# Project export: Tesla VLM Track

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: TreeHacks 2025
- Tagline: Using a VLM, we were able to analyze a series of traffic videos and answer a series of questions regarding the proper procedure for a possible autonomous vehicle.
- Devpost: https://devpost.com/software/tesla-vlm-track
- GitHub: not linked
- Video: https://www.youtube.com/embed/8-XA7BPi3bg?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

We wanted to build an AI-driven system that leverages vision-language models (VLMs) to enhance Tesla’s capabilities, possibly in autonomous systems, customer support, or AI-powered insights.

### What it does

The project integrates LangChain with OpenAI’s GPT models (and potentially Groq’s models) to handle conversational AI, maintain session memory, and process vision-related inputs.

### How we built it

We used LangChain to manage LLM interactions, session-based history storage, and potential multimodal processing through Groq’s vision-language models.

### Challenges we ran into

Optimizing memory storage for multi-session interactions API constraints like token limits and response handling Tuning the model for accuracy in vision-language tasks

### Accomplishments we're proud of

Successfully implemented session-based chat memory Integrated OpenAI’s GPT-4o-mini for fast, efficient responses Explored Groq’s vision-language models for potential enhancements

### What we learned

How to efficiently manage session-based memory in LangChain The strengths and limitations of different LLM providers Strategies for optimizing AI models in constrained environments

### What's next

Fine-tuning the model for specific Tesla-related applications Expanding the use of vision-language models for real-time insights Exploring hardware acceleration for on-device AI processing

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- Ollama (technology) — claimed on Devpost, not found in the code
- OpenAI (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- PyTorch (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.