Docs RAG
About
Utilizing a RAG framework developed with TypeScript, LlamaIndex, and Gemini embeddings, this protocol empowers artificial intelligence to search and assess native files and Git repositories effectively.
Explore Similar MCP Servers
Crawl4AI RAG
Enhance your knowledge access by leveraging a cutting-edge Model Context Protocol (MCP) that combines web crawling and RAG capabilities. This innovative approach allows for seamless retrieval and storage of website content in vector databases, paving the way for advanced semantic search functionalities across crawled data.
Kodit
Enhances local code repositories by leveraging tree-sitter analysis and semantic embeddings to support a unique hybrid search method that blends vector similarity with keyword matching, empowering contextual code retrieval.
Rust Docs
Discover an advanced approach to managing Rust crate documentation through seamless integration with LlamaIndex's HTML reader. Benefit from smart file selection algorithms, eliminating duplicates, and enjoy flexible parsing options for in-depth analysis.
LlamaIndex Documentation
Access the LlamaIndex documentation effortlessly through a dynamic query interface fueled by RAG technology. Receive comprehensive information and code illustrations from LlamaCloud's proficient index service.
Ragie
Enhances connectivity with Ragie's knowledge repository system for streamlined retrieval and extraction of data from extensive datasets, optimizing search and information access.
Cloudflare AutoRAG
Elevate your AI applications with precision by implementing comprehensive RAG pipelines that are fully managed for seamless operation.
GraphRAG
Enhance your document search experience with a potent combination of Neo4j graph database and Qdrant vector database. Uncover semantic connections and expand structural context by seamlessly following relationships.
Consult LLM
Enhance intricate reasoning assignments using advanced language models like OpenAI o3, Google Gemini 2.5 Pro, and DeepSeek Reasoner. Share markdown cues along with code environment details and git differentials to receive comprehensive responses including precise cost analysis.
Minima (Local RAG)
Efficiently access and fetch contextual information from nearby documents for RAG applications.
GitHub Chat
Unlock the capability for artificial intelligence to scrutinize and search GitHub code repositories via an interface built on the efficient FastMCP framework. Gain insights into code structures, delve into architectural aspects, and extract relevant contextual details along with their corresponding source citations.
Apify RAG Web Browser
Utilize Apify's RAG Web Browser Actor, an open-source tool, to seamlessly conduct online searches, extract website links, and deliver information formatted in Markdown.
RAG Docs
Enhances information retrieval through semantic search functionality and a vector database (Qdrant), facilitating streamlined access to extensive document repositories.
RAG Documentation
Experience advanced knowledge access with seamless integration of Qdrant vector search and documentation retrieval in Model Context Protocol (MCP). Unlock context-aware responses and enable semantic querying for a richer user experience.
Google Docs
Enhances the connection between Google Docs and artificial intelligence applications, enabling seamless interaction for analyzing, editing, and formatting text in documents.
Vertex AI Gemini
Enhance your Google Cloud Vertex AI Gemini model integration with web search connection, precise knowledge retrieval, and text-based replies using customizable utilities and real-time assistance.