826d9ec5a7
This PR refactors the schema we introduced in #7518 based on the feedback from production tests. Here is the change log - Decouple Inbox association to a new table inbox_response_sources -> this lets us share the same response source between multiple inboxes - Add a status field to responses. This ensures that, by default, responses are created in pending status. You can do quality assurance before making them active. In future, this status can be leveraged by the bot to auto-generate response questions from conversations which require a handoff - Add response_source association to responses and remove hard dependency from response_documents. This lets users write free-form question answers based on conversations, which doesn't necessarily need a response source.
47 lines
1.4 KiB
Ruby
47 lines
1.4 KiB
Ruby
# == Schema Information
|
|
#
|
|
# Table name: responses
|
|
#
|
|
# id :bigint not null, primary key
|
|
# answer :text not null
|
|
# embedding :vector(1536)
|
|
# question :string not null
|
|
# status :integer default(0)
|
|
# created_at :datetime not null
|
|
# updated_at :datetime not null
|
|
# account_id :bigint not null
|
|
# response_document_id :bigint
|
|
# response_source_id :bigint not null
|
|
#
|
|
# Indexes
|
|
#
|
|
# index_responses_on_embedding (embedding) USING ivfflat
|
|
# index_responses_on_response_document_id (response_document_id)
|
|
#
|
|
class Response < ApplicationRecord
|
|
belongs_to :response_document, optional: true
|
|
belongs_to :account
|
|
belongs_to :response_source
|
|
has_neighbors :embedding, normalize: true
|
|
|
|
before_save :update_response_embedding
|
|
before_validation :ensure_account
|
|
|
|
enum status: { pending: 0, active: 1 }
|
|
|
|
def self.search(query)
|
|
embedding = Openai::EmbeddingsService.new.get_embedding(query)
|
|
nearest_neighbors(:embedding, embedding, distance: 'cosine').first(5)
|
|
end
|
|
|
|
private
|
|
|
|
def ensure_account
|
|
self.account = response_source.account
|
|
end
|
|
|
|
def update_response_embedding
|
|
self.embedding = Openai::EmbeddingsService.new.get_embedding("#{question}: #{answer}")
|
|
end
|
|
end
|