Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

Description and use

Bird Buddy AI prototype lets users upload bird photos, receive AI‑generated identification suggestions and feature descriptions, and engage in daily nature challenges.

Problem

Users lack an easy way to identify birds from photographs and learn about them while exploring outdoors.

Outcome

Prototype demonstrates that open‑weight AI can provide bird identification suggestions and encourage outdoor activity.

Workflow

• Upload bird photo via Streamlit interface
• Model (SmolVLM‑500M‑Instruct) processes image
• Generates identification suggestion and feature description
• Displays result and daily challenge prompt

Evidence

Bird Buddy AI lets users upload a bird photograph and receive an AI-generated identification suggestion with a description of visible features.

Source

I built Bird Buddy AI with Python and Streamlit. For image analysis, I used SmolVLM-500M-Instruct, an open-weight vision-language model from Hugging Face, through PyTorch and Transformers.

Source

The model sometimes gave a confident-sounding answer that was actually incorrect. That showed me that generating a convincing explanation isn't the same as correctly identifying a species.

Source

The local version runs inference on my laptop after downloading the model. This lets me experiment without sending photographs to a separate inference API through the local application.

Source