refine: 调整docker
This commit is contained in:
parent
c85e166208
commit
1138683da1
|
|
@ -7,7 +7,6 @@ services:
|
||||||
- "8000:8000"
|
- "8000:8000"
|
||||||
volumes:
|
volumes:
|
||||||
- ./storage:/app/storage
|
- ./storage:/app/storage
|
||||||
- ./legal_doc_masker.db:/app/legal_doc_masker.db
|
|
||||||
env_file:
|
env_file:
|
||||||
- .env
|
- .env
|
||||||
environment:
|
environment:
|
||||||
|
|
@ -21,7 +20,6 @@ services:
|
||||||
command: celery -A app.services.file_service worker --loglevel=info
|
command: celery -A app.services.file_service worker --loglevel=info
|
||||||
volumes:
|
volumes:
|
||||||
- ./storage:/app/storage
|
- ./storage:/app/storage
|
||||||
- ./legal_doc_masker.db:/app/legal_doc_masker.db
|
|
||||||
env_file:
|
env_file:
|
||||||
- .env
|
- .env
|
||||||
environment:
|
environment:
|
||||||
|
|
|
||||||
|
|
@ -1,67 +0,0 @@
|
||||||
import json
|
|
||||||
import shutil
|
|
||||||
import os
|
|
||||||
|
|
||||||
import requests
|
|
||||||
from modelscope import snapshot_download
|
|
||||||
|
|
||||||
|
|
||||||
def download_json(url):
|
|
||||||
# 下载JSON文件
|
|
||||||
response = requests.get(url)
|
|
||||||
response.raise_for_status() # 检查请求是否成功
|
|
||||||
return response.json()
|
|
||||||
|
|
||||||
|
|
||||||
def download_and_modify_json(url, local_filename, modifications):
|
|
||||||
if os.path.exists(local_filename):
|
|
||||||
data = json.load(open(local_filename))
|
|
||||||
config_version = data.get('config_version', '0.0.0')
|
|
||||||
if config_version < '1.2.0':
|
|
||||||
data = download_json(url)
|
|
||||||
else:
|
|
||||||
data = download_json(url)
|
|
||||||
|
|
||||||
# 修改内容
|
|
||||||
for key, value in modifications.items():
|
|
||||||
data[key] = value
|
|
||||||
|
|
||||||
# 保存修改后的内容
|
|
||||||
with open(local_filename, 'w', encoding='utf-8') as f:
|
|
||||||
json.dump(data, f, ensure_ascii=False, indent=4)
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
mineru_patterns = [
|
|
||||||
# "models/Layout/LayoutLMv3/*",
|
|
||||||
"models/Layout/YOLO/*",
|
|
||||||
"models/MFD/YOLO/*",
|
|
||||||
"models/MFR/unimernet_hf_small_2503/*",
|
|
||||||
"models/OCR/paddleocr_torch/*",
|
|
||||||
# "models/TabRec/TableMaster/*",
|
|
||||||
# "models/TabRec/StructEqTable/*",
|
|
||||||
]
|
|
||||||
model_dir = snapshot_download('opendatalab/PDF-Extract-Kit-1.0', allow_patterns=mineru_patterns)
|
|
||||||
layoutreader_model_dir = snapshot_download('ppaanngggg/layoutreader')
|
|
||||||
model_dir = model_dir + '/models'
|
|
||||||
print(f'model_dir is: {model_dir}')
|
|
||||||
print(f'layoutreader_model_dir is: {layoutreader_model_dir}')
|
|
||||||
|
|
||||||
# paddleocr_model_dir = model_dir + '/OCR/paddleocr'
|
|
||||||
# user_paddleocr_dir = os.path.expanduser('~/.paddleocr')
|
|
||||||
# if os.path.exists(user_paddleocr_dir):
|
|
||||||
# shutil.rmtree(user_paddleocr_dir)
|
|
||||||
# shutil.copytree(paddleocr_model_dir, user_paddleocr_dir)
|
|
||||||
|
|
||||||
json_url = 'https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/magic-pdf.template.json'
|
|
||||||
config_file_name = 'magic-pdf.json'
|
|
||||||
home_dir = os.path.expanduser('~')
|
|
||||||
config_file = os.path.join(home_dir, config_file_name)
|
|
||||||
|
|
||||||
json_mods = {
|
|
||||||
'models-dir': model_dir,
|
|
||||||
'layoutreader-model-dir': layoutreader_model_dir,
|
|
||||||
}
|
|
||||||
|
|
||||||
download_and_modify_json(json_url, config_file, json_mods)
|
|
||||||
print(f'The configuration file has been configured successfully, the path is: {config_file}')
|
|
||||||
Loading…
Reference in New Issue