v2.0.0

[anirudTT]

What's Changed

• rc-v2.0.0 by @anirudTT in rc-v2.0.0 #389

Full Changelog: v1.5.0...v2.0.0

v2.0.0 Release Notes

This release represents a significant step forward for the platform, introducing new AI models, a redesigned user interface, and an updated backend infrastructure. Our focus with version 2.0.0 has been on expanding capabilities, improving the user experience, and streamlining development.

Key Features & Improvements
🚀 AI Playground Launch: Introduced the AI Playground, a cloud-hosted environment bringing all new models and features to a wider audience.

🎙️ New AI Models: Integrated Whisper for real-time speech-to-text and enhanced Stable Diffusion for high-quality image generation.

✨ UI/UX Overhaul: Implemented a comprehensive redesign for mobile and desktop, featuring new interactive components, dynamic themes, improved layouts, and a modern aesthetic.

⚙️ New Infrastructure & Dev Experience: Rolled out a new run.py startup script and integrated the tt-inference-server to automate running vLLM and TT-Metal based models, and added live hardware monitoring and container log streaming.

🧠 Enhanced RAG and Chat: Upgraded the RAG system to support multi-modal file uploads (including PDFs) and added granular model parameter controls to the chat interface.

👁️ Object Detection Fixes: Improved the YOLOv4 interface with more accurate bounding box detection and refined webcam controls.

Contributors:

@anirudTT
@atupe-tt
@sbennettTT
@tstescoTT
@mvanniasingheTT
@bgoelTT

---

This discussion was created from the release v2.0.0.