Search

What are you looking for?

Search our services, use cases and practical insights.

Enter at least 2 characters

Popular starting points

Knowledge, data and RAG

What are embeddings and vector databases?

Embeddings translate content into numerical vectors so a system can search for similar meaning. A vector database stores and searches these representations efficiently.

The short answer

An embedding is a numerical representation of content in which semantically similar items are closer in vector space. A vector database stores these vectors with content and metadata and retrieves similar entries.

In brief

  • Embeddings represent meaning as sequences of numbers; they are not the readable original text.
  • Vector search finds passages with similar meaning even when they use different words.
  • A vector database replaces neither the original source nor permissions and freshness rules.
  • Good retrieval often combines vectors, keywords, metadata filters and subsequent ranking.

How does content become an embedding?

An embedding model receives a passage, image or other supported content and produces a fixed sequence of numbers. The same process is applied to a search query. A similarity measure then compares query and document vectors.

  1. Step 1

    Split content

    Documents are divided into meaningful sections with enough context.

  2. Step 2

    Create vectors

    An embedding model calculates a numerical representation for each section.

  3. Step 3

    Store metadata

    Source, title, version, language and permissions remain attached.

  4. Step 4

    Search by similarity

    The query is embedded and compared with stored vectors.

What does a vector database do?

A vector database or search index optimises search across many high-dimensional vectors. It returns candidates that are semantically related to the query and can constrain them using metadata. The stored original passage is still needed for display and model context.

  • Fast similarity search across large content sets
  • Filters for language, product, validity or user permission
  • A link to the readable original and its location
  • Updates and deletion of vectors when sources change

What determines retrieval quality?

An embedding alone does not create good search. Chunk size, headings, metadata, language and query type all influence results. The three retrieval approaches solve different problems and should be compared on the same real questions.

What determines retrieval quality?
Retrieval approachExampleParticular strengthTypical failure
Keyword search‘Error code E-417’ finds that exact character sequence.Product codes, names, domain terms and exact wordingMisses a passage that expresses the same meaning in different words.
Vector search‘Working abroad’ finds ‘temporary cross-border activity’.Semantically similar questions, paraphrases and natural languageReturns a thematically similar but inapplicable special case.
Hybrid search‘E-417 during an overseas assignment’ combines the code match and semantic context.Weights exact signals and semantic similarity togetherPoor weighting suppresses the exact result or overvalues one keyword.

What are the limits and security concerns?

A vector is not secure anonymisation. It is derived from content and must be protected accordingly. Permissions cannot wait until after retrieval if unauthorised passages have already reached a model. A high similarity score also does not prove factual correctness.

  • Protect embeddings and original content under the same security logic
  • Carry permission metadata into the index and enforce it during retrieval
  • Plan model changes and vector dimensions as migrations
  • Evaluate successful, missing and incorrect retrieval separately
Example from day-to-day business

Example: finding a policy expressed in different words

An employee asks, 'How long may I work abroad?' The policy uses the term 'temporary cross-border activity'. A keyword-only search may miss it; vector search recognises similar meaning. Metadata limits results to the current country and authorised user group. The answer shows the original passage and version date.

What to remember

Use embeddings for semantic search, but keep the original source, metadata and permissions inseparable from every result. Measured retrieval quality matters more than the database type alone.

Sources and further reading

These primary sources provide further detail on definitions, technical foundations or responsible use.

Content reviewed

Would you like to apply this to your situation?

Together, we clarify what makes sense for your process, data and systems – in plain language and without unnecessary complexity.

Discuss Your Project