centersl/MinerU
1
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-03-27 11:08:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

feat: update parse_doc function to support backend options and add environment variable instructions

Browse Source
This commit is contained in:
myhloli
2025-06-13 15:48:34 +08:00
parent 8737ebb2e2
commit d41179da84
1 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
demo/demo.py
View File

@@ -230,4 +230,14 @@ if __name__ == '__main__':
for doc_path in Path(pdf_files_dir).glob('*'):
if doc_path.suffix in pdf_suffixes + image_suffixes:
doc_path_list.append(doc_path)
parse_doc(doc_path_list, output_dir)
"""如果您由于网络问题无法下载模型，可以设置环境变量MINERU_MODEL_SOURCE为modelscope使用免代理仓库下载模型"""
# os.environ['MINERU_MODEL_SOURCE'] = "modelscope"
"""Use pipeline mode if your environment does not support VLM"""
parse_doc(doc_path_list, output_dir, backend="pipeline")
"""To enable VLM mode, change the backend to 'vlm-xxx'"""
# parse_doc(doc_path_list, output_dir, backend="vlm-transformers") # more general.
# parse_doc(doc_path_list, output_dir, backend="vlm-sglang-engine") # faster(engine).
# parse_doc(doc_path_list, output_dir, backend="vlm-sglang-client", server_url="http://127.0.0.1:30000"） # faster(client).