pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix plainPdf bugs (#152)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-26 15:11:07 +08:00
committed by GitHub
parent 75f7c6da2f
commit da21320b88
13 changed files with 36 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
deepdoc/vision/ocr.py
View File

@ -14,9 +14,6 @@
import copy
import time
import os
from huggingface_hub import snapshot_download
from .operators import *
import numpy as np
import onnxruntime as ort
@ -24,7 +21,6 @@ import onnxruntime as ort
from .postprocess import build_post_process
from rag.settings import cron_logger
def transform(data, ops=None):
""" transform """
if ops is None:
@ -82,7 +78,7 @@ class TextRecognizer(object):
self.rec_batch_num = 16
postprocess_params = {
'name': 'CTCLabelDecode',
"character_dict_path": os.path.join(os.path.dirname(os.path.realpath(__file__)), "ocr.res"),
"character_dict_path": os.path.join(model_dir, "ocr.res"),
"use_space_char": True
}
self.postprocess_op = build_post_process(postprocess_params)

4
deepdoc/vision/table_structure_recognizer.py
View File

@ -16,6 +16,7 @@ import re
from collections import Counter
import numpy as np
from huggingface_hub import snapshot_download
from api.utils.file_utils import get_project_base_directory
from rag.nlp import huqie
@ -33,7 +34,8 @@ class TableStructureRecognizer(Recognizer):
]
def __init__(self):
super().__init__(self.labels, "tsr",os.path.join(get_project_base_directory(), "rag/res/deepdoc/"))
model_dir = snapshot_download(repo_id="InfiniFlow/deepdoc")
super().__init__(self.labels, "tsr", model_dir)#os.path.join(get_project_base_directory(), "rag/res/deepdoc/"))
def __call__(self, images, thr=0.2):
tbls = super().__call__(images, thr)