| Name | Type | Description |
|---|---|---|
model* | str | Model name |
nomic_api_key | str | None | Default: NoneOptionally, set the Nomic API key. Uses the |
dimensionality | int | None | Default: NoneThe embedding dimension, for use with Matryoshka-capable models. Defaults to full-size. |
inference_mode | str | Default: 'remote' |
device | str | None | Default: None |
vision_model | str | None | Default: None |
NomicEmbeddings embedding model.
Example:
from langchain_nomic import NomicEmbeddings
model = NomicEmbeddings()How to generate embeddings. One of 'remote', 'local'
(Embed4All), or 'dynamic' (automatic).
The device to use for local embeddings. Choices include
'cpu', 'gpu', 'nvidia', 'amd', or a specific device
name. See the docstring for GPT4All.__init__ for more info.
Typically defaults to 'cpu'.
Do not use on macOS.
The vision model to use for image embeddings.