- 添加 txt 到允许上传格式,跳过 MinerU OCR - 直接读取 UTF-8 文本,按 3000 字符/页分页后送入 LangExtract - 适合有中文文本的规范文件,避免扫描件 OCR 乱码问题
This commit is contained in:
@@ -110,6 +110,7 @@ async def list_formats():
|
||||
{"ext": "jpg", "description": "JPEG 图片(单页)", "max_size_mb": 200, "max_pages": 1, "requires_ocr": True},
|
||||
{"ext": "jpeg", "description": "JPEG 图片(单页)", "max_size_mb": 200, "max_pages": 1, "requires_ocr": True},
|
||||
{"ext": "html", "description": "HTML 文件", "max_size_mb": 200, "max_pages": 600, "requires_ocr": False},
|
||||
{"ext": "txt", "description": "纯文本文件(UTF-8 编码)", "max_size_mb": 200, "max_pages": 0, "requires_ocr": False},
|
||||
],
|
||||
"ocr_languages": [
|
||||
{"code": "ch", "name": "中文(默认)"},
|
||||
|
||||
Reference in New Issue
Block a user