Red Panda
The mysterious Red Panda text-to-image model has finally been revealed by its creators. The company behind this innovative technology is Recraft AI, which has also given the model the name “Recraft V3”.
You can currently access Recraft V3 in two different platforms: directly on the Recraft AI website and within Replicate. This allows users to experience firsthand what makes Red_Panda so special, including its ability to generate SVG images. The model’s capacity for producing intricate and detailed visualizations has been subject of much curiosity.
Read more: https://x.com/dr_cintas/status/1852061917361156208 https://x.com/zeke/status/1852104708657418505
ChatGPT Search
In a recent development, OpenAI has rolled out an exciting feature called ChatGPT Search. This innovative tool allows you to effortlessly make ChatGPT search the web for your queries, saving you time and effort. With just one click on the 🌐 icon, you can access the vast wealth of online information.
The rollout is currently limited to Paid users, but we’re thrilled to know that this feature will soon be available to Free Users as well, scheduled for the coming months.
Ollama
Ollama 0.4.0 released candidate 6. This adds experimental support for Llama 3.2 vision model.
kotaemon
kotaemon tool is an open-sourced, fantastic tool for chatting with documents using open-source Large Language Models (LLMs). It gained popularity on GitHub and offers several features:
* Clean and customizable UI for document QA
* Supports local LLMs and API providers
* Hybrid pipeline with full-text & vector retrieval
* Multi-modal QA with figures & tables support
Key Features:
• Host your own RAG web UI with multi-user login
• Organize LLM & embedding models (local & API)
• Hybrid retrieval + re-ranking for quality
• Multi-modal parsing and QA across documents
• Adjustable retrieval & generation settings
• Customizable UI and indexing strategies
You can find it on: https://github.com/Cinnamon/kotaemon