nemoguardrails.embeddings.providers.nim

Module Contents

Name	Description
`NIMEmbeddingModel`	Embedding model using langchain-nvidia-ai-endpoints.
`NVIDIAAIEndpointsEmbeddingModel`	A wrapper with a different name for the NIM embedding models.

class nemoguardrails.embeddings.providers.nim.NIMEmbeddingModel(
    embedding_model: str,
    kwargs = {}
)

Bases: EmbeddingModel

Embedding model using langchain-nvidia-ai-endpoints.

This class is a wrapper for using embedding models powered by NIM (hosted in the NVIDIA API Catalog or locally).

Parameters:

embedding_model

str

The name embedding model to be used.

document_embedder

= NVIDIAEmbeddings(model=embedding_model, **kwargs)

engine_name

= 'nim'

nemoguardrails.embeddings.providers.nim.NIMEmbeddingModel.encode(
    documents: typing.List[str]
) -> typing.List[typing.List[float]]

Encode a list of documents into their corresponding sentence embeddings.

Parameters:

documents

List[str]

The list of documents to be encoded.

Returns: List[List[float]]

List[List[float]]: The list of sentence embeddings, where each embedding is a list of floats.

nemoguardrails.embeddings.providers.nim.NIMEmbeddingModel.encode_async(
    documents: typing.List[str]
) -> typing.List[typing.List[float]]

async

Encode a list of documents into their corresponding sentence embeddings.

Parameters:

documents

List[str]

The list of documents to be encoded.

Returns: List[List[float]]

List[List[float]]: The list of sentence embeddings, where each embedding is a list of floats.

class nemoguardrails.embeddings.providers.nim.NVIDIAAIEndpointsEmbeddingModel()

Bases: NIMEmbeddingModel

A wrapper with a different name for the NIM embedding models.

There will be a better separation in the future between local NIM and NVIDIA AI Endpoints.

engine_name

= 'nvidia_ai_endpoints'