WeaviateEx.API.Vectorizers.Multi2VecCohere (WeaviateEx v0.7.4)
View SourceMulti2Vec-Cohere vectorizer configuration.
Uses Cohere's multimodal embedding models for image and text.
Example
Multi2VecCohere.new(
model: "embed-english-v3.0",
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-Cohere configuration.
Convert configuration to API format.
Returns the vectorizer name for the API.
Types
@type t() :: %WeaviateEx.API.Vectorizers.Multi2VecCohere{ base_url: String.t() | nil, image_fields: [field_config()] | nil, model: String.t() | nil, text_fields: [field_config()] | nil, truncate: String.t() | nil, vectorize_collection_name: boolean() }
Functions
Parse configuration from API response.
Create a new Multi2Vec-Cohere configuration.
Options
:model- Cohere model name (e.g., "embed-english-v3.0", "embed-multilingual-v3.0"):base_url- Custom API endpoint:truncate- Truncation strategy ("NONE", "START", "END"):image_fields- List of image field configs with name and optional weight:text_fields- List of text 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.