GoogleGenAIDocumentEmbedder

Compute document embeddings using Google AI models.

Key Features

• Computes embeddings for documents using Google AI embedding models.
• Supports both the Gemini Developer API and Vertex AI through a single component.
• Stores embeddings in the embedding field of each document.
• Configurable batch size and progress bar for large document sets.
• Supports metadata field embedding alongside document text.

Configuration

Authentication

Gemini Developer API: Create a secret with your Google API key. Use GOOGLE_API_KEY or GEMINI_API_KEY as the secret key. Get your API key from Google AI Studio.

Vertex AI: Create secrets for GCP_PROJECT_ID and GCP_DEFAULT_REGION, or use Application Default Credentials.

For detailed instructions on creating secrets, see Create Secrets.

1. Drag the GoogleGenAIDocumentEmbedder 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 model name (for example, text-embedding-004). For supported models, see the Google AI documentation.
4. Go to the Advanced tab to configure the API type, API key, Vertex AI project and location, prefix, suffix, batch size, progress bar, metadata fields to embed, embedding separator, and config.

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.

Connections

GoogleGenAIDocumentEmbedder accepts a list of Document objects as input (documents). It outputs a list of documents with embeddings (documents) and usage metadata (meta).

In an index pipeline, connect a converter or DocumentSplitter to the documents input, then connect the documents output to DocumentWriter for storage.

Usage Example

This index uses GoogleGenAIDocumentEmbedder to embed documents before storing them:

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: sentence
      split_length: 5
      split_overlap: 1

  GoogleGenAIDocumentEmbedder:
    type: haystack_integrations.components.embedders.google_genai.document_embedder.GoogleGenAIDocumentEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
          - GOOGLE_API_KEY
          - GEMINI_API_KEY
        strict: false
      api: gemini
      vertex_ai_project:
      vertex_ai_location:
      model: text-embedding-004
      prefix: ""
      suffix: ""
      batch_size: 32
      progress_bar: true
      meta_fields_to_embed:
      embedding_separator: "\n"
      config:

  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: 'google-embeddings'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      policy: OVERWRITE

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

inputs:
  files:
    - TextFileToDocument.sources

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

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

Outputs

Parameter	Type	Default	Description
documents	List[Document]		A list of documents with embeddings.
meta	Dict[str, Any]		Information about the usage of the model.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var(['GOOGLE_API_KEY', 'GEMINI_API_KEY'], strict=False)	Google API key. Not needed if using Vertex AI with Application Default Credentials.
api	Literal['gemini', 'vertex']	gemini	Which API to use. Either "gemini" for the Gemini Developer API or "vertex" for Vertex AI.
vertex_ai_project	Optional[str]	None	Google Cloud project ID for Vertex AI. Required when using Vertex AI with Application Default Credentials.
vertex_ai_location	Optional[str]	None	Google Cloud location for Vertex AI (for example, "us-central1", "europe-west1"). Required when using Vertex AI with Application Default Credentials.
model	str	text-embedding-004	The name of the model to use for calculating embeddings.
prefix	str	""	A string to add at the beginning of each text.
suffix	str	""	A string to add at the end of each text.
batch_size	int	32	Number of documents to embed at once.
progress_bar	bool	True	If True, shows a progress bar when running.
meta_fields_to_embed	Optional[List[str]]	None	List of metadata fields to embed along with the document text.
embedding_separator	str	\n	Separator used to concatenate the metadata fields to the document text.
config	Optional[Dict[str, Any]]	None	A dictionary to configure embedding content configuration. Defaults to {"task_type": "SEMANTIC_SIMILARITY"}. See Google AI Task types.

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.