Database / Weaviate Vector database Interview questions
What is a vectorizer module in Weaviate?
A vectorizer module is a pluggable component that automatically converts an object's text (or image, or other supported data) into a vector embedding, at both insert time and query time, by calling out to an embedding provider or model. Configuring one on a collection means the application can work directly with raw text and let Weaviate handle producing and storing the corresponding vector.
Configure.Vectors.text2vec_openai() # OpenAI embeddings Configure.Vectors.text2vec_cohere() # Cohere embeddings Configure.Vectors.text2vec_huggingface() # Hugging Face models Configure.Vectors.multi2vec_clip() # multimodal (text + image) via CLIP
Alternatively, a collection can be configured with no vectorizer at all (none), in which case the application is responsible for computing and supplying its own vectors on every insert and query, which is the right choice when embeddings are already produced elsewhere in a pipeline or when a specific embedding model isn't available as a built-in Weaviate module.
More Related questions...
