Enables ingestion and semantic search over text documents using PostgreSQL + pgvector and OpenAI-compatible embeddings, allowing any LLM agent to retrieve relevant chunks for grounded answers.
A Retrieval Augmented Generation system that enables AI assistants to perform semantic searches and manage document indices for markdown files. It supports PostgreSQL with pgvector and integrates both Google Gemini and Ollama for intelligent embedding generation.
Enables semantic search across text documents using vector embeddings stored in PostgreSQL. Provides multiple search modalities including semantic similarity, question/answer, and style-based search through a retrieval-augmented generation system.
Enables semantic search and question-answering over uploaded documents using vector embeddings and Google AI. Supports document organization with tags, section-aware queries, and hierarchical markdown structure preservation.
Enables RAG (Retrieval-Augmented Generation) capabilities with document processing, vector storage, and intelligent Q\&A using OpenAI embeddings and semantic search.