diff --git a/examples/data/di/dog.jpg b/examples/data/di/dog.jpg new file mode 100644 index 000000000..679a932e8 Binary files /dev/null and b/examples/data/di/dog.jpg differ diff --git a/examples/data/di/receipt_shopping.jpg b/examples/data/di/receipt_shopping.jpg new file mode 100644 index 000000000..3368eb42f Binary files /dev/null and b/examples/data/di/receipt_shopping.jpg differ diff --git a/examples/data/omniparse/test01.docx b/examples/data/omniparse/test01.docx index 7b6251799..87b37a8ee 100644 Binary files a/examples/data/omniparse/test01.docx and b/examples/data/omniparse/test01.docx differ diff --git a/examples/di/ocr_receipt.py b/examples/di/ocr_receipt.py index af54d519b..bf32f5722 100644 --- a/examples/di/ocr_receipt.py +++ b/examples/di/ocr_receipt.py @@ -1,17 +1,17 @@ +from metagpt.const import EXAMPLE_DATA_PATH from metagpt.roles.di.data_interpreter import DataInterpreter async def main(): # Notice: pip install metagpt[ocr] before using this example - image_path = "image.jpg" + image_path = EXAMPLE_DATA_PATH / "di/receipt_shopping.jpg" language = "English" requirement = f"""This is a {language} receipt image. Your goal is to perform OCR on images using PaddleOCR, output text content from the OCR results and discard - coordinates and confidence levels, then recognize the total amount from ocr text content, and finally save as table. + coordinates and confidence levels, then recognize the total amount from ocr text content, and finally save as csv table. Image path: {image_path}. NOTE: The environments for Paddle and PaddleOCR are all ready and has been fully installed.""" - di = DataInterpreter() - + di = DataInterpreter(react_mode="react") await di.run(requirement) diff --git a/examples/di/rm_image_background.py b/examples/di/rm_image_background.py index cb7900a0a..e28778241 100644 --- a/examples/di/rm_image_background.py +++ b/examples/di/rm_image_background.py @@ -1,5 +1,6 @@ import asyncio +from metagpt.const import DEFAULT_WORKSPACE_ROOT, EXAMPLE_DATA_PATH from metagpt.roles.di.data_interpreter import DataInterpreter @@ -9,7 +10,7 @@ async def main(requirement: str = ""): if __name__ == "__main__": - image_path = "/your/path/to/the/image.jpeg" - save_path = "/your/intended/save/path/for/image_rm_bg.png" + image_path = EXAMPLE_DATA_PATH / "di/dog.jpg" + save_path = DEFAULT_WORKSPACE_ROOT / "image_rm_bg.png" requirement = f"This is a image, you need to use python toolkit rembg to remove the background of the image and save the result. image path:{image_path}; save path:{save_path}." asyncio.run(main(requirement))