Embedders#

Supported Embedder Providers#

NeMo Agent toolkit supports the following embedder providers:

Provider

Type

Description

NVIDIA NIM

nim

NVIDIA Inference Microservice (NIM)

OpenAI

openai

OpenAI API

Embedder Configuration#

The embedder configuration is defined in the embedders section of the workflow configuration file. The _type value refers to the embedder provider, and the model_name value always refers to the name of the model to use.

embedders:
  nim_embedder:
    _type: nim
    model_name: nvidia/nv-embedqa-e5-v5
  openai_embedder:
    _type: openai
    model_name: text-embedding-3-small

NVIDIA NIM#

The NIM embedder provider is defined by the NIMEmbedderModelConfig class.

  • model_name - The name of the model to use

  • api_key - The API key to use for the model

  • base_url - The base URL to use for the model

  • max_retries - The maximum number of retries for the request

  • truncate - The truncation strategy to use for the model

OpenAI#

The OpenAI embedder provider is defined by the OpenAIEmbedderModelConfig class.

  • model_name - The name of the model to use

  • api_key - The API key to use for the model

  • base_url - The base URL to use for the model

  • max_retries - The maximum number of retries for the request