Vector database
A vector database stores and searches vector representations. A similar match is not automatically a valid or permitted answer source.
A vector database stores vector representations and supports searching for similar entries. Vectors can be linked to documents or other content and additional metadata. Vector search can also be part of an existing database.
A document search example
A hypothetical assistant searches work instructions for passages relevant to a question. Document references and version information are needed alongside vectors to keep results traceable.
The result alone does not show whether a passage remains valid or the person may read it. Updates and access rules must cover the whole flow. A separate additional database is therefore not automatically necessary; architecture follows the data, search needs and operational requirements.
Sources
Related terms
- EmbeddingAn embedding represents content as a numeric vector. The model and comparison method determine which similarities become visible.
- Retrieval-augmented generationRAG combines information retrieval with generated answers. Access to sources does not remove the need for quality and permission design.
- Role-based access controlRBAC connects permissions to roles and assigns people to those roles. The data scope must be clear alongside the role name.
- Model cardA model card documents an AI model’s purpose, foundations, evaluation conditions and known limitations for a particular version.
- AI readinessAI readiness concerns the foundations of an AI project: objectives, usable data, skills, responsibilities and an operating workflow.
- Context engineeringContext engineering prepares information for individual model calls: relevant instructions, messages, sources and current states.
Articles on this topic
AI & Automation with ASES
AI assistants and automated workflows