Image understanding, OCR, and object detection powered by VisionAgent — analyze uploaded images and documents.
The media analysis feature uses the VisionAgent and OCRAgent from the PraisonAI SDK when available. Without the SDK, it returns simulated responses to allow frontend development without API keys.
| Capability | Description |
|------------|-------------|
| image_description | Natural language description of image contents |
image_description
| ocr | Extract text from images and documents |
ocr
| object_detection | Identify objects in images |
object_detection
| image_qa | Answer questions about image contents |
image_qa
| Endpoint | Method | Description |
|----------|--------|-------------|
| /api/media/analyze | POST | Analyze an image |
/api/media/analyze
| /api/media/ocr | POST | Extract text via OCR |
/api/media/ocr
| /api/media/capabilities | GET | List analysis capabilities |
/api/media/capabilities