WeaviateEx.API.Vectorizers.Multi2VecGoogle (WeaviateEx v0.7.4)
View SourceMulti2Vec-Google (Vertex AI) vectorizer configuration.
Uses Google's multimodal embedding models for image, text, and video.
Example
Multi2VecGoogle.new(
project_id: "my-gcp-project",
location: "us-central1",
image_fields: [%{name: "image", weight: 0.5}],
text_fields: [%{name: "description", weight: 0.5}]
)
Summary
Functions
Parse configuration from API response.
Create a new Multi2Vec-Google configuration.
Convert configuration to API format.
Returns the vectorizer name for the API.
Types
@type t() :: %WeaviateEx.API.Vectorizers.Multi2VecGoogle{ dimensions: pos_integer() | nil, image_fields: [field_config()] | nil, location: String.t() | nil, model_id: String.t() | nil, project_id: String.t() | nil, text_fields: [field_config()] | nil, vectorize_collection_name: boolean(), video_fields: [field_config()] | nil }
Functions
Parse configuration from API response.
Create a new Multi2Vec-Google configuration.
Options
:project_id- Google Cloud project ID (required):location- Google Cloud location (e.g., "us-central1"):model_id- Model ID (e.g., "multimodalembedding@001"):dimensions- Output dimensions:image_fields- List of image field configs with name and optional weight:text_fields- List of text field configs with name and optional weight:video_fields- List of video field configs with name and optional weight:vectorize_collection_name- Include collection name (default: true)
Field Config
Fields can be specified as:
- Simple strings:
["image", "caption"] - Maps with weights:
[%{name: "image", weight: 0.7}]
Convert configuration to API format.
@spec vectorizer_name() :: String.t()
Returns the vectorizer name for the API.