# Building RagRabbit, An Open Source RAG Search with Postgres as the Vector Store

DevFeed: [Building RagRabbit, An Open Source RAG Search with Postgres as the Vector Store](<https://devfeed.tech/articles/building-ragrabbit-an-open-source-rag-search-with-postgres-as-the-vector-store-5761.md>)

Original publisher: [Read original article](<https://neon.com/blog/ragrabbit-neon>)

Author: Carlota Soto

Published: 2025-03-17T17:40:19Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [Web Scraping](<https://devfeed.tech/topics/web-scraping.md>), [llamaindex](<https://devfeed.tech/topics/llamaindex.md>), [Model Context Protocol (MCP)](<https://devfeed.tech/topics/model-context-protocol-mcp.md>), [Appwrite](<https://devfeed.tech/topics/appwrite.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [building](<https://devfeed.tech/tags/building.md>), [case-studies](<https://devfeed.tech/tags/case-studies.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [databases](<https://devfeed.tech/tags/databases.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [llamaindex](<https://devfeed.tech/tags/llamaindex.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [openai](<https://devfeed.tech/tags/openai.md>), [rag](<https://devfeed.tech/tags/rag.md>), [search](<https://devfeed.tech/tags/search.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [source](<https://devfeed.tech/tags/source.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

## AI overview

This article introduces RagRabbit, an open-source toolkit for building retrieval-augmented generation workflows with Postgres and pgVector. It crawls websites, converts pages to Markdown, creates LLM-friendly text files, stores embeddings in Postgres, and provides AI question answering through OpenAI or Claude. It also offers an MCP server for supplying relevant document chunks to Cursor and Claude Desktop, with deployment on Vercel and Neon.

## Source excerpt

"When I started RagRabbit, I did testing on vector databases, but I didn't see a real advantage. Postgres with Pgvector covers everything I need, and it's very performant for the number of rows I handle" (Marco D'Alia, Software Architect behind RagRabbit) While experimenting with...