Munshi is an AI-powered conversational assistant for Munshig, a digital platform that offers invoicing, payment reminders, and financial reporting services for small businesses. This project uses GPT-3 and Streamlit to build a natural language processing (NLP) chatbot that can seamlessly log transactions at point-of-sale using speech recognition and image recognition.
- Generate invoices and payment reminders for customers
- Log transactions at point-of-sale using speech recognition and image recognition
- Customize invoice templates with logos and color schemes
- Analyze financial data and generate reports
To run Munshi on your local machine, you need to have Python 3.x and the following dependencies installed:
- OpenAI API
- Streamlit
- Pillow (To be updated)
- SpeechRecognition
- PyAudio
You can install these dependencies by running the following command: pip install -r requirements.txt
To run Munshi, run the following command: streamlit run app.py
This will start the Streamlit server and open the Munshi interface in your default web browser. You can then interact with the chatbot by typing in your queries and receiving responses in natural language.
- Munshi was developed by Shreya Mishra.
- This project uses the OpenAI API for natural language processing and response generation.
- The user interface is built using Streamlit.
- Speech recognition is powered by SpeechRecognition.
- Image recognition is powered by Pillow.(to be updated)
Munshi is licensed under the MIT License. Feel free to use and modify this code as per your requirements.