mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-06-30 11:32:18 +00:00
5e80f93e4c
This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes: **1. LLM Model Association for RAG and Personas:** - **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`. - **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter. - **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes. - **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector. - **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes. **2. PDF and Image Support for RAG:** - **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`. - **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled. - **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced. - **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs. - **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments. - **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types. **3. Refactoring and Improvements:** - **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend. - **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility. - **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based. - **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing. - **Eval Script:** An evaluation script is included. **4. Testing:** - The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
48 lines
1.1 KiB
Ruby
48 lines
1.1 KiB
Ruby
# frozen_string_literal: true
|
|
require "optparse"
|
|
|
|
class DiscourseAi::Evals::Cli
|
|
class Options
|
|
attr_accessor :eval_name, :model, :list, :list_models
|
|
def initialize(eval_name: nil, model: nil, list: false, list_models: false)
|
|
@eval_name = eval_name
|
|
@model = model
|
|
@list = list
|
|
@list_models = list_models
|
|
end
|
|
end
|
|
|
|
def self.parse_options!
|
|
options = Options.new
|
|
|
|
parser =
|
|
OptionParser.new do |opts|
|
|
opts.banner = "Usage: evals/run [options]"
|
|
|
|
opts.on("-e", "--eval NAME", "Name of the evaluation to run") do |eval_name|
|
|
options.eval_name = eval_name
|
|
end
|
|
|
|
opts.on("--list-models", "List models") { |model| options.list_models = true }
|
|
|
|
opts.on(
|
|
"-m",
|
|
"--model NAME",
|
|
"Model to evaluate (will eval all models if not specified)",
|
|
) { |model| options.model = model }
|
|
|
|
opts.on("-l", "--list", "List evals") { |model| options.list = true }
|
|
end
|
|
|
|
show_help = ARGV.empty?
|
|
parser.parse!
|
|
|
|
if show_help
|
|
puts parser
|
|
exit 0
|
|
end
|
|
|
|
options
|
|
end
|
|
end
|