A local Retrieval-Augmented Generation system that enables AI agents to query and retrieve information from document collections using ChromaDB vector search and Ollama LLMs through a FastAPI interface.
A Retrieval-Augmented Generation system that enables uploading, processing, and semantic search of PDF documents using vector embeddings and FAISS indexing for context-aware question answering.
A modular RAG (Retrieval-Augmented Generation) service framework with pluggable architecture and full observability, enabling AI assistants to perform document Q\&A, semantic search, and knowledge base construction through the Model Context Protocol.
Enables AI-powered querying and management of documentation through markdown file serving, keyword search, and OpenAI-based Q\&A capabilities. Supports document indexing, analysis, and agent handoffs with rate limiting protection.
An MCP server and document upload API designed for RAG workflows with Weaviate vector databases. It enables users to search, retrieve, and manage documents across specialized collections like account notes, product promos, and contracts.
Enables LLMs to search and retrieve information from large technical documentation (OpenAPI specs, markdown) via intelligent chunking and semantic search.
