Multimodal OCR
@aya-vision for image, @video-infer for video
Chatbot
Can you describe this image?
@aya-vision Summarize the letter
@aya-vision Extract JSON from the image
@video-infer Explain what is happening in this video ?
Extract as JSON table from the table
@aya-vision Describe the photo
@aya-vision Summarize the full image in detail
@aya-vision Describe this image.
@aya-vision What is this UI about?
Can you describe this image?
@aya-vision Where do the severe droughts happen according to this diagram?
Query Input
Fake API
Response
Examples
Pages:
1
2