-
-
Chat Function That Allows User To Prompt Naturally
-
Interactive Area Chart With Filters
-
Interactive Scatter Plot With Filters
Inspiration
Analyzing racing telemetry data can be tedious when using large CSV files or spreadsheets. We wanted to make exploring this data intuitive and interactive, allowing users to ask natural language questions and instantly get meaningful insights.
What it does
Racing Data Chat Explorer is a Streamlit app that lets users interactively query racing telemetry data. You can filter by vehicle ID, lap number, or retrieve key stats like the highest value or vehicle count. It provides a chat-based interface, making data exploration as simple as asking questions.
How we built it
Python for data processing and logic.
Pandas & NumPy to manipulate the telemetry dataset efficiently.
Streamlit to create the interactive web interface, including a chat widget for querying data.
Simple regex-based natural language parsing to understand user queries like “Show me vehicle 32768” or “Lap 5 data”.
Challenges we ran into
Designing a flexible query system that could interpret natural language without building a full NLP model.
Ensuring that the chat interface updates correctly and preserves conversation history.
Styling the app to make suggested questions and data previews clear and visually appealing.
Accomplishments that we're proud of
Successfully created a chat-driven data explorer that works on any telemetry dataset with minimal setup.
Implemented dynamic filtering and statistics extraction with simple user queries.
Made the interface user-friendly and visually clear, with expandable data previews and suggested questions.
What we learned
How to integrate Python data processing with a Streamlit front-end effectively.
Techniques for maintaining session state in Streamlit to preserve chat history.
How to guide users with example queries to improve UX.
What's next for Racing Data Explorer
Implement more advanced query understanding with NLP for fully free-form questions.
Add visualizations like lap time graphs and vehicle comparisons.
Allow users to upload their own datasets for instant exploration.
Integrate Streamlit deployment workflow with automatic GitHub updates for easier sharing.
Log in or sign up for Devpost to join the conversation.