Vision Describe And Summarize
A 2-step recipe with NVIDIA NIM. We can help you get access.
Recipe · 2 steps
Vision Describe And Summarize
with NVIDIA NIM
Describe an image with a VLM, then summarize the description into a caption.
- Ask the vision-language model to produce a detailed description of the image supplied as an image_url content part.
- Condense the detailed image description into a single short caption using a text-only chat model.
What you'll need to have ready
- apiKey: NVIDIA developer API key (nvapi-...) sent as a Bearer token.
- imageUrl: HTTPS URL or data:image/...;base64,... payload for the image to analyze.
- visionModel: Vision-language model id.
- chatModel: Text model id used to summarize the description.
For your developer
Arazzo workflow nvidia-nim:vision-describe-and-summarize, 2 operations: createVisionChatCompletion → createChatCompletion. Specs on APIs.io.