A
alicloud-ai-multimodal-qwen-ocr-test
About alicloud-ai-multimodal-qwen-ocr-test
A minimal executable test skill for the Alibaba Cloud multimodal Qwen OCR skill. It provides a sample command to prepare an OCR request and a criterion for checking the generated result.
Key features
- 01Runs an OCR request-preparation example
- 02Configures key information extraction
- 03Checks success response and output file
Use cases
- 01Verifying the target OCR skill's request preparation
- 02Checking generation of request.json
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ cinience/ alicloud-skills --skill alicloud-ai-multimodal-qwen-ocr-testAfter installing, type/alicloud-ai-multimodal-qwen-ocr-testin Claude Code to confirm it loaded.
Details
From the project READMECategory: test
Minimal Viable Test
Prerequisites
- Target skill:
skills/ai/multimodal/alicloud-ai-multimodal-qwen-ocr
Executable Example
.venv/bin/python skills/ai/multimodal/alicloud-ai-multimodal-qwen-ocr/scripts/prepare_ocr_request.py \
--image "https://example.com/invoice.png" \
--task key_information_extraction \
--task-config '{"keys":["seller_name","invoice_date","amount"]}'
Pass criteria: script returns {"ok": true, ...} and writes output/alicloud-ai-multimodal-qwen-ocr/request.json.
Comments
Markdown supported