Knowledge resource
Glossary
Clear, citable definitions for Retrieval-Augmented Generation, Swiss data protection, vector databases, BYOK, Azure Switzerland North, and other terms that come up repeatedly in enterprise AI projects. Last updated: April 22, 2026
24 entries · in English.
A
B
C
Chunking
Text chunking · Document segmentation
Chunking is the practice of splitting a document into smaller text segments (chunks) that can be indexed individually and retrieved by a RAG system.
Read definition →Compliance frameworks (ISO 27001, SOC 2)
ISO 27001 · SOC 2 · Information security frameworks
ISO 27001 and SOC 2 are two widely adopted frameworks that define information security, privacy, and control requirements for organizations and are verified through external audits.
Read definition →Context window
Context length
The context window is the maximum number of tokens a large language model can process as input at once — including the system prompt, chat history, and any retrieved documents.
Read definition →
D
E
F
FADP (Swiss Federal Act on Data Protection)
revFADP · nFADP · Swiss Data Protection Act · DSG · revDSG
The FADP is the Swiss Federal Act on Data Protection, in the revised version that has been in force since 1 September 2023 (revFADP, locally known as revDSG).
Read definition →Field-level encryption
Application-layer encryption · Column-level encryption
Field-level encryption encrypts individual database fields at the application layer so that, even with full database access, they remain unreadable without the matching key.
Read definition →Fine-tuning vs. RAG
Fine-tuning · Instruction tuning · RAG vs. fine-tuning
Fine-tuning adjusts an LLM's weights against additional data, while RAG leaves the base model untouched and injects relevant material from an external knowledge base at runtime.
Read definition →
G
H
L
M
MCP (Model Context Protocol)
Model Context Protocol
Model Context Protocol (MCP) is an open protocol that connects language models to external tools, data sources, and services in a standardized way.
Read definition →Multi-tenant SaaS
Multi-tenant architecture
Multi-tenant SaaS refers to a software-as-a-service architecture in which multiple customer organizations (tenants) run on shared infrastructure but remain strictly isolated at the logical layer.
Read definition →
O
P
R
RAG (Retrieval-Augmented Generation)
Retrieval-Augmented Generation · Retrieval Augmented Generation
Retrieval-Augmented Generation (RAG) is an architecture in which a language model retrieves relevant passages from an external knowledge base before answering and uses them as context.
Read definition →Reranking
Re-ranking · Cross-encoder reranking
Reranking is a second search step in RAG pipelines that re-orders an initial set of hits with a more precise model so that the most relevant passages end up at the top.
Read definition →