qianwen-vision

Understand images, videos, documents, and charts with Qwen.

visual analysis

What it does

Analyzes images and videos for understanding, reasoning, comparison, and text extraction.

When to use it

Use for image or video analysis, OCR, chart and table reading, visual reasoning, comparisons, and screenshot understanding.

Give it visual input and the desired analysis; it saves a response containing the resulting understanding, reasoning, or extracted text.

What you provide

This skill

DashScope API

Write

Sends visual input to DashScope

DashScope temp storage

Write

Uploads large files temporarily

OSS bucket

Write

Uploads files to your OSS

Qwen vision model catalog

Read

Reads the current model catalog

The default script path requires Python 3.9 or newer and uses only the standard library.

Reads the required API key from the environment and can also load it from .env.

Reads QIANWEN_API_KEY as an alternative environment-variable alias for DASHSCOPE_API_KEY.

This package enables the documented production path that uploads files to the user's own OSS bucket.