Generate vector embeddings

This example pipeline demonstrates how to generate vector embeddings for sample data.


Amazon Titan Embedder Example Pipeline

Download this pipeline.
  1. Configure the JSON Generator Snap to pass your input data.
    Note: In this example, we use the JSON Generator Snap. However, you can replace the JSON Generator Snap with any Snap of your choice, such as the Chunker, Constant, File Reader, or S3 File Reader Snaps.

    JSON Generator Snap - Edit JSON

  2. Configure the Amazon Titan Embedder Snap to generate embedding vectors for input data based on the Model name, and the input document.
    On validation, the input data is processed into embedded vectors and you can view the data in the output preview.
    Amazon Titan Embedder Snap Configuration Amazon Titan Embedder Snap Output

    Amazon Titan Embedder Snap Configuration
    Amazon Titan Embedder Snap Output
    Note: After generating the vector embeddings, you can store the embeddings into a vector database.
To successfully reuse pipelines:
  1. Download and import the pipeline into SnapLogic.
  2. Configure Snap accounts as applicable.
  3. Provide pipeline parameters as applicable.