DeepsetNvidiaNIMTextEmbedder

Embed strings of text using embedding models by NVIDIA NIM on optimized hardware.

Key Features

• Embeds text strings (typically queries) using NVIDIA NIM models running on hardware optimized for performance by deepset.
• Unlike models hosted on platforms like Hugging Face, these models are not downloaded at query time — you choose a model upfront on the component card.
• The optimized models are only available on Haystack Enterprise Platform. To run this component on your own hardware, use a sentence transformers embedder instead.
• Use in query pipelines to transform a query into a vector for semantic search.
• Configurable truncation and normalization.

Embedding Models in Query Pipelines and Indexes

The embedding model you use to embed documents in your indexing pipeline must be the same as the embedding model you use to embed the query in your query pipeline.

This means the embedders for your indexing and query pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

Configuration

1. Drag the DeepsetNvidiaNIMTextEmbedder component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Select the NVIDIA NIM embedding model from the list on the component card.
4. Go to the Advanced tab to configure prefix, suffix, truncate, normalize_embeddings, timeout, and backend_kwargs.

Connections

DeepsetNvidiaNIMTextEmbedder accepts a text string through its text input. It outputs the embedding as a list of floats through its embedding output, plus usage metadata through its meta output.

Connect the Input component's query output to DeepsetNvidiaNIMTextEmbedder's text input. Then connect DeepsetNvidiaNIMTextEmbedder's embedding output to an embedding retriever's query_embedding input.

Usage Examples

Basic Configuration

  DeepsetNvidiaNIMTextEmbedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.nim_text_embedder.DeepsetNvidiaNIMTextEmbedder
    init_parameters:
      model: nvidia/nv-embedqa-e5-v5
      prefix: ''
      suffix: ''
      normalize_embeddings: true

This is an example of a DeepsetNvidiaNIMTextEmbedder used in a query pipeline. It receives the text to embed from Input and sends the embedded query to OpenSearchEmbeddingRetriever:

Here's the YAML configuration:

components:
  DeepsetNvidiaNIMTextEmbedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.nim_text_embedder.DeepsetNvidiaNIMTextEmbedder
    init_parameters:
      model: nvidia/nv-embedqa-e5-v5
      prefix: ''
      suffix: ''
      normalize_embeddings: true

  retriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: default
      top_k: 10

connections:
  - sender: DeepsetNvidiaNIMTextEmbedder.embedding
    receiver: retriever.query_embedding
max_runs_per_component: 100

inputs:
  query:
    - DeepsetNvidiaNIMTextEmbedder.text

outputs:
  documents: retriever.documents

Parameters

Inputs

Parameter	Type	Description
text	str	The text to embed.

Outputs

Parameter	Type	Description
embedding	List[float]	Embedding of the text.
meta	Dict[str, Any]	Metadata on usage statistics.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	DeepsetNvidiaNIMEmbeddingModels	DeepsetNvidiaNIMEmbeddingModels.NVIDIA_NV_EMBEDQA_E5_V5	The model to use for calculating embeddings. Choose a model from the list on the component card.
prefix	str		A string to add at the beginning of the string being embedded. Can be used to prepend the text with an instruction, as required by some embedding models, such as E5 and bge.
suffix	str		A string to add at the end of the string being embedded.
truncate	Optional[EmbeddingTruncateMode]	None	Specifies how to truncate inputs longer than the maximum token length. Possible options are: START, END, NONE. If set to START, the input is truncated from the start. If set to END, the input is truncated from the end. If set to NONE, returns an error if the input is too long.
normalize_embeddings	bool	True	Whether to normalize the embeddings. Normalization is done by dividing the embedding by its L2 norm.
timeout	Optional[float]	None	Timeout for request calls in seconds.
backend_kwargs	Optional[Dict[str, Any]]	None	Keyword arguments to further customize model behavior.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
text	str		The text to embed.