77493c5d0f
# Pull Request Template ## Description Fixes # (issue) When we migrated to RubyLLM, images weren't being sent properly in RubyLLM format to the model, so it did not understand images. ## Type of change Please delete options that are not relevant. - [x] Bug fix (non-breaking change which fixes an issue) ## How Has This Been Tested? Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration. specs + local testing Current behaviour on staging: <img width="772" height="1012" alt="image" src="https://github.com/user-attachments/assets/7b7d360f-dea4-48af-b20b-ee4c98a38a85" /> local testing with fix: <img width="792" height="1216" alt="image" src="https://github.com/user-attachments/assets/5ef82452-015e-4bda-a68f-884d00acb014" /> ## Checklist: - [x] My code follows the style guidelines of this project - [x] I have performed a self-review of my code - [x] I have commented on my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [x] Any dependent changes have been merged and published in downstream modules --------- Co-authored-by: Sojan Jose <sojan@pepalo.com>
70 lines
2.3 KiB
Ruby
70 lines
2.3 KiB
Ruby
class Captain::OpenAiMessageBuilderService
|
|
pattr_initialize [:message!]
|
|
|
|
# Extracts text and image URLs from multimodal content array (reverse of generate_content)
|
|
def self.extract_text_and_attachments(content)
|
|
return [content, []] unless content.is_a?(Array)
|
|
|
|
text_parts = content.select { |part| part[:type] == 'text' }.pluck(:text)
|
|
image_urls = content.select { |part| part[:type] == 'image_url' }.filter_map { |part| part.dig(:image_url, :url) }
|
|
[text_parts.join(' ').presence, image_urls]
|
|
end
|
|
|
|
def generate_content
|
|
parts = []
|
|
parts << text_part(@message.content) if @message.content.present?
|
|
parts.concat(attachment_parts(@message.attachments)) if @message.attachments.any?
|
|
|
|
return 'Message without content' if parts.blank?
|
|
return parts.first[:text] if parts.one? && parts.first[:type] == 'text'
|
|
|
|
parts
|
|
end
|
|
|
|
private
|
|
|
|
def text_part(text)
|
|
{ type: 'text', text: text }
|
|
end
|
|
|
|
def image_part(image_url)
|
|
{ type: 'image_url', image_url: { url: image_url } }
|
|
end
|
|
|
|
def attachment_parts(attachments)
|
|
image_attachments = attachments.where(file_type: :image)
|
|
image_content = image_parts(image_attachments)
|
|
|
|
transcription = extract_audio_transcriptions(attachments)
|
|
transcription_part = text_part(transcription) if transcription.present?
|
|
|
|
attachment_part = text_part('User has shared an attachment') if attachments.where.not(file_type: %i[image audio]).exists?
|
|
|
|
[image_content, transcription_part, attachment_part].flatten.compact
|
|
end
|
|
|
|
def image_parts(image_attachments)
|
|
image_attachments.each_with_object([]) do |attachment, parts|
|
|
url = get_attachment_url(attachment)
|
|
parts << image_part(url) if url.present?
|
|
end
|
|
end
|
|
|
|
def get_attachment_url(attachment)
|
|
return attachment.download_url if attachment.download_url.present?
|
|
return attachment.external_url if attachment.external_url.present?
|
|
|
|
attachment.file.attached? ? attachment.file_url : nil
|
|
end
|
|
|
|
def extract_audio_transcriptions(attachments)
|
|
audio_attachments = attachments.where(file_type: :audio)
|
|
return '' if audio_attachments.blank?
|
|
|
|
audio_attachments.map do |attachment|
|
|
result = Messages::AudioTranscriptionService.new(attachment).perform
|
|
result[:success] ? result[:transcriptions] : ''
|
|
end.join
|
|
end
|
|
end
|