discourse-ai/plugin.rb

106 lines
3.5 KiB
Ruby
Raw Normal View History

2023-02-17 09:33:47 -05:00
# frozen_string_literal: true
2023-02-22 18:46:53 -05:00
# name: discourse-ai
# about: Enables integration between AI modules and features in Discourse
# meta_topic_id: 259214
2023-02-17 09:33:47 -05:00
# version: 0.0.1
# authors: Discourse
# url: https://meta.discourse.org/t/discourse-ai/259214
2023-02-17 09:33:47 -05:00
# required_version: 2.7.0
gem "tokenizers", "0.4.4"
2024-07-22 14:26:14 -04:00
gem "tiktoken_ruby", "0.0.9"
gem "ed25519", "1.2.4" #TODO remove this as existing ssl gem should handle this
enabled_site_setting :discourse_ai_enabled
2023-02-17 09:33:47 -05:00
register_asset "stylesheets/common/streaming.scss"
register_asset "stylesheets/modules/ai-helper/common/ai-helper.scss"
register_asset "stylesheets/modules/ai-helper/desktop/ai-helper-fk-modals.scss", :desktop
register_asset "stylesheets/modules/ai-helper/mobile/ai-helper.scss", :mobile
register_asset "stylesheets/modules/summarization/mobile/ai-summary.scss", :mobile
register_asset "stylesheets/modules/summarization/common/ai-summary.scss"
register_asset "stylesheets/modules/summarization/desktop/ai-summary.scss", :desktop
2024-11-19 15:33:34 -05:00
register_asset "stylesheets/modules/summarization/common/ai-gists.scss"
register_asset "stylesheets/modules/ai-bot/common/bot-replies.scss"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
register_asset "stylesheets/modules/ai-bot/common/ai-persona.scss"
register_asset "stylesheets/modules/ai-bot/mobile/ai-persona.scss", :mobile
register_asset "stylesheets/modules/embeddings/common/semantic-related-topics.scss"
register_asset "stylesheets/modules/embeddings/common/semantic-search.scss"
register_asset "stylesheets/modules/sentiment/common/dashboard.scss"
register_asset "stylesheets/modules/llms/common/ai-llms-editor.scss"
register_asset "stylesheets/modules/llms/common/usage.scss"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
register_asset "stylesheets/modules/ai-bot/common/ai-tools.scss"
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
register_asset "stylesheets/modules/ai-bot/common/ai-artifact.scss"
module ::DiscourseAi
PLUGIN_NAME = "discourse-ai"
def self.public_asset_path(name)
File.expand_path(File.join(__dir__, "public", name))
end
end
Rails.autoloaders.main.push_dir(File.join(__dir__, "lib"), namespace: ::DiscourseAi)
require_relative "lib/engine"
after_initialize do
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
if defined?(Rack::MiniProfiler)
Rack::MiniProfiler.config.skip_paths << "/discourse-ai/ai-bot/artifacts"
end
# do not autoload this cause we may have no namespace
require_relative "discourse_automation/llm_triage"
require_relative "discourse_automation/llm_report"
2023-02-22 18:46:53 -05:00
add_admin_route("discourse_ai.title", "discourse-ai", { use_new_show_route: true })
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
[
DiscourseAi::Embeddings::EntryPoint.new,
DiscourseAi::Nsfw::EntryPoint.new,
DiscourseAi::Toxicity::EntryPoint.new,
DiscourseAi::Sentiment::EntryPoint.new,
DiscourseAi::AiHelper::EntryPoint.new,
DiscourseAi::Summarization::EntryPoint.new,
DiscourseAi::AiBot::EntryPoint.new,
].each { |a_module| a_module.inject_into(self) }
register_reviewable_type ReviewableAiChatMessage
register_reviewable_type ReviewableAiPost
on(:reviewable_transitioned_to) do |new_status, reviewable|
ModelAccuracy.adjust_model_accuracy(new_status, reviewable)
end
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
if Rails.env.test?
require_relative "spec/support/embeddings_generation_stubs"
require_relative "spec/support/stable_diffusion_stubs"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
end
reloadable_patch do |plugin|
Guardian.prepend DiscourseAi::GuardianExtensions
Topic.prepend DiscourseAi::TopicExtensions
end
register_modifier(:post_should_secure_uploads?) do |_, _, topic|
if topic.private_message? && SharedAiConversation.exists?(target: topic)
false
else
# revert to default behavior
# even though this can be shortened this is the clearest way to express it
nil
end
end
2023-02-22 18:46:53 -05:00
end