Retrieval, RAG & Knowledge
Explain how enterprise AI systems locate, rank, validate and authorize knowledge.
Why This Matters
Enterprise answers are only as trustworthy as the retrieval path that produced them. Ranking, provenance, and access control are architecture problems, not prompt tricks.
Architecture Position
Retrieval is the Knowledge Layer: it feeds context assembly and must respect Trust Layer authorization before a model ever sees a chunk. See it on the architecture map.
Start Here
Core Concepts
Retrieval Foundations
- Semantic search
- Keyword search
- Embeddings
- Vector databases
Retrieval Strategies
- BM25
- Hybrid retrieval
- Reranking
- Metadata filtering
- Query rewriting
- Query decomposition
RAG
- Basic RAG
- Advanced RAG
- Agentic RAG
- Multi-stage retrieval
- GraphRAG
Data Pipelines
- Ingestion
- Chunking
- Indexing
- Refresh
- Document processing
Enterprise Retrieval
- Access-aware retrieval
- Permission-aware RAG
- Data residency
- Provenance
- Citations
Evaluation
- Retrieval precision
- Recall
- Groundedness
- RAG evaluation
Advanced
- Knowledge graphs
- Deterministic retrieval
- Retrieval planning
Advanced
Advanced material
Deeper guides for this domain are on the way.
Coming SoonArchitecture Patterns
Applied patterns for this domain live in the pattern library.
Browse architecture patternsCase Studies
Enterprise walkthroughs that apply this topic in a full system.
Browse case studiesRelated Topics
Context Engineering
How information is assembled, prioritized, and supplied to models and agents.
Open →Models, Reasoning & Inference
How modern AI models operate and what system architects need to understand about them.
Open →Identity & Authorization
How humans, agents, and workloads establish identity and receive authority to act.
Open →AI Security & Trust
Threats created by probabilistic systems that retrieve data and take actions.
Open →Roadmaps
This topic appears in the Enterprise AI Architect path.
Follow the Enterprise AI Architect roadmap