130 lines
3.5 KiB
Ruby
Raw Normal View History

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
# frozen_string_literal: true
class DiscourseAi::Evals::Llm
CONFIGS = {
"gpt-4o" => {
display_name: "GPT-4o",
name: "gpt-4o",
tokenizer: "DiscourseAi::Tokenizer::OpenAiTokenizer",
api_key_env: "OPENAI_API_KEY",
provider: "open_ai",
url: "https://api.openai.com/v1/chat/completions",
max_prompt_tokens: 131_072,
vision_enabled: true,
},
"gpt-4o-mini" => {
display_name: "GPT-4o-mini",
name: "gpt-4o-mini",
tokenizer: "DiscourseAi::Tokenizer::OpenAiTokenizer",
api_key_env: "OPENAI_API_KEY",
provider: "open_ai",
url: "https://api.openai.com/v1/chat/completions",
max_prompt_tokens: 131_072,
vision_enabled: true,
},
"claude-3.5-haiku" => {
display_name: "Claude 3.5 Haiku",
name: "claude-3-5-haiku-latest",
tokenizer: "DiscourseAi::Tokenizer::AnthropicTokenizer",
api_key_env: "ANTHROPIC_API_KEY",
provider: "anthropic",
url: "https://api.anthropic.com/v1/messages",
max_prompt_tokens: 200_000,
vision_enabled: false,
},
"claude-3.5-sonnet" => {
display_name: "Claude 3.5 Sonnet",
name: "claude-3-5-sonnet-latest",
tokenizer: "DiscourseAi::Tokenizer::AnthropicTokenizer",
api_key_env: "ANTHROPIC_API_KEY",
provider: "anthropic",
url: "https://api.anthropic.com/v1/messages",
max_prompt_tokens: 200_000,
vision_enabled: true,
},
"gemini-2.0-flash" => {
display_name: "Gemini 2.0 Flash",
name: "gemini-2-0-flash",
tokenizer: "DiscourseAi::Tokenizer::GeminiTokenizer",
api_key_env: "GEMINI_API_KEY",
provider: "google",
url: "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash",
max_prompt_tokens: 1_000_000,
vision_enabled: true,
},
"gemini-2.0-pro-exp" => {
display_name: "Gemini 2.0 pro",
name: "gemini-2-0-pro-exp",
tokenizer: "DiscourseAi::Tokenizer::GeminiTokenizer",
api_key_env: "GEMINI_API_KEY",
provider: "google",
url: "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-pro-exp",
max_prompt_tokens: 1_000_000,
vision_enabled: true,
},
}
def self.print
CONFIGS
.keys
.map do |config_name|
begin
new(config_name)
rescue StandardError
nil
end
end
.compact
.each { |llm| puts "#{llm.config_name}: #{llm.name} (#{llm.provider})" }
end
def self.choose(config_name)
if CONFIGS[config_name].nil?
CONFIGS
.keys
.map do |config_name|
begin
new(config_name)
rescue => e
puts "Error initializing #{config_name}: #{e}"
nil
end
end
.compact
elsif !CONFIGS.include?(config_name)
raise "Invalid llm"
else
[new(config_name)]
end
end
attr_reader :llm_model
attr_reader :llm_proxy
attr_reader :config_name
def initialize(config_name)
config = CONFIGS[config_name].dup
api_key_env = config.delete(:api_key_env)
if !ENV[api_key_env]
raise "Missing API key for #{config_name}, should be set via #{api_key_env}"
end
config[:api_key] = ENV[api_key_env]
@llm_model = LlmModel.new(config)
@llm_proxy = DiscourseAi::Completions::Llm.proxy(@llm_model)
@config_name = config_name
end
def provider
@llm_model.provider
end
def name
@llm_model.display_name
end
def vision?
@llm_model.vision_enabled
end
end