提醒fitz包是来自pyMuPDF (#1407)

This commit is contained in:
roki1031 2023-09-08 12:20:20 +08:00 committed by GitHub
parent f422575a17
commit 196bde3ead
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions

View File

@ -5,7 +5,7 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
class RapidOCRPDFLoader(UnstructuredFileLoader): class RapidOCRPDFLoader(UnstructuredFileLoader):
def _get_elements(self) -> List: def _get_elements(self) -> List:
def pdf2text(filepath): def pdf2text(filepath):
import fitz import fitz # pyMuPDF里面的fitz包不要与pip install fitz混淆
from rapidocr_onnxruntime import RapidOCR from rapidocr_onnxruntime import RapidOCR
import numpy as np import numpy as np
ocr = RapidOCR() ocr = RapidOCR()