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

Template for building your own custom ChatGPT style doc search powered by Next.js, OpenAI, and Supabase.

Repository: https://github.com/supabase-community/nextjs-openai-doc-search
Canonical: https://ross.abutalabs.com/products/nextjs-openai-doc-search
Homepage: https://supabase.com/blog/chatgpt-supabase-docs
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: ai, chatgpt, nextjs, openai, postgres, supabase, template, vector-search
Last push: 2026-05-12T19:58:11+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 82, release rhythm 35, longevity 89
- inputs: {"age_days": 1250, "days_push": 113, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1732, forks 315 (observed 2026-08-28T04:05:28.762440+00:00)

## What it is
A Next.js starter template for building a custom ChatGPT-style documentation search over your own .mdx content. It generates OpenAI embeddings at build time, stores them in Supabase Postgres with pgvector, and streams GPT answers grounded in vector similarity search results.

## Use cases
- build a chatgpt-style search over my docs
- add an ai question-answering bot to documentation
- create rag search over mdx files
- store openai embeddings in postgres with pgvector
- deploy a docs chatbot to vercel
- semantic search for a next.js site
- let users ask questions about my knowledge base

## When to choose
- you have mdx documentation and want a ChatGPT-like ask interface
- you already use or want Supabase Postgres with pgvector as your vector store
- you want a deployable Next.js template on Vercel with minimal setup

## When to avoid
- you need a production-grade RAG pipeline with advanced retrieval features
- your content is not markdown/mdx and would require heavy preprocessing
- you want to avoid OpenAI API costs or vendor lock-in
- you need a framework-agnostic or Python-based solution

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: rag, search-engine, llm-inference, web-framework
- domain: large-language-models, web-development, developer-tools
- platform: serverless
- tags: nextjs, openai, supabase, pgvector, vector-search, chatgpt, starter-template, mdx, embeddings, vercel, boilerplate, retrieval-augmented-generation, nodejs, web-server, docker

## Member repositories
- supabase-community/nextjs-openai-doc-search (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.762440+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:32:28.839244+00:00, confidence not recorded.
  - readme: https://github.com/supabase-community/nextjs-openai-doc-search (fetched 2026-08-28T04:05:28.762440+00:00, sha d80a4cc679aa)
  - homepage: https://supabase.com/blog/chatgpt-supabase-docs (fetched 2026-08-29T11:08:49.040248+00:00, sha 6c95f1a5118b)
  - site_page: https://supabase.com/features (fetched 2026-08-29T11:08:49.058895+00:00, sha 1db3c6202b2a)
  - site_page: https://supabase.com/docs (fetched 2026-08-29T11:08:49.052055+00:00, sha 3c98b89d27d7)
  - site_page: https://supabase.com/blog/new-supabase-docs-built-with-nextjs (fetched 2026-08-29T11:08:49.053827+00:00, sha 0cba9f7137d2)
  - site_page: https://supabase.com/docs/guides/ai (fetched 2026-08-29T11:08:49.055686+00:00, sha 6024c8d727b1)
  - site_page: https://supabase.com/blog/tags/docs (fetched 2026-08-29T11:08:49.057266+00:00, sha c71148552a24)
  - site_page: https://supabase.com/changelog (fetched 2026-08-29T11:08:49.060641+00:00, sha 117f8a7b5d70)
  - site_page: https://supabase.com/pricing (fetched 2026-08-29T11:08:49.049813+00:00, sha a762d00f7048)
- Data as of 2026-08-30T08:39:29.467469+00:00.