Explore 'rag' MCP Resources

An Electron React-based MCP client example integrating LLMs like Gemini and Vercel AI SDK for platform communication.

Java AI framework supporting full scenario application development with LLM, Function Call, RAG, Embedding, Flow, MCP Server, Client.

A language model chat application with RAG, database, and MCP server capabilities, optimized for Japanese users.

Provides up-to-date Rust crate documentation for AI assistants to improve code accuracy.

A CLI tool for personal RAG that retrieves data from Notion, Obsidian, Apple Notes, stored in Qdrant, exposed as an MCP server.

A local MCP server that performs web search using a RAG-like protocol without APIs.

A server enabling Retrieval Augmented Generation (RAG) by indexing documents for efficient info retrieval for LLMs.

Connects MCP servers with Semantic Kernel to enable LLMs to call external tools seamlessly.

This MCP enables seamless integration between Ollama models and other applications for efficient AI processing.

A demo MCP integrating retrieval-augmented generation with document retrieval and context-aware prompt generation.