Optional
baseURL?: stringThe base URL where API requests should go.
Optional
imageThe image fields used when vectorizing.
Optional
model?: stringThe model to use. Defaults to None
, which uses the server-defined default.
Optional
output_Format in which the embeddings are encoded. Defaults to None
, so the embeddings are represented as a list of floating-point numbers.
Optional
textThe text fields used when vectorizing.
Optional
truncation?: booleanWhether to apply truncation.
Optional
weights?: { The weights of the fields used for vectorization.
Optional
imageThe weights of the image fields.
Optional
textThe weights of the text fields.
The configuration for multi-media vectorization using the NVIDIA module.
See the documentation for detailed usage.