vlm-http-client组织架构图识别成文字 #4620
Description
🔎 Search before asking | 提交之前请先搜索
- I have searched the MinerU Readme and found no similar bug report.
- I have searched the MinerU Issues and found no similar bug report.
- I have searched the MinerU Discussions and found no similar bug report.
🤖 Consult the online AI assistant for assistance | 在线 AI 助手咨询
- I have consulted the online AI assistant but was unable to obtain a solution to the issue.
Description of the bug | 错误描述
一个pdf中，一个公司的组织架构图，有部分解析成文字了，用的hybrid-http-client和vlm-http-client的backend, 但是pipeline是正常转成图片了，我的服务启动是mineru-vllm-server & api
How to reproduce the bug | 如何复现
mineru-vllm-server & mineru-api 启动
BACKENDS = ["pipeline", "vlm-http-client", "hybrid-http-client"]
def run_backend(backend: str):
data = {
"backend": backend,
"lang_list": "ch",
"parse_method": "auto",
"return_md": "true",
"return_middle_json": "true",
"return_images": "true",
"return_content_list": "true",
"image_resolution": "high",
"extract_tables": "true",
"extract_charts": "true",
"start_page_id": "0",
"end_page_id": "99999",
}
Operating System Mode | 操作系统类型
Linux
Operating System Version| 操作系统版本
Ubuntu 22.04
Python version | Python 版本
3.11
Software version | 软件版本 (mineru --version)
No response
Backend name | 解析后端
No response
Device mode | 设备模式
No response