Duaer

Integrations

Use NVIDIA Nemotron Embeddings in Duaer

In Duaer, NVIDIA Nemotron Embeddings is an AI sub-node. Connect it to the Embedding input of a vector store node. Use NVIDIA NeMo Retriever embedding models from build.nvidia.com or a self-hosted NIM.

Connect NVIDIA Nemotron Embeddings in Duaer

  1. On the Duaer canvas, select the Embedding input under a vector store node and pick NVIDIA Nemotron Embeddings.
  2. In Credential to connect with, pick or create a NVIDIA Nemotron credential.
  3. Set Model.
  4. If needed, select Add Option for the optional settings listed below.
  5. Run a vector store node. NVIDIA Nemotron Embeddings runs as part of it, and its calls show under that node in the execution.

NVIDIA Nemotron Embeddings parameters in Duaer

  • Model: The NeMo Retriever embedding model.

NVIDIA Nemotron Embeddings options in Duaer

Under Add Option, NVIDIA Nemotron Embeddings offers Batch Size, Strip New Lines, Dimensions, and Timeout.

Questions

Where does NVIDIA Nemotron Embeddings connect in Duaer?

In Duaer, NVIDIA Nemotron Embeddings connects to the Embedding input of a vector store node. It does not run on its own.

Which credential does NVIDIA Nemotron Embeddings use in Duaer?

Duaer's NVIDIA Nemotron Embeddings uses a NVIDIA Nemotron credential. The secret stays in the credential, not in node parameters.

In this section