WeaviateEx.API.Vectorizers.Text2VecOpenAI (WeaviateEx v0.7.4)

View Source

Text2Vec-OpenAI vectorizer configuration.

Uses OpenAI's embedding models for text vectorization.

Example

# Basic usage with default model
Text2VecOpenAI.new(model: "text-embedding-ada-002")

# With dimensions (for text-embedding-3-* models)
Text2VecOpenAI.new(
  model: "text-embedding-3-small",
  dimensions: 512
)

# Full configuration
Text2VecOpenAI.new(
  model: "text-embedding-3-large",
  dimensions: 1024,
  base_url: "https://custom.openai.com",
  type: :text,
  vectorize_collection_name: false
)

Summary

Types

embedding_type()
t()

Functions

from_api(map)

Parse configuration from API response.

new(opts \\ [])

Create a new Text2Vec-OpenAI configuration.

to_api(config)

Convert configuration to API format.

vectorizer_name()

Returns the vectorizer name for the API.

Types

embedding_type()

@type embedding_type() :: :text | :code

t()

@type t() :: %WeaviateEx.API.Vectorizers.Text2VecOpenAI{
  base_url: String.t() | nil,
  dimensions: pos_integer() | nil,
  model: String.t() | nil,
  type: embedding_type() | 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 Text2Vec-OpenAI configuration.

Options

  • :model - OpenAI model name (e.g., "text-embedding-ada-002", "text-embedding-3-small")
  • :dimensions - Output dimensions (only for text-embedding-3-* models)
  • :base_url - Custom OpenAI API endpoint
  • :type - Embedding type, either :text or :code
  • :vectorize_collection_name - Include collection name in vectorization (default: true)

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.