SIMHEAD Blog by Peter Kim

Posts

Vector Databases

July 08, 2026

Vector Databases Vector Databases Vector databases store and search embeddings for semantic retrieval, memory, clustering, and hybrid search. Full series Previous: Retrieval-Augmented Generation Next: Workflow Automation Orchestration Introduction Vector Databases is presented here as an architecture concept inside an LLM-maintained Obsidian wiki, not as an isolated glossary definition. Vector databases store and search embeddings for semantic retrieval, memory, clustering, and hybrid search. The article introduces the concept by explaining what role it plays in an AI system, which neighboring layers it influences, and how a reader should recognize the concept when evaluating a real implementation. The key terms for this page are vector, search, databases, retrieval, embeddings, memory, and they point to the decisions the reader will usually need to make: where the boundary sits, what data or control flow passes through...

Retrieval-Augmented Generation

July 08, 2026

Retrieval-Augmented Generation Retrieval-Augmented Generation RAG grounds model responses in retrieved external knowledge to improve factuality, freshness, and source traceability. Full series Previous: Model Context Protocol Next: Vector Databases Introduction Retrieval-Augmented Generation is presented here as an architecture concept inside an LLM-maintained Obsidian wiki, not as an isolated glossary definition. RAG grounds model responses in retrieved external knowledge to improve factuality, freshness, and source traceability. The article introduces the concept by explaining what role it plays in an AI system, which neighboring layers it influences, and how a reader should recognize the concept when evaluating a real implementation. The key terms for this page are generation, model, graphrag, knowledge, retrieval, retrieval-augmented, and they point to the decisions the reader will usually need to make: where the bo...

Model Context Protocol

July 08, 2026

Model Context Protocol Model Context Protocol MCP standardizes how AI applications connect to tools, data sources, and local or remote environments. Full series Previous: Foundation Models Next: Retrieval-Augmented Generation Introduction Model Context Protocol is presented here as an architecture concept inside an LLM-maintained Obsidian wiki, not as an isolated glossary definition. MCP standardizes how AI applications connect to tools, data sources, and local or remote environments. The article introduces the concept by explaining what role it plays in an AI system, which neighboring layers it influences, and how a reader should recognize the concept when evaluating a real implementation. The key terms for this page are servers, tools, protocol, agent, context, local, and they point to the decisions the reader will usually need to make: where the boundary sits, what data or control flow passes through it, what has to ...

Foundation Models

July 08, 2026

Foundation Models Foundation Models Foundation models provide the base language, reasoning, coding, and multimodal capabilities used by higher AI stack layers. Full series Previous: Embedding Layer Next: Model Context Protocol Introduction Foundation Models is presented here as an architecture concept inside an LLM-maintained Obsidian wiki, not as an isolated glossary definition. Foundation models provide the base language, reasoning, coding, and multimodal capabilities used by higher AI stack layers. The article introduces the concept by explaining what role it plays in an AI system, which neighboring layers it influences, and how a reader should recognize the concept when evaluating a real implementation. The key terms for this page are model, foundation, coding, inference, local, and they point to the decisions the reader will usually need to make: where the boundary sits, what data or control flow passes through it,...

Embedding Layer

July 08, 2026

Embedding Layer Embedding Layer The embedding layer converts content into dense vectors for semantic search, clustering, ranking, and memory. Full series Previous: AI Security Guardrails Governance Next: Foundation Models Introduction Embedding Layer is presented here as an architecture concept inside an LLM-maintained Obsidian wiki, not as an isolated glossary definition. The embedding layer converts content into dense vectors for semantic search, clustering, ranking, and memory. The article introduces the concept by explaining what role it plays in an AI system, which neighboring layers it influences, and how a reader should recognize the concept when evaluating a real implementation. The key terms for this page are embedding, layer, content, retrieval, search, and they point to the decisions the reader will usually need to make: where the boundary sits, what data or control flow passes through it, what has to be meas...

AI Ecosystem KB

July 08, 2026

AI Ecosystem KB AI Ecosystem KB Seed reference map for the modern AI ecosystem, organized by stack layer and connected to concept/entity pages. Full series Previous: AI Ecosystem Coverage Plan Next: Agent Development Tools Inventory Introduction AI Ecosystem KB is a reference page in the LLM Wiki, so it is designed to preserve source-backed facts, scope decisions, and maintenance cues that other articles can depend on. Seed reference map for the modern AI ecosystem, organized by stack layer and connected to concept/entity pages. The introduction explains what the reference covers, why it belongs in a durable wiki page, and how readers should use it when updating or validating the broader AI ecosystem map. Reference pages are most valuable when they make their boundaries visible. The terms https, docs, documentation, microsoft, models, embeddings describe the evidence and classification surface for this page, while the b...