RRepoGEO

REPOGEO REPORT · LITE

magicyuan876/mineru-tianshu

Default branch main · commit 4a3710ab · scanned 6/12/2026, 9:11:53 AM

GitHub: 672 stars · 99 forks

AI VISIBILITY SCORE
27 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
1 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface magicyuan876/mineru-tianshu, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Add a clear, explicit opening sentence to the README

    Why:

    CURRENT
    The README currently starts with a centered H1 and a bold subtitle, followed by a list of features.
    COPY-PASTE FIX
    After the H1 and bold subtitle, add: 'Tianshu (天枢) is an enterprise-grade AI data preprocessing platform designed for multi-modal information extraction and document conversion, specifically for AI assistants and large language models.'
  • mediumtopics#2
    Expand repository topics to include broader categories

    Why:

    CURRENT
    deepseek-ocr, markitdown, mcp-server, mineru, paddleocr-vl, pdf-converter
    COPY-PASTE FIX
    ai-data-preprocessing, document-processing, multi-modal-ai, llm-data-preparation, ocr, pdf-to-markdown, office-to-markdown, fastapi, vue3, enterprise-ai, data-extraction, mcp-protocol
  • mediumabout#3
    Rephrase the repository description to emphasize core purpose

    Why:

    CURRENT
    天枢 - 企业级 AI 一站式数据预处理平台 | PDF/Office转Markdown | 支持MCP协议AI助手集成 | Vue3+FastAPI全栈方案 | 文档解析 | 多模态信息提取
    COPY-PASTE FIX
    天枢 - 企业级AI数据预处理平台，专注于PDF/Office转Markdown、多模态信息提取与文档解析，支持MCP协议AI助手集成。基于Vue3+FastAPI的全栈解决方案。

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface magicyuan876/mineru-tianshu
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Apache Tika
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Apache Tika · recommended 1×
  2. Pandoc · recommended 1×
  3. Unstructured.io · recommended 1×
  4. Microsoft Azure AI Document Intelligence · recommended 1×
  5. Google Cloud Document AI · recommended 1×
  • CATEGORY QUERY
    What's a robust enterprise solution for converting various document types to Markdown for AI processing?
    you: not recommended
    AI recommended (in order):
    1. Apache Tika
    2. Pandoc
    3. Unstructured.io
    4. Microsoft Azure AI Document Intelligence
    5. Google Cloud Document AI
    6. AWS Textract

    AI recommended 6 alternatives but never named magicyuan876/mineru-tianshu. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking an AI data preprocessing platform with multi-modal information extraction using FastAPI and Vue3.
    you: not recommended
    AI recommended (in order):
    1. Label Studio
    2. Argilla
    3. SuperAnnotate
    4. V7
    5. Prodigy
    6. CVAT

    AI recommended 6 alternatives but never named magicyuan876/mineru-tianshu. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of magicyuan876/mineru-tianshu?
    pass
    AI did not name magicyuan876/mineru-tianshu — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts magicyuan876/mineru-tianshu in production, what risks or prerequisites should they evaluate first?
    pass
    AI named magicyuan876/mineru-tianshu explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo magicyuan876/mineru-tianshu solve, and who is the primary audience?
    pass
    AI did not name magicyuan876/mineru-tianshu — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of magicyuan876/mineru-tianshu. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/magicyuan876/mineru-tianshu.svg)](https://repogeo.com/en/r/magicyuan876/mineru-tianshu)
HTML
<a href="https://repogeo.com/en/r/magicyuan876/mineru-tianshu"><img src="https://repogeo.com/badge/magicyuan876/mineru-tianshu.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

magicyuan876/mineru-tianshu — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite