Module rag 

Retrieval-Augmented Generation pipeline. Retrieval-Augmented Generation (RAG) pipeline for knowledge base search.

Provides document ingestion (chunking + embedding + storage) and context-aware retrieval for LLM injection.

Main types

• RagPipeline — Orchestrates ingestion and retrieval.
• Document — A document to ingest into the knowledge base.
• DocumentChunk — A chunk of a document after splitting.
• ChunkingStrategy — How to split documents into chunks.
• RagConfig — Pipeline configuration.
• RagResult — Query result containing scored chunks and formatted context.
• ScoredChunk — A chunk paired with its relevance score.

Structs

Document

A document to ingest into the RAG knowledge base.

DocumentChunk

A chunk produced by splitting a Document.

RagConfig

Configuration for the RAG pipeline.

RagPipeline

Retrieval-Augmented Generation pipeline.

RagResult

Result of a RAG query.

ScoredChunk

A scored chunk returned by the RAG query.

Enums

ChunkingStrategy

Strategy for splitting documents into chunks.