Building RagRabbit, An Open Source RAG Search with Postgres as the Vector Store
Blog post from Neon
Marco D'Alia, a software architect behind RagRabbit, built the tool to simplify his own workflow by combining multiple systems for web scraping, vector search, and AI responses into one single, open-source toolkit. RagRabbit crawls websites, converts pages to Markdown, generates embeddings with Postgres via pgVector, provides AI Q&A using OpenAI or Claude, and offers an MCP server for read-only doc chunks directly into IDEs or chat apps. The tool accommodates different authentication setups, including user/password, GitHub OAuth, and magic links, and can be deployed on Vercel's Neon with a single click, taking advantage of its serverless scaling and Postgres features like full-text search.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| Vector Search | 14 | 1,879 | 278 | 111 | +3% |
| LLM | 9 | 4,855 | 541 | 180 | +51% |
| RAG | 5 | 1,499 | 228 | 73 | +7% |
| MCP | 4 | 1,783 | 93 | 50 | +605% |
| Serverless | 3 | 748 | 176 | 78 | +30% |
| AI Model Fine-tuning | 1 | 692 | 165 | 79 | +32% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.