Image Recognition FAQs

Question 1

What image formats are supported?

Accepted Answer

The tool supports a variety of common image formats, including JPEG, PNG, GIF, and WebP.

Question 2

How do I configure which vision API to use?

Accepted Answer

You can configure the primary and fallback vision providers using the `VISION_PROVIDER` and `FALLBACK_PROVIDER` environment variables, allowing you to prioritize Anthropic or OpenAI.

Question 3

What is Image Recognition and what does it do?

Accepted Answer

Image Recognition is a server that uses Anthropic and OpenAI vision APIs to provide descriptions of images. It also supports text extraction using Tesseract OCR.

Question 4

Is Tesseract OCR required?

Accepted Answer

No, Tesseract OCR is optional. It's only required if you want to use the text extraction feature.

Question 5

Can I use this tool with OpenRouter?

Accepted Answer

Yes! You can easily configure the Image Recognition server to use OpenRouter by setting the `OPENAI_BASE_URL` and `OPENAI_MODEL` environment variables.

Image Recognition

Key Features

Use Cases

Image Recognition

Key Features

Use Cases