Optional
endpointURL?: stringThe endpoint URL to use.
Optional
model?: stringThe model to use.
Optional
passageThe model to use for passage vectorization.
Optional
queryThe model to use for query vectorization.
Optional
useWhether to use the cache.
Optional
useGPU?: booleanWhether to use the GPU.
Optional
vectorizeWhether to vectorize the collection name.
Optional
waitWhether to wait for the model.
The configuration for text vectorization using the HuggingFace module.
See the documentation for detailed usage.