WeaviateEx.API.Vectorizers.Multi2VecClip (WeaviateEx v0.7.4)

View Source

Multi2Vec-CLIP vectorizer configuration.

Uses CLIP models for multimodal (image + text) embedding.

Example

Multi2VecClip.new(
  image_fields: [%{name: "image", weight: 0.7}],
  text_fields: [%{name: "caption", weight: 0.3}]
)

Summary

Types

field_config()
t()

Functions

from_api(map)

Parse configuration from API response.

new(opts \\ [])

Create a new Multi2Vec-CLIP configuration.

to_api(config)

Convert configuration to API format.

vectorizer_name()

Returns the vectorizer name for the API.

Types

field_config()

@type field_config() :: %{:name => String.t(), optional(:weight) => float()}

t()

@type t() :: %WeaviateEx.API.Vectorizers.Multi2VecClip{
  image_fields: [field_config()] | nil,
  inference_url: String.t() | nil,
  text_fields: [field_config()] | nil,
  vectorize_collection_name: boolean()
}

Functions

from_api(map)

@spec from_api(map()) :: t()

Parse configuration from API response.

new(opts \\ [])

@spec new(keyword()) :: t()

Create a new Multi2Vec-CLIP configuration.

Options

  • :image_fields - List of image field configs with name and optional weight
  • :text_fields - List of text field configs with name and optional weight
  • :inference_url - Custom inference URL
  • :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}]

to_api(config)

@spec to_api(t()) :: map()

Convert configuration to API format.

vectorizer_name()

@spec vectorizer_name() :: String.t()

Returns the vectorizer name for the API.