Enables document Q&A and knowledge retrieval through hybrid semantic and keyword search, with tools for document ingestion, chunking, summarization, PII redaction, and RAGAS-based evaluation.
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.
Creates and searches private, local RAG libraries from documentation to ground AI assistants in authoritative sources, reducing hallucinations by providing current, accurate context from your own docs instead of relying on outdated training data.
Enables RAG (Retrieval-Augmented Generation) capabilities with document processing, vector storage, and intelligent Q\&A using OpenAI embeddings and semantic search.
Crawls and indexes documentation websites to Supabase with vector embeddings for RAG, using smart sitemap discovery and Jina AI for fast content extraction with multi-project support.