🦙📚 Demonstration chatbot with Streamlit, LlamaIndex and Google Gemini

Build a chatbot hosted on Streamlit Community Cloud and powered by LlamaIndex that augments Google Gemini with local documents. This repository is used in the Build Your Own AI Chatbot offered by King Library's Digital Humanities Center. The original code for this chatbot is based on the chabtot described in this blog post.

The demo chatbot is an expert on the works of author Rabindranath Tagore. Fork the repository and add your own documents to create a chatbot that focuses on a different topic.

Overview of the App

• Takes user queries via Streamlit's st.chat_input and displays both user queries and model responses with st.chat_message
• Uses LlamaIndex to load and index data and create a chat engine that will retrieve context from that data to respond to each user query

Demo App

https://sjsu-chatbot-workshop.streamlit.app/

Build your own copy

Follow the steps in the workshop slides at https://tiny.sjsu.edu/chatbot-workshop-2025

Caution

Don't commit your secrets file to your GitHub repository. The .gitignore file in this repo includes .streamlit/secrets.toml and secrets.toml.

Try out the app

Once the app is loaded, enter your question about Rabindranath Tagore and wait for a response.

Source texts

The demo version of the chatbot uses texts from the writer Rabindranath Tagore. These texts are available from Project Gutenberg.