Database / Weaviate Vector database Interview questions
What are named vectors in Weaviate?
Named vectors let a single collection define multiple distinct vector fields per object, each with its own vectorizer, index configuration, and compression settings, rather than being limited to exactly one vector per object.
vector_config=[ Configure.Vectors.text2vec_openai(name="title_vector", source_properties=["title"]), Configure.Vectors.text2vec_openai(name="body_vector", source_properties=["body"]), ]
This is useful when different pieces of an object's content genuinely warrant different embeddings, like separately vectorizing a document's title versus its full body text, or combining a text embedding and an image embedding on the same product object, and querying against whichever named vector (or combination) fits a given search's intent. Each named vector's compression is configured independently, so one vector on an object could use RQ compression while another stays uncompressed, based on each one's specific accuracy and memory needs.
More Related questions...
