WatsonxTextEmbedder

Embed strings using IBM watsonx.ai embedding models. Use this component in query pipelines to transform user queries into vectors for embedding-based retrieval.

Key Features

• Uses IBM watsonx.ai embedding models such as ibm/slate-30m-english-rtrvr-v2.
• Outputs a float vector embedding suitable for use with embedding retrievers.
• The embedding model must match the one used by WatsonxDocumentEmbedder in the indexing pipeline.

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 WatsonxTextEmbedder component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Set the model to the same watsonx.ai embedding model used in your indexing pipeline.
   2. Create secrets for your watsonx.ai credentials: WATSONX_API_KEY and WATSONX_PROJECT_ID. For instructions, see Create Secrets.
4. Go to the Advanced tab to configure prefix, suffix, truncate_input_tokens, and api_base_url.

Connections

WatsonxTextEmbedder receives the user query as a text string, typically from the Input component. It outputs a float vector through its embedding output, which you connect to an embedding retriever.

Source Code

To check this component's source code, open text_embedder.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  WatsonxTextEmbedder:
    type: haystack_integrations.components.embedders.watsonx.WatsonxTextEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - WATSONX_API_KEY
        strict: false
      project_id:
        type: env_var
        env_vars:
        - WATSONX_PROJECT_ID
        strict: false
      model: ibm/slate-30m-english-rtrvr-v2

Using the Component in a Pipeline

# haystack-pipeline
components:
  WatsonxTextEmbedder:
    type: haystack_integrations.components.embedders.watsonx.WatsonxTextEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - WATSONX_API_KEY
        strict: false
      project_id:
        type: env_var
        env_vars:
        - WATSONX_PROJECT_ID
        strict: false
      model: ibm/slate-30m-english-rtrvr-v2

  retriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      top_k: 10
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: my-index
          embedding_dim: 384

connections:
- sender: WatsonxTextEmbedder.embedding
  receiver: retriever.query_embedding

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - WatsonxTextEmbedder.text

Parameters

Inputs

Parameter	Type	Description
text	str	The text to embed.

Outputs

Parameter	Type	Description
embedding	List[float]	The embedding of the text.
meta	Dict[str, Any]	Metadata about the request.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str	ibm/slate-30m-english-rtrvr-v2	The name of the watsonx.ai embedding model.
api_key	Secret	Secret.from_env_var("WATSONX_API_KEY")	The IBM Cloud API key for watsonx.ai.
api_base_url	str	https://us-south.ml.cloud.ibm.com	The IBM Cloud watsonx.ai API base URL.
project_id	Secret	Secret.from_env_var("WATSONX_PROJECT_ID")	The watsonx.ai project ID.
truncate_input_tokens	Optional[int]	None	The maximum number of input tokens. Text exceeding this limit is truncated.
prefix	str	""	A string to add at the beginning of the text before embedding.
suffix	str	""	A string to add at the end of the text before embedding.
timeout	Optional[float]	None	Request timeout in seconds.
max_retries	Optional[int]	None	Maximum number of retries on API errors.

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.

Related Information

• WatsonxDocumentEmbedder
• Pipeline Components