REPOGEO REPORT · LITE

shibing624/similarities

Default branch main · commit 80d5ef40 · scanned 6/3/2026, 4:07:00 AM

GitHub: 902 stars · 88 forks

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 shibing624/similarities, 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's main heading and opening sentence

Why:

CURRENT

# Similarities: Similarity Calculation and Semantic Search
**similarities**: a toolkit for similarity calculation and semantic search, supports text and image.

COPY-PASTE FIX

# Similarities: A Python Toolkit for Semantic Search & Similarity Calculation (Text & Image)
**similarities**: a comprehensive Python toolkit for building semantic search and similarity applications, supporting text and image data at scale.

mediumtopics#2

Add more specific topics related to vector search and large-scale data

Why:

CURRENT

bm25, deep-learning, faiss, image-search, image-similarity, matching, nlp, pytorch, search-engine, similarity, similarity-search, text-matching

COPY-PASTE FIX

bm25, deep-learning, faiss, image-search, image-similarity, matching, nlp, pytorch, search-engine, similarity, similarity-search, text-matching, vector-search, vector-embeddings, large-scale, information-retrieval, python-library

lowreadme#3

Add a 'Comparison to Alternatives' section in the README

Why:

COPY-PASTE FIX

Add a new section, e.g., `## Comparison to Alternatives` with a brief explanation like: `Unlike full-fledged vector databases (e.g., Weaviate, Pinecone) or low-level indexing libraries (e.g., Faiss), Similarities is a Python toolkit focused on providing a comprehensive, easy-to-use suite of algorithms for similarity calculation and semantic search, integrating with these underlying technologies for scalable solutions.`

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 shibing624/similarities

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

facebookresearch/faiss

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

facebookresearch/faiss · recommended 2×
weaviate/weaviate · recommended 2×
Pinecone · recommended 2×
milvus-io/milvus · recommended 2×
deepset-ai/haystack · recommended 1×

CATEGORY QUERY
What Python library helps build a semantic search engine for billions of text documents?
you: not recommended
AI recommended (in order):
1. Haystack (deepset-ai/haystack)
2. Sentence-Transformers (UKP-LAB/sentence-transformers)
3. Faiss (facebookresearch/faiss)
4. Weaviate (weaviate/weaviate)
5. Pinecone
6. Elasticsearch (elastic/elasticsearch)
7. Milvus (milvus-io/milvus)
AI recommended 7 alternatives but never named shibing624/similarities. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Looking for a comprehensive toolkit to calculate text and image similarities for search applications.
you: not recommended
AI recommended (in order):
1. Hugging Face Transformers (huggingface/transformers)
2. FAISS (facebookresearch/faiss)
3. OpenAI Embeddings
4. Pinecone
5. Weaviate (weaviate/weaviate)
6. Elasticsearch
7. Milvus (milvus-io/milvus)
8. Qdrant (qdrant/qdrant)
9. Sentence-Transformers (UKPLab/sentence-transformers)
10. CLIP
AI recommended 10 alternatives but never named shibing624/similarities. 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 shibing624/similarities?
pass
AI named shibing624/similarities explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts shibing624/similarities in production, what risks or prerequisites should they evaluate first?
pass
AI named shibing624/similarities 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 shibing624/similarities solve, and who is the primary audience?
pass
AI named shibing624/similarities 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 shibing624/similarities. 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/shibing624/similarities.svg)](https://repogeo.com/en/r/shibing624/similarities)

HTML

<a href="https://repogeo.com/en/r/shibing624/similarities"><img src="https://repogeo.com/badge/shibing624/similarities.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

shibing624/similarities — 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