RAG resources

Three resources that build a retrieval-augmented generation (RAG) pipeline. Each has its own reference page.

Works in workflow and agent mode.

load_document (load + chunk)  ->  embedding or vector_store component (index)  ->  embedding or vector_store component (search)  ->  chat (answer with context)

Resource	Role	Reference
component: load_document	Read files, URLs, or a directory into text chunks	Loader
component: embedding	Local SQLite keyword store - index and search, no API key	Embedding
component: vector_store	External vector database - Qdrant, Chroma, pgvector, ...	Vector store

embedding or vector store

	component: embedding	component: vector_store
Storage	Local SQLite file	External vector DB service
Matching	Keyword (LIKE)	Vector similarity
Setup	None	Run and configure the DB
API key	Not needed	Needed for the embedding model
Best for	On-prem, small corpora	Production scale, semantic ranking

See also

• Document search tutorial - component: embedding upsert and search
• Search resources - keyword file and web search
• LLM resource - answer with the retrieved context
• Resources overview - all resource types