← Back to Glossary
Knowledge Base / Corpus
Phase 03 · RAGcore-concept

The complete collection of raw documents, PDFs, manuals, and data files indexed by a RAG system.

Why it exists

Serves as the single source of truth that grounds your AI system's domain knowledge.

How it works

Ingestion pipelines parse new files, split text into chunks, generate embeddings, and update vector indexes.

Where you'll use this