Software:Weaviate

Weaviate

Original author(s)	Bob van Luijt
Developer(s)	SeMI Technologies
Initial release	May 21, 2019 (2019-05-21)
Repository	https://github.com/semi-technologies/weaviate
Written in	Go, C++
Operating system	Cross-platform
Type	Knowledge engine, Knowledge graph, Search and index
License	BSD-3, Weaviate Enterprice (commercial)
Website	https://www.semi.technology/

Weaviate is an open source knowledge graph based on a vector storage mechanism called the contextionary. It allows a user to search for context or keywords in a dataset rather than fixed keywords alone. It provides a GraphQL interface to query the knowledge graph and an HTTP web interface to add the data via an ontology schema.

Contextionary

The contextionary (c11y) is the knowledge engine at the core of Weaviate. Conceptually it is a form of word embeddings. From every data object added to Weaviate, a new point in the vector space is created giving the data a unique, semantic meaning. When querying Weaviate, known as exploring, one can target data-objects directly or based on contextual and semantic search. For example, a City with the name Amsterdam can be found by targeting place, Netherlands, canals, Rembrandt.

Ontology & Concepts

Weaviate defines things and actions which are called concepts where things often consist of nouns and actions consist of verbs. Weaviate's ontology-schema is class-based and determines the semantic meaning of the concepts. For example, a class Animal with the name-property Seal translates into a weighted centroid representing a Seal.

# Example of a Weaviate ontology in YAML
class: Zoo
keywords:
- keyword: park
  weight: 0.7
- keyword: animals
  weight: 0.7
description: Animal park
properties:
- dataType:
  - string
  cardinality: atMostOne
  description: Name of the Zoo
  name: name
  keywords:
  - keyword: identifier
    weight: 0.8

GraphQL interface

Weaviate exposes the complete knowledge graph through a GraphQL API-interface. The interface allows targeting individual concepts directly or through identifiers inside the vector space called beacons.

{
  Local {
    Explore {
      Concepts(keywords: ["fins", "marine", "mammal"]) {
        beacon
        className
      }
    }
    Get {
      Things {
        Animal {
          name
          age
          InZoo {
            ... on Zoo {
              name
            }
          }
        }
      }
    }
  }
}

Open Source Contextionary

The open source contextionary is based on WikiPedia and the Wiktionary but can also be created based on custom documents such as scientific journals or legal documents.