Skip to main content
For the complete documentation index for agents and LLMs, see llms.txt.

MockedTextEmbedder

A test component that returns a mocked embedding for a given text string.

Work in Progress

We're working on adding pipeline examples and most common component connections.

Key Features​

  • Returns a mocked dense embedding for testing purposes.
  • Useful for testing hybrid retrieval pipeline configurations without a real embedding model.

Configuration​

  1. Drag the MockedTextEmbedder component onto the canvas from the Component Library.
  2. Click on the component to open the configuration panel.
  3. On the General tab, no configuration is required.

Connections​

MockedTextEmbedder accepts no inputs. It outputs a dense embedding vector as list[float]. Connect its embedding output to the query_embedding input of an embedding retriever.

Usage Examples​

Basic Configuration​

  MockedTextEmbedder:
    type: opensearch.tests.test_open_search_hybrid_retriever.MockedTextEmbedder
    init_parameters: {}
components:
  MockedTextEmbedder:
    type: opensearch.tests.test_open_search_hybrid_retriever.MockedTextEmbedder
    init_parameters:

Parameters​

Inputs​

ParameterTypeDefaultDescription

Outputs​

ParameterTypeDefaultDescription
embeddinglist[float]A mocked embedding vector.

Init Parameters​

These are the parameters you can configure in Pipeline Builder:

ParameterTypeDefaultDescription

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.

ParameterTypeDefaultDescription