REPOGEO REPORT · LITE

zjunlp/DeepKE

Default branch main · commit 4b27718f · scanned 5/25/2026, 11:56:47 PM

GitHub: 4,401 stars · 743 forks

AI VISIBILITY SCORE

71 /100

Needs work

Category recall

1 / 2

Avg rank #2.0 when recommended

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 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 zjunlp/DeepKE, 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

Emphasize DeepKE's unique scenario support in the README's introductory paragraph

Why:

CURRENT

DeepKE is a knowledge extraction toolkit for knowledge graph construction supporting **cnSchema**，**low-resource**, **document-level** and **multimodal** scenarios for *entity*, *relation* and *attribute* extraction. We provide documents, online demo, paper, slides and poster for beginners.

COPY-PASTE FIX

DeepKE is a comprehensive knowledge extraction toolkit specifically designed for knowledge graph construction, with robust support for challenging scenarios including **Chinese text**, **low-resource environments**, **document-level extraction**, and **multimodal data**. It facilitates entity, relation, and attribute extraction, offering resources like documents, an online demo, papers, slides, and posters for new users.

mediumabout#2

Expand the repository description to highlight key scenario support

Why:

CURRENT

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

COPY-PASTE FIX

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction, specifically designed for Chinese, low-resource, document-level, and multimodal scenarios.

lowtopics#3

Add LLM-related topics to reflect README content

Why:

CURRENT

attribute-extraction, chinese, deep-learning, deepke, document-level, few-shot, information-extraction, instructie, kg, knowledge-graph, knowprompt, lightner, low-resource, multi-modal, named-entity-recognition, ner, nlp, prompt, pytorch, relation-extraction

COPY-PASTE FIX

attribute-extraction, chinese, deep-learning, deepke, document-level, few-shot, information-extraction, instructie, kg, knowledge-graph, knowprompt, lightner, low-resource, large-language-models, llm, multi-modal, named-entity-recognition, ner, nlp, prompt, pytorch, relation-extraction

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

1 / 2

50% of queries surface zjunlp/DeepKE

Avg rank

#2.0

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

pyg-team/pytorch_geometric

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

pyg-team/pytorch_geometric · recommended 1×
dmlc/dgl · recommended 1×
thunlp/OpenNRE · recommended 1×
huggingface/transformers · recommended 1×
usc-isi-i2/kgtk · recommended 1×

CATEGORY QUERY
What are the best deep learning toolkits for automated knowledge graph construction?
you: #2
AI recommended (in order):
1. PyTorch Geometric (pyg-team/pytorch_geometric)
2. DeepKE (DeepKE-NLP/DeepKE) ← you
3. DGL (dmlc/dgl)
4. OpenNRE (thunlp/OpenNRE)
5. Hugging Face Transformers (huggingface/transformers)
6. KGTK (usc-isi-i2/kgtk)
Show full AI answer
CATEGORY QUERY
How to extract knowledge graphs from Chinese text in low-resource and document-level scenarios?
you: not recommended
AI recommended (in order):
1. OpenNRE
2. PaddleNLP
3. Hugging Face Transformers
4. Stanford CoreNLP
5. Spacy
6. PyKEEN
7. OpenKE
8. Doccano
9. Label Studio
10. fastText
11. Tencent AI Lab
AI recommended 11 alternatives but never named zjunlp/DeepKE. 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 zjunlp/DeepKE?
pass
AI named zjunlp/DeepKE explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts zjunlp/DeepKE in production, what risks or prerequisites should they evaluate first?
pass
AI named zjunlp/DeepKE 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 zjunlp/DeepKE solve, and who is the primary audience?
pass
AI named zjunlp/DeepKE explicitly
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 zjunlp/DeepKE. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/zjunlp/DeepKE.svg)](https://repogeo.com/en/r/zjunlp/DeepKE)

HTML

<a href="https://repogeo.com/en/r/zjunlp/DeepKE"><img src="https://repogeo.com/badge/zjunlp/DeepKE.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

zjunlp/DeepKE — 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