test_ai/document_loaders/myimgloader.py

26 lines
824 B
Python
Raw Normal View History

2024-01-12 10:26:57 +08:00
from typing import List
from langchain.document_loaders.unstructured import UnstructuredFileLoader
class RapidOCRLoader(UnstructuredFileLoader):
def _get_elements(self) -> List:
def img2text(filepath):
from rapidocr_onnxruntime import RapidOCR
resp = ""
ocr = RapidOCR()
result, _ = ocr(filepath)
if result:
ocr_result = [line[1] for line in result]
resp += "\n".join(ocr_result)
return resp
text = img2text(self.file_path)
from unstructured.partition.text import partition_text
return partition_text(text=text, **self.unstructured_kwargs)
if __name__ == "__main__":
loader = RapidOCRLoader(file_path="../tests/samples/ocr_test.jpg")
docs = loader.load()
print(docs)