Retrievers & Vectorizers
This section includes reference guides for retriever & vectorizer modules. As their names suggest,
XXX2vec modules are configured to produce a vector for each object.
text2vecconverts text data
img2vecconverts image data
multi2vecconverts image or text data (into the same embedding space)
ref2vecconverts cross-reference data (from within Weaviate)
Weaviate generates vector embeddings at the object level (rather than for individual properties). For instance
text2vec-* modules can generate vectors from text objects. To produce the string to be vectorized from each object, Weaviate follows the schema configuration for the relevant class.
Unless specified otherwise in the schema, the default behavior is to:
- Only vectorize properties that use the
textdata type (unless skipped)
- Sort properties in alphabetical (a-z) order before concatenating values
- Prepend the property name to each property value (unless
vectorizePropertyNameis false) then join them with spaces, and
- Prepend the class name (unless
- Convert the produced string to lowercase
Vector inference at object update
Where Weaviate is configured with a vectorizer, it will only obtain a new vector if an object update changes the underlying text to be vectorized.