RRepoGEO

REPOGEO REPORT · LITE

supabase-community/nextjs-openai-doc-search

Default branch main · commit 50d6bb71 · scanned 5/15/2026, 2:02:58 AM

GitHub: 1,716 stars · 313 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 supabase-community/nextjs-openai-doc-search, 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 emphasize 'complete starter template'

    Why:

    CURRENT
    This starter takes all the `.mdx` files in the `pages` directory and processes them to use as custom context within OpenAI Text Completion prompts.
    COPY-PASTE FIX
    This project is a complete, deployable Next.js application template for building your own custom ChatGPT-style documentation search. It provides a full-stack solution that processes your `.mdx` files, stores embeddings in Supabase with `pgvector`, and integrates with OpenAI for text completion prompts.
  • mediumreadme#2
    Add a 'Why Choose This Starter?' section to highlight differentiators

    Why:

    COPY-PASTE FIX
    ## Why Choose This Starter?

This project stands out as a complete, opinionated template for several reasons:

*   **Full-stack Integration:** Seamlessly combines Next.js for the frontend, Supabase (Postgres with `pgvector`) for vector storage and backend, and OpenAI for powerful semantic search and text completion.
*   **Ready-to-Deploy:** Designed as a starter kit, it's optimized for quick deployment to platforms like Vercel, getting your custom doc search live in minutes.
*   **Customizable Knowledge Base:** Easily adapt it to your own `.mdx` documentation, providing a tailored AI experience for your users.
*   **Open-Source Reference:** Serves as a robust, open-source reference architecture for building AI-powered semantic search applications.
  • lowtopics#3
    Add more specific topics for 'starter kit' and 'full-stack'

    Why:

    CURRENT
    ai, chatgpt, nextjs, openai, postgres, supabase, template, vector-search
    COPY-PASTE FIX
    ai, chatgpt, nextjs, openai, postgres, supabase, template, vector-search, starter-kit, full-stack-app, semantic-search-app

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 supabase-community/nextjs-openai-doc-search
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
deepset-ai/haystack
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. deepset-ai/haystack · recommended 1×
  2. OpenAI Embeddings · recommended 1×
  3. Pinecone · recommended 1×
  4. weaviate/weaviate · recommended 1×
  5. qdrant/qdrant · recommended 1×
  • CATEGORY QUERY
    How to implement a custom question-answering system for website documentation using semantic search?
    you: not recommended
    AI recommended (in order):
    1. Haystack (deepset-ai/haystack)
    2. OpenAI Embeddings
    3. Pinecone
    4. Weaviate (weaviate/weaviate)
    5. Qdrant (qdrant/qdrant)
    6. BERT
    7. GPT-3.5/GPT-4
    8. LlamaIndex (run-llama/llama_index)
    9. Chroma (chroma-core/chroma)
    10. FAISS (facebookresearch/faiss)
    11. Milvus (milvus-io/milvus)
    12. LangChain (langchain-ai/langchain)
    13. Supabase Vector
    14. Redis (redis/redis)
    15. Elasticsearch (elastic/elasticsearch)
    16. Hugging Face Transformers (huggingface/transformers)
    17. Sentence Transformers (UKPLab/sentence-transformers)
    18. Annoy (spotify/annoy)
    19. OpenAI

    AI recommended 19 alternatives but never named supabase-community/nextjs-openai-doc-search. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a quick-start solution for building a conversational agent over my project's knowledge base.
    you: not recommended
    AI recommended (in order):
    1. LangChain
    2. LlamaIndex
    3. Haystack
    4. Rasa
    5. Azure AI Search + Azure OpenAI Service
    6. Google Cloud Vertex AI Search and Conversation
    7. Amazon Kendra + Amazon Lex/Bedrock

    AI recommended 7 alternatives but never named supabase-community/nextjs-openai-doc-search. 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 supabase-community/nextjs-openai-doc-search?
    pass
    AI did not name supabase-community/nextjs-openai-doc-search — 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 supabase-community/nextjs-openai-doc-search in production, what risks or prerequisites should they evaluate first?
    pass
    AI named supabase-community/nextjs-openai-doc-search 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 supabase-community/nextjs-openai-doc-search solve, and who is the primary audience?
    pass
    AI did not name supabase-community/nextjs-openai-doc-search — 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 supabase-community/nextjs-openai-doc-search. 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/supabase-community/nextjs-openai-doc-search.svg)](https://repogeo.com/en/r/supabase-community/nextjs-openai-doc-search)
HTML
<a href="https://repogeo.com/en/r/supabase-community/nextjs-openai-doc-search"><img src="https://repogeo.com/badge/supabase-community/nextjs-openai-doc-search.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

supabase-community/nextjs-openai-doc-search — 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