RRepoGEO

REPOGEO REPORT · LITE

zjunlp/PromptKG

Default branch main · commit 3035e7f8 · scanned 6/9/2026, 10:08:07 PM

GitHub: 734 stars · 76 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
40 /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
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/PromptKG, 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
    Reposition README opening to clarify project type and scope

    Why:

    CURRENT
    PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.
    COPY-PASTE FIX
    PromptKG is a comprehensive research toolkit and curated gallery focusing on the intersection of Prompt Learning and Knowledge Graphs. It provides implementations of research models, libraries for PLM-based KG embeddings, and a valuable paper-list for NLP researchers and AI engineers.
  • mediumtopics#2
    Add topics emphasizing 'research toolkit' and 'paper collection'

    Why:

    CURRENT
    awsome-list, demo-tuning, dialogue, genkgc, knowledge-graph, knowledge-informed-prompt-learning, lambdakg, link-prediction, natural-language-processing, nlp, paper, paper-list, prompt-tuning, promptkg, pytorch, question-answering, relation-extraction, retrieval-augmented, retrievalre, retroprompt
    COPY-PASTE FIX
    awsome-list, demo-tuning, dialogue, genkgc, knowledge-graph, knowledge-informed-prompt-learning, lambdakg, link-prediction, natural-language-processing, nlp, paper, paper-list, prompt-tuning, promptkg, pytorch, question-answering, relation-extraction, retrieval-augmented, retrievalre, retroprompt, research-toolkit, nlp-research, knowledge-graph-research, prompt-learning-toolkit
  • mediumreadme#3
    Add a 'Who is PromptKG for?' or 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    ### Who is PromptKG for?
PromptKG is designed for NLP researchers and AI engineers interested in the intersection of prompt learning and knowledge graphs. It serves as a comprehensive resource for understanding and implementing state-of-the-art research. It is *not* a production-ready knowledge graph database like Neo4j or TypeDB, nor is it a general-purpose deep learning framework like PyTorch or TensorFlow. Instead, it provides specialized tools and research implementations for PLM-based KG embeddings and prompt engineering.

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 zjunlp/PromptKG
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Neo4j
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Neo4j · recommended 2×
  2. Grakn (now Vaticle's TypeDB) · recommended 1×
  3. RDFox · recommended 1×
  4. Stardog · recommended 1×
  5. LangChain · recommended 1×
  • CATEGORY QUERY
    How can I leverage prompt learning and knowledge graphs for NLP tasks like QA or relation extraction?
    you: not recommended
    AI recommended (in order):
    1. Neo4j
    2. Grakn (now Vaticle's TypeDB)
    3. RDFox
    4. Stardog
    5. LangChain
    6. LlamaIndex
    7. Haystack (deepset.ai)
    8. PromptSource
    9. GPT-4 (OpenAI)
    10. Claude 3 (Anthropic)
    11. Llama 2 (Meta AI)
    12. Mistral 7B / Mixtral 8x7B (Mistral AI)

    AI recommended 12 alternatives but never named zjunlp/PromptKG. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools help with creating and dynamically editing PLM-based knowledge graph embeddings?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. PyTorch
    3. TensorFlow
    4. Deep Graph Library (DGL)
    5. PyTorch Geometric (PyG)
    6. OpenKE
    7. AmpliGraph
    8. Neo4j
    9. Neo4j Graph Data Science Library (GDS)
    10. KGTK

    AI recommended 10 alternatives but never named zjunlp/PromptKG. 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/PromptKG?
    pass
    AI named zjunlp/PromptKG 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/PromptKG in production, what risks or prerequisites should they evaluate first?
    pass
    AI named zjunlp/PromptKG 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/PromptKG solve, and who is the primary audience?
    pass
    AI named zjunlp/PromptKG 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/PromptKG. 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/zjunlp/PromptKG.svg)](https://repogeo.com/en/r/zjunlp/PromptKG)
HTML
<a href="https://repogeo.com/en/r/zjunlp/PromptKG"><img src="https://repogeo.com/badge/zjunlp/PromptKG.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

zjunlp/PromptKG — 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