MariaDB Cloud Hybrid RAG Search

4

Combines MariaDB's native vector search with real-time web search through Brave API integration, enabling hybrid retrieval workflows that query both internal knowledge bases and external web results simultaneously.

GitHub
Category APIs
Added Mar 28, 2026
Views 52

About

This MariaDB Cloud hybrid search implementation combines semantic vector search capabilities with real-time web search augmentation through a Brave Search MCP server. The system uses MariaDB's native vector search with cosine distance, generating embeddings via SentenceTransformer's all-MiniLM-L6-v2 model, while simultaneously querying external web results through a FastMCP-powered Brave API integration. This architecture keeps vector data directly in the database, making it ideal for RAG workflows that need both internal knowledge retrieval and real-time external information augmentation.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/mariadb-cloud-hybrid-rag-search.svg)](https://hifriendbot.com/ai-list/mariadb-cloud-hybrid-rag-search/)
Listed on AiList

Compare

MariaDB Cloud Hybrid RAG Search vs Knowledge RAG MariaDB Cloud Hybrid RAG Search vs Alibaba Cloud Lindorm MariaDB Cloud Hybrid RAG Search vs RAG

Similar Projects

Knowledge RAG

80

Local knowledge retrieval system that combines semantic search with keyword-based routing for document analysis across security, development, and general knowledge domains using ChromaDB for vector storage and hybrid search through Reciprocal Rank Fusion.

MCP Servers Python

Alibaba Cloud Lindorm

3

Provides a bridge between AI and Alibaba Cloud's Lindorm database, enabling vector search operations and SQL query execution for knowledge retrieval and data exploration

MCP Servers Python

RAG

5

Provides cloud-based document management and semantic search using OpenAI embeddings with in-memory vector storage, enabling retrieval-augmented generation workflows through document ingestion, metadata filtering, and cosine similarity search.

MCP Servers

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project