DeepsetNvidiaNIMTextEmbedder

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

Basic Information

Pipeline type: Query
Type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
Components it most often connects with:
- Query: DeepsetNvidiaDocumentEmbedder receives the query to embed from Query.
- Embedding Retrievers: DeepsetNvidiaDocumentEmbedder can send the embedded query to an Embedding Retriever that uses it to find matching documents.

Inputs

Name	Type	Description
`text`	String	The text to embed.

Outputs

Name	Type	Description
`embedding`	List of floats	The embedding of the text.
`meta`	Dictionary	Metadata regarding the usage statistics.

Overview

NvidiaDocumentEmbedder uses an NVIDIA NIM model to embed a text string, such as a query.

This component runs on models provided by deepset on hardware optimized for performance. Unlike models hosted on platforms like Hugging Face, these models are not downloaded at query time. Instead, you choose a model upfront on the component card.

The optimized models are only available on deepset AI Platform. To run this component on your own hardware, use a sentence transformers embedder instead.

ℹ️
Embedding Models in Query and Indexing Pipelines
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.

Usage Example

This is an example of a DeepsetNvidiaNIMTextEmbedder used in a query pipeline. It receives the text to embed from Query and then 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
      
connections:
  - sender: DeepsetNvidiaNIMTextEmbedder.embedding
    receiver: OpenSearchEmbeddingRetriever.query_embedding
max_runs_per_component: 100

inputs:
  query:
    - DeepsetNvidiaNIMTextEmbedder.text

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Possible values	Description
`model`	DeepsetNVIDIAEmbeddingModels	Default: `NVIDIA_NV_EMBEDQA_E5_V5`	The model to use for calculating embeddings. Choose the model from the list in Builder. Required.
`prefix`	String	Default: `""`	A string to add at the beginning of the string being embedded. Required.
`suffix`	String	Default: `""`	A string to add at the end of the string being embedded. Required.
`truncate`	EmbeddingTruncateMode	`START`, `END`, `NONE` Default: `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. Optional.
`normalize_embeddings`	Boolean	`True` `False` Default: `True`	Whether to normalize the embeddings by dividing the embedding by its L2 norm. Required.
`timeout`	Float	Default: `None`	Timeout for request calls in seconds. Optional.
`backend_kwargs`	Dictionary	Default: `None`	Keyword arguments to further customize model behavior. Optional.

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	Description
`text`	String	The text to embed. Required.

Updated 7 days ago

Basic Information

Inputs

Outputs

Overview

ℹ️Embedding Models in Query and Indexing Pipelines

Usage Example

Parameters

Init Parameters

Run Method Parameters

ℹ️
Embedding Models in Query and Indexing Pipelines