Hi DEV! I’m Mughees, an AI/software engineer, and I’m new here. 👋
I’m working on LangVio, an open-source Python project for querying images and videos in natural language. The idea is simple: describe what you want to find, and get an annotated result with an explanation.
For example: “Find the person wearing glasses.”
The current default pipeline uses Qwen-VL through OpenRouter for query parsing, object grounding, and explanations. There’s a web interface for trying things out, alongside the Python API and CLI.
Give it a try
pip install langvio
Set your OPENROUTER_API_KEY and follow the setup instructions in the repository:
GitHub: https://github.com/MugheesMehdi07/langvio
I’d love feedback from people working with computer vision, VLMs, or video applications:
- Which queries would you try first?
- Where do the results fall short?
- What would make the API or setup easier to use?
Bug reports, ideas, and contributions are all welcome. If you find the project useful, a ⭐ on GitHub would mean a lot and help others discover it.
Looking forward to learning from this community and sharing more of what I’m building!
Top comments (0)