DeepYardDeepYard
R

RAG-as-a-Service

Hosted RAG platform that serves retrieval-augmented generation as an API

Open SourceFree

About

A production-ready RAG deployment pattern that wraps document ingestion, embedding, retrieval, and generation into a hosted service with API endpoints. Supports document upload, collection management, and query APIs. Demonstrates how to package a RAG pipeline for multi-tenant use with proper isolation, caching, and error handling. Part of the awesome-llm-apps collection.

Details

Patternservice
StepsUpload and index documents via API → Manage collections and embeddings → Query with retrieval-augmented generation → Return structured responses with sources
Use CasesRAG API deployment, Multi-tenant document Q&A, Production RAG infrastructure

Tags

ragapiproductionworkflow