Google Vertex AI

Google Vertex AI provides text embedding models. seekdb provides a GoogleVertexEmbeddingFunction wrapper so you can generate embeddings via Vertex AI and use them with seekdb collections.

tip

Using Google Vertex AI service requires you to follow Google Cloud's pricing rules and may incur corresponding fees. Before proceeding, please visit their official website or refer to relevant documentation to confirm and accept their pricing standards. If you do not agree, please do not proceed.

Dependencies and authentication

GoogleVertexEmbeddingFunction calls the Vertex AI embedding API via the Google Cloud SDK. In practice, you typically need:

• A Google Cloud project with Vertex AI enabled and permission to invoke embedding models
• Python packages: pyseekdb and google-cloud-aiplatform
• Google Application Default Credentials (ADC) configured for your environment

Example: create a Google Vertex AI embedding function

from pyseekdb.utils.embedding_functions import GoogleVertexEmbeddingFunction

ef = GoogleVertexEmbeddingFunction(
    project_id="your-project-id",
    model_name="textembedding-gecko",
)

Parameters

• project_id: your Google Cloud project ID.
• model_name: the Vertex AI embedding model name (for example, textembedding-gecko).