mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-03-08 10:20:07 +00:00
534b0df391
In a previous refactor, we moved the responsibility of querying and storing embeddings into the `Schema` class. Now, it's time for embedding generation. The motivation behind these changes is to isolate vector characteristics in simple objects to later replace them with a DB-backed version, similar to what we did with LLM configs.
52 lines
923 B
Ruby
52 lines
923 B
Ruby
# frozen_string_literal: true
|
|
|
|
module DiscourseAi
|
|
module Embeddings
|
|
module VectorRepresentations
|
|
class TextEmbedding3Small < Base
|
|
class << self
|
|
def name
|
|
"text-embedding-3-small"
|
|
end
|
|
|
|
def correctly_configured?
|
|
SiteSetting.ai_openai_api_key.present?
|
|
end
|
|
|
|
def dependant_setting_names
|
|
%w[ai_openai_api_key]
|
|
end
|
|
end
|
|
|
|
def id
|
|
6
|
|
end
|
|
|
|
def version
|
|
1
|
|
end
|
|
|
|
def dimensions
|
|
1536
|
|
end
|
|
|
|
def max_sequence_length
|
|
8191
|
|
end
|
|
|
|
def pg_function
|
|
"<=>"
|
|
end
|
|
|
|
def tokenizer
|
|
DiscourseAi::Tokenizer::OpenAiTokenizer
|
|
end
|
|
|
|
def inference_client
|
|
DiscourseAi::Inference::OpenAiEmbeddings.instance(model: self.class.name)
|
|
end
|
|
end
|
|
end
|
|
end
|
|
end
|