NvidiaDocumentEmbedder

Embeds documents using NVIDIA models and stores results in each document's embedding field for use in semantic search.

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.

Key Features

• Embeds documents using NVIDIA embedding models, including self-hosted NVIDIA NIM models and NVIDIA API Catalog models.
• Stores computed embeddings in each document's embedding field.
• Configurable batch size (up to 50) for efficient processing of large document collections.
• Optionally embeds metadata fields alongside document text.
• Configurable truncation mode for inputs that exceed the maximum token length.

Configuration

Authentication

Connect Haystack Platform to NVIDIA on the Integrations page. For detailed instructions, see Use NVIDIA Models.

1. Drag the NvidiaDocumentEmbedder component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the name of the NVIDIA embedding model to use, such as nvidia/nv-embedqa-e5-v5.
4. Go to the Advanced tab to configure the API key, API URL, batch size, metadata fields to embed, embedding separator, and truncation mode.

Connections

NvidiaDocumentEmbedder receives a list of documents as input and outputs those documents with embeddings stored in their embedding field, along with a meta dictionary with usage statistics.

Connect DocumentSplitter or another preprocessor to its documents input. Connect its documents output to DocumentWriter to store the embedded documents.

Use the same embedding model in NvidiaTextEmbedder in your query pipeline to ensure consistent results.

Usage Example

In this index, NvidiaDocumentEmbedder receives documents from DocumentSplitter, embeds them, and sends them to DocumentWriter. The index uses the nvidia/nv-embedqa-e5-v5 model, so NvidiaTextEmbedder in the query pipeline must use the same model.

components:
  TextFileToDocument:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8
      store_full_path: false
  DocumentSplitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: word
      split_length: 200
      split_overlap: 0
      split_threshold: 0
      splitting_function:
  NvidiaDocumentEmbedder:
    type: haystack_integrations.components.embedders.nvidia.document_embedder.NvidiaDocumentEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - NVIDIA_API_KEY
        strict: true
      model: nvidia/nv-embedqa-e5-v5
      api_url: https://integrate.api.nvidia.com/v1
      prefix: ''
      suffix: ''
      batch_size: 32
      progress_bar: true
      meta_fields_to_embed:
      embedding_separator: "\n"
      truncate:
      timeout:
  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: nvidia-embeddings-index
          max_chunk_bytes: 104857600
          embedding_dim: 1024
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
          similarity: cosine
      policy: NONE

connections:
- sender: TextFileToDocument.documents
  receiver: DocumentSplitter.documents
- sender: DocumentSplitter.documents
  receiver: NvidiaDocumentEmbedder.documents
- sender: NvidiaDocumentEmbedder.documents
  receiver: DocumentWriter.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - TextFileToDocument.sources

Parameters

Inputs

Parameter	Type	Default	Description
documents	List[Document]		A list of Documents to embed.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		Documents with their embeddings added to the embedding field.
meta	Dict[str, Any]		Metadata related to the embedding process, including usage statistics.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	Optional[str]	None	Embedding model to use. If no specific model along with locally hosted API URL is provided, the system defaults to the available model found using /models API.
api_key	Optional[Secret]	Secret.from_env_var('NVIDIA_API_KEY')	API key for the NVIDIA NIM.
api_url	str	os.getenv('NVIDIA_API_URL', DEFAULT_API_URL)	Custom API URL for the NVIDIA NIM. Format for API URL is http://host:port
prefix	str		A string to add to the beginning of each text.
suffix	str		A string to add to the end of each text.
batch_size	int	32	Number of Documents to encode at once. Cannot be greater than 50.
progress_bar	bool	True	Whether to show a progress bar or not.
meta_fields_to_embed	Optional[List[str]]	None	List of meta fields that should be embedded along with the Document text.
embedding_separator	str	\n	Separator used to concatenate the meta fields to the Document text.
truncate	Optional[Union[EmbeddingTruncateMode, str]]	None	Specifies how inputs longer than the maximum token length should be truncated. If None the behavior is model-dependent, see the official documentation for more information.
timeout	Optional[float]	None	Timeout for request calls, if not set it is inferred from the NVIDIA_TIMEOUT environment variable or set to 60 by default.

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
documents	List[Document]		A list of Documents to embed.