Skip to content
New

EDDI v6.0.0-RC1 is now available for developer preview! Get started

Get Started

RAG — Retrieval-Augmented Generation

7 embedding providers, 5 vector stores, httpCall RAG, and async document ingestion — enterprise-grade knowledge retrieval for AI agents.

RAG — Retrieval-Augmented Generation

Enterprise Knowledge Retrieval

EDDI provides a complete Retrieval-Augmented Generation pipeline with native support for multiple embedding providers, vector stores, and a zero-infrastructure RAG option via HTTP calls.

RAG Capabilities

Flexible Deployment

RAG is fully configuration-driven. Choose your embedding provider and vector store via JSON configuration — no code changes needed. The httpCall RAG option lets you use any existing search infrastructure (Elasticsearch, Solr, custom APIs) without deploying a separate vector database.