---
title: "Supabase Clippy: ChatGPT for Supabase Docs"
description: "Supabase introduced “Supabase Clippy,” a ChatGPT-like interface trained on its documentation, as a hidden MVP in the Supabase docs. It responds to questions by retrieving relevant documentation and streaming GPT-3's answer in realtime. The implementation parses docs into sections, creates OpenAI embeddings, stores them in Postgres with pgvector, and injects matching documents as context for generation. The project was motivated by the growth of Supabase's product suite and documentation, plus the need to support developers unfamiliar with Postgres; the current version uses only Guides and is presented as a one-week MVP intended to gather feedback. Planned directions include adding reference docs and community discussions, caching repeated queries, thumbs-up relevance feedback, and interactive guidance."
---

# Supabase Clippy: ChatGPT for Supabase Docs

[Supabase](https://yomu.fyi/company/supabase) · paul\_copplestone · Feb 7, 2023

**Type:** Announcement

## Summary

Supabase introduced “Supabase Clippy,” a ChatGPT-like interface trained on its documentation, as a hidden MVP in the Supabase docs. It responds to questions by retrieving relevant documentation and streaming GPT-3's answer in realtime. The implementation parses docs into sections, creates OpenAI embeddings, stores them in Postgres with pgvector, and injects matching documents as context for generation. The project was motivated by the growth of Supabase's product suite and documentation, plus the need to support developers unfamiliar with Postgres; the current version uses only Guides and is presented as a one-week MVP intended to gather feedback. Planned directions include adding reference docs and community discussions, caching repeated queries, thumbs-up relevance feedback, and interactive guidance.

## Context

Supabase's product suite and documentation had grown substantially, while the project was attracting developers who had never used Postgres. The documentation also contained more information than an average developer would consume in one sitting, creating a need for a more accessible question-and-answer interface.

## Approach / What changed

The system parses Supabase documentation into sections, generates embeddings for each section through OpenAI's embeddings API, stores them in Postgres using pgvector, retrieves documents relevant to a user's question, injects those documents as context for GPT-3, and streams the response back in realtime. The MVP currently uses only the Guides.

## Takeaways

- Supabase Clippy is available as a hidden MVP in the Supabase docs and can be opened with cmd + /; the source notes that it is not available to mobile users.
- The retrieval pipeline combines OpenAI embeddings, Postgres with pgvector, contextual prompting for GPT-3, and realtime response streaming.
- Proposed extensions include indexing reference docs and community discussions, caching similar queries, collecting thumbs-up relevance feedback, and making the interface interactive.

**Tags:** [LLMs](https://yomu.fyi/topic/llm), [Open Source](https://yomu.fyi/topic/open-source), [Postgres](https://yomu.fyi/topic/postgres), [Search](https://yomu.fyi/topic/search)

- Source: [Supabase](https://supabase.com/blog/chatgpt-supabase-docs)
- Source URL: https://supabase.com/blog/chatgpt-supabase-docs
- Ingested by Yomu: 2026-08-29T01:16:19.299Z

[Read original post](https://supabase.com/blog/chatgpt-supabase-docs)