Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
sergiopaniego 
posted an update 5 days ago
Post
960
📣 CALL FOR CONTRIBUTORS! 📣

Following last week’s full release of Gemma 3n, we launched a dedicated recipes repo to explore and share use cases. We already added some! 🧑‍🍳

Now we’re inviting the community to contribute and showcase how these models shine! ✨

Let them cook.

Check it out: https://github.com/huggingface/huggingface-gemma-recipes/issues/4
yasir-13001

Hi  @sergiopaniego  👋

Just opened Issue #7 – “ShopAI: Multimodal Order Extraction with Gemma 3n”
👉 https://github.com/huggingface/huggingface-gemma-recipes/issues/7#issue-3195036130

Why it’s exciting

  • True multimodal demo: text 📝 + speech 🎙️ + vision 📷, all in one recipe powered by Gemma 3n.
  • Retail‑ready workflow: turns a casual request—“Add 2 kg sugar and 1 litre milk” or a photo of the item—into structured order lines.
  • Semantic matching: ChromaDB embeddings link parsed items to real inventory, complete with stock levels.
  • Drop‑in backend: FastAPI endpoints so any voice assistant, chatbot, or web store can plug‑and‑play.

I’d love your thoughts on how to push the vision/audio pipelines even further—or any other ways to make this a flagship recipe for on‑device retail AI.

Thanks for the inspiration and looking forward to collaborating! 🚀

In this post