RAG vs Wiki Pattern

Fundamental comparison between traditional Retrieval-Augmented Generation (RAG) systems and andrej-karpathy's llm-wiki-pattern, highlighting different approaches to knowledge management and query answering.

Traditional RAG Approach

Process Flow

1. Upload collection of files
2. Chunk and embed documents
3. At query time: retrieve relevant chunks
4. Generate answer from retrieved fragments
5. Repeat process for each new query

Characteristics

• Stateless: Each query starts fresh
• Rediscovery: Knowledge reconstructed every time
• Fragment-based: Works with document chunks, not integrated knowledge
• No accumulation: Understanding doesn't build over time
• Limited synthesis: Difficult to connect insights across multiple documents

Examples

• NotebookLM
• ChatGPT file uploads
• Most commercial RAG systems
• Document Q&A tools

LLM Wiki Pattern Approach

Process Flow

1. Ingest sources into persistent wiki structure
2. LLM builds and maintains cross-referenced knowledge base
3. At query time: synthesize from existing wiki pages
4. File valuable answers back as new wiki content
5. Knowledge compounds with each interaction

Characteristics

• Stateful: Persistent knowledge accumulation
• Pre-synthesized: Understanding built incrementally over time
• Integration-based: Works with structured, cross-referenced content
• Compounding: Each addition makes the whole more valuable
• Rich synthesis: Connections already established across sources

Key Differences

Aspect	Traditional RAG	Wiki Pattern
Knowledge State	Stateless retrieval	Persistent accumulation
Processing Time	Query-time discovery	Ingest-time integration
Cross-reference	Ad-hoc during query	Pre-established and maintained
Contradictions	Discovered per query	Flagged and tracked systematically
Synthesis Quality	Limited by retrieval	Rich, pre-built connections
Maintenance	None (static chunks)	Automated wiki maintenance

When to Use Each

RAG Works Well For

• Simple document Q&A
• One-off queries against large document sets
• When you don't need knowledge to compound
• Rapid deployment without setup overhead
• Documents that rarely need cross-referencing

Wiki Pattern Works Well For

• Long-term knowledge building
• Complex synthesis across multiple sources
• Research that builds over time
• When contradictions and evolution matter
• Domains where connections between concepts are valuable

Hybrid Approaches

Some systems might combine both patterns:

• Wiki pattern for core, frequently-accessed knowledge
• RAG for supplementary document collections
• Different layers for different types of content

Performance Implications

RAG

• Pros: Simple setup, works immediately, scales to large document sets
• Cons: Repeated processing overhead, limited synthesis depth, no knowledge accumulation

Wiki Pattern

• Pros: Rich synthesis, compounding value, deep cross-references, maintained consistency
• Cons: Higher setup cost, requires ongoing LLM maintenance, more complex architecture

See also

• llm-wiki-pattern
• andrej-karpathy
• retrieval-augmented-generation
• persistent-learning
• compounding-artifacts