Introduction

RAGSpine is a backend RAG engine you assemble in plain Python — not a framework you submit to. No Dify, no LangGraph, no graph DSL, no bundled UI. Just a coherent, batteries-included library of composable parts — retrieval, agent orchestration, document extraction, evaluation, and an HTTP service layer — wired together by ordinary functions and typed Protocols. The core imports zero SDKs and runs fully offline with a deterministic MockProvider.

It was built for a demanding use case (executive insight Q&A over financial and operational reports) and ships that rigor as first-class, code-enforced invariants:

• Never fabricate. When the data isn't there, the orchestrator deterministically refuses ("not found") regardless of what the LLM says — anti-fabrication lives in the control flow, not in a prompt you hope the model obeys.
• Always cite. Every answer carries source lineage (document + locator).
• Two channels, one router. A deterministic structured / numeric channel answers "what's the number," a narrative RAG channel answers "why / what happened," and an agent routes each question — or splits a composite one and runs both.
• Everything is pluggable. LLM, embeddings, reranker, OCR, retriever, task queue — all typed Protocols injected at the edges.

Start here

Explore the domains

The engine is organized by domain — find the file by folder before you read its name. Each has a focused guide: