Skip to content
Menu
English

Use case

Semantic search

Find documents by meaning rather than by keyword, so a search for "how do I cancel" finds the page titled "ending your subscription".

See the recommended stack, with reasons and alternatives →

What it takes

In the order you would adopt them. Every step opens in the knowledge graph.

  1. 1 Embedding

    Embedding

    concept

    Dense numeric vector representing the meaning of a piece of text.

  2. 2 Vector database

    Weaviate

    database

    Open-source vector database with hybrid keyword and vector search built in.

  3. 3 Base model

    BERT

    model

    Encoder-only Transformer pre-trained with masked language modelling.

  4. 4 Reranking

    Reranking

    technique

    Second-stage ordering of retrieved candidates by a more accurate scoring model.