Instructions to use PaddlePaddle/PaddleOCR-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PaddleOCR-VL with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation from paddleocr import PaddleOCRVL pipeline = PaddleOCRVL(pipeline_version="v1") output = pipeline.predict("path/to/document_image.png") for res in output: res.print() res.save_to_json(save_path="output") res.save_to_markdown(save_path="output") - Notebooks
- Google Colab
- Kaggle
How to convert charts to table?
The technical paper showed examples for charts to markdown table but I am unable to find any parameter which can help me convert that. Right now it is classic ocr where chart just treated as image and not shown in markdown
Hello, this is supported. If you are using our online demo, there is an optional "enable chart parsing" next to the "Parse document" button, which is turned off by default and needs to be manually checked. In addition, in "Element-level Recognition", you can upload a chart image and click "chart recognition". If you are using the official code, you can refer to our user guide https://github.com/PaddlePaddle/PaddleOCR/blob/main/docs/version3.x/pipeline_usage/PaddleOCR-VL.en.md and set use_chart_recognition to True.