Skip to content

vlm-http-client组织架构图识别成文字 #4620

@chhackman

Description

@chhackman

🔎 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

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions