Embedders#
Supported Embedder Providers#
NeMo Agent toolkit supports the following embedder providers:
Provider |
Type |
Description |
---|---|---|
|
NVIDIA Inference Microservice (NIM) |
|
|
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 useapi_key
- The API key to use for the modelbase_url
- The base URL to use for the modelmax_retries
- The maximum number of retries for the requesttruncate
- 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 useapi_key
- The API key to use for the modelbase_url
- The base URL to use for the modelmax_retries
- The maximum number of retries for the request