Weaviate is completely modularized. The Core of Weaviate, without any modules attached, is a pure vector-native database and search engine. Data is stored as vectors, and these vectors are searchable by the provide vector index (ANN) algorithm. The functionality of the vector-native database can be enriched by modules. One or more modules can be attached, for example to vectorize data or other functionalities like question answering.
Vectorization modules, like the
text2vec-transformers, transform data into vectors. Depending on the type of data you want to store and search (text, images, etc), and depending on the use case domain (science, healthcare, common daily language, etc), you can choose and attach a module that best fits your use case.
Note: at the moment, text vectorization modules cannot be combined in a single setup. This means that you can either enable the
text2vec-transformers or no text vectorization module.
Modules with additional functionalities
Modules can also add a certain functionality to Weaviate. For example, the
qna-transformers module adds a question answering feature, which can be used to query data using GraphQL.
Custom modules will soon be supported, more information can be found here. Stay tuned!
Modules can be dependent on other modules to be present. For example, to use the
qna-transformers module, exacly one text vectorization module is required.
This graphic shows the available modules of the latest Weaviate version (v1.15.2).
Modules can be “vectorizers” (defines how the numbers in the vectors are chosen from the data) or other modules providing additional functions like question answering, custom classification, etc. Modules have the following characteristics:
- Naming convention:
<media>2vec-<name>-<optional>, for example
- Other modules:
<functionality>-<name>-<optional>, for example
- A module name must be url-safe, meaning it must not contain any characters which would require url-encoding.
- A module name is not case-sensitive.
text2vec-bertwould be the same module as
- Module information is accessible through the
- General module information (which modules are attached, version, etc.) is accessible through Weaviate’s
- Modules can add
additionalproperties in the RESTful API and
_additionalproperties in the GraphQL API.
- A module can add filters in GraphQL queries.
- Which vectorizer and other modules are applied to which data classes is configured in the schema.
If you can’t find the answer to your question here, please look at the: