Versatile AI Risk Assessment

Glossary Systems and architecture

Embeddings

Numerical vectors that represent content for similarity searches.

As of: September 2026 · Glossary with 46 terms

What is Embeddings?

An embedding model converts content such as a text passage into a numerical vector. A RAG application can use these vectors to find passages related to a question. Vector similarity is neither proof of truth nor permission to access the content.

Embeddings can contain information about their source data. Do not automatically treat them as anonymous; include their storage, access and deletion in the data review.

Sources for context: OWASP LLM08:2025

EmbeddingVector searchRAG

Threats using this term (1)

Entries in the threat catalogue whose text uses the term. Every link leads to the full threat page.

Cross-Tenant Leakage (Multi-Tenant Vector DB) On AI platforms that serve several customers on shared infrastructure, one customer's data can surface in another customer's answers when …

More terms from the subject area Systems and architecture.

GPAI and systemic risk Foundation models for many tasks, with their own duties and a separate tier for systemic risk. Agentic system (agentic AI) A system that uses a language model to carry out multi-step tasks on its own. Multi-agent system Several agents share a task and call each other.

From the term into the substance

The link leads to the place on the website where the term becomes practical; the overview shows every term in the glossary by subject area.

Explore in the use case or review tool All terms in the glossary

Cite this term

For reports, policies or internal documents; the link leads directly to this term page.

“Embeddings”. Versatile AI Risk Assessment, glossary of AI risk analysis, as of September 2026.
https://www.versatile-ai-risk-assessment.com/en/wissensbasis/glossary/embeddings/

← Back to the glossary