discourse-ai/lib/configuration/llm_enumerator.rb

116 lines
3.8 KiB
Ruby
Raw Permalink Normal View History

# frozen_string_literal: true
require "enum_site_setting"
module DiscourseAi
module Configuration
class LlmEnumerator < ::EnumSiteSetting
def self.global_usage
rval = Hash.new { |h, k| h[k] = [] }
if SiteSetting.ai_bot_enabled
LlmModel
.where("enabled_chat_bot = ?", true)
.pluck(:id)
.each { |llm_id| rval[llm_id] << { type: :ai_bot } }
end
# this is unconditional, so it is clear that we always signal configuration
AiPersona
.where("default_llm_id IS NOT NULL")
.pluck(:default_llm_id, :name, :id)
.each { |llm_id, name, id| rval[llm_id] << { type: :ai_persona, name: name, id: id } }
if SiteSetting.ai_helper_enabled
model_id = SiteSetting.ai_helper_model.split(":").last.to_i
rval[model_id] << { type: :ai_helper } if model_id != 0
end
if SiteSetting.ai_helper_image_caption_model
model_id = SiteSetting.ai_helper_image_caption_model.split(":").last.to_i
rval[model_id] << { type: :ai_helper_image_caption } if model_id != 0
end
if SiteSetting.ai_summarization_enabled
summarization_persona = AiPersona.find_by(id: SiteSetting.ai_summarization_persona)
model_id = summarization_persona.default_llm_id || LlmModel.last&.id
rval[model_id] << { type: :ai_summarization }
end
if SiteSetting.ai_embeddings_semantic_search_enabled
model_id = SiteSetting.ai_embeddings_semantic_search_hyde_model.split(":").last.to_i
rval[model_id] << { type: :ai_embeddings_semantic_search }
end
if SiteSetting.ai_spam_detection_enabled && AiModerationSetting.spam.present?
2024-12-12 09:17:25 +11:00
model_id = AiModerationSetting.spam[:llm_model_id]
rval[model_id] << { type: :ai_spam }
end
if defined?(DiscourseAutomation::Automation)
DiscourseAutomation::Automation
.joins(:fields)
.where(script: %w[llm_report llm_triage])
.where("discourse_automation_fields.name = ?", "model")
.pluck(
"metadata ->> 'value', discourse_automation_automations.name, discourse_automation_automations.id",
)
.each do |model_text, name, id|
next if model_text.blank?
model_id = model_text.split("custom:").last.to_i
if model_id.present?
if model_text =~ /custom:(\d+)/
rval[model_id] << { type: :automation, name: name, id: id }
end
end
end
end
rval
end
def self.valid_value?(val)
true
end
FEATURE: PDF support for rag pipeline (#1118) 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`
2025-02-14 12:15:07 +11:00
# returns an array of hashes (id: , name:, vision_enabled:)
def self.values_for_serialization(allowed_seeded_llm_ids: nil)
builder = DB.build(<<~SQL)
SELECT id, display_name AS name, vision_enabled
FROM llm_models
/*where*/
SQL
if allowed_seeded_llm_ids.is_a?(Array) && !allowed_seeded_llm_ids.empty?
builder.where(
"id > 0 OR id IN (:allowed_seeded_llm_ids)",
allowed_seeded_llm_ids: allowed_seeded_llm_ids,
)
else
builder.where("id > 0")
end
builder.query_hash.map(&:symbolize_keys)
end
2024-12-12 09:17:25 +11:00
def self.values(allowed_seeded_llms: nil)
values = DB.query_hash(<<~SQL).map(&:symbolize_keys)
SELECT display_name AS name, id AS value
FROM llm_models
SQL
2024-12-12 09:17:25 +11:00
if allowed_seeded_llms.is_a?(Array)
values =
values.filter do |value_h|
value_h[:value] > 0 || allowed_seeded_llms.include?("#{value_h[:value]}")
2024-12-12 09:17:25 +11:00
end
end
2024-12-12 09:17:25 +11:00
values.each { |value_h| value_h[:value] = "custom:#{value_h[:value]}" }
values
end
end
end
end