Multi-Model Support¶
Currently, the platform supports LLM (Large Language Models) for text generation and conversation.
Coming Soon: Vision Models¶
VLM (Vision-Language Models) support is planned for a future release.
Vision models will enable:
| Capability | Description |
|---|---|
| Image Understanding | Analyze and describe images |
| Visual Question Answering | Answer questions about uploaded images |
| Document OCR | Extract text from images and PDFs |
| Multimodal Workflows | Combine text and vision in agent workflows |
Model Types¶
| Type | Status | Description |
|---|---|---|
| LLM | β Available | Text generation and conversation |
| VLM | π Coming Soon | Image understanding and analysis |
Stay tuned for updates on vision model support.