed on your system:
- Python 3.6 or higher
- Required Python packages (you can install them using pip):
- langchain
- chainlit
- sentence-transformers
- faiss
- PyPDF2 (for PDF document loading)
-
Clone this repository to your local machine.
git clone https://github.com/NRanjan-17/IRIS.git cd IRIS -
Create a Python virtual environment (optional but recommended):
python -m venv venv source venv/bin/activate # On Windows, use: venv\Scripts\activate
-
Install the required Python packages:
pip install -r requirements.txt
-
Download the required language models and data. Please refer to the Langchain documentation for specific instructions on how to download and set up the language model and vector store.
-
Set up the necessary paths and configurations in your project, including the
DB_FAISS_PATHvariable and other configurations as per your needs.
Use the following commang to start the bot
-
Provide the dat in the pdf file is data dir and run the
ingest.pyscript to create the vector store. -
After the vector store is created start the bot.
python -m chainlit run model.py
```