Compare commits

..
Author SHA1 Message Date
Mark VanLandingham 0df00bf1c4 DEV: Move semantic search out of connector to component 2024-11-11 11:44:21 -06:00
317 changed files with 5209 additions and 11782 deletions
+1
View File
@@ -0,0 +1 @@
module.exports = require("@discourse/lint-configs/eslint");
@@ -1,18 +1,18 @@
import DiscourseRoute from "discourse/routes/discourse";
export default class AdminPluginsShowDiscourseAiLlmsNew extends DiscourseRoute {
queryParams = {
export default DiscourseRoute.extend({
queryParams: {
llmTemplate: { refreshModel: true },
};
},
async model() {
const record = this.store.createRecord("ai-llm");
record.provider_params = {};
return record;
}
},
setupController(controller, model) {
super.setupController(controller, model);
this._super(controller, model);
controller.set(
"allLlms",
this.modelFor("adminPlugins.show.discourse-ai-llms")
@@ -21,5 +21,5 @@ export default class AdminPluginsShowDiscourseAiLlmsNew extends DiscourseRoute {
"llmTemplate",
this.paramsFor(this.routeName).llmTemplate || null
);
}
}
},
});
@@ -1,19 +1,19 @@
import DiscourseRoute from "discourse/routes/discourse";
export default class AdminPluginsShowDiscourseAiLlmsShow extends DiscourseRoute {
export default DiscourseRoute.extend({
async model(params) {
const allLlms = this.modelFor("adminPlugins.show.discourse-ai-llms");
const id = parseInt(params.id, 10);
const record = allLlms.findBy("id", id);
record.provider_params = record.provider_params || {};
return record;
}
},
setupController(controller, model) {
super.setupController(controller, model);
this._super(controller, model);
controller.set(
"allLlms",
this.modelFor("adminPlugins.show.discourse-ai-llms")
);
}
}
},
});
@@ -1,7 +1,7 @@
import { AUTO_GROUPS } from "discourse/lib/constants";
import DiscourseRoute from "discourse/routes/discourse";
export default class AdminPluginsShowDiscourseAiPersonasNew extends DiscourseRoute {
export default DiscourseRoute.extend({
async model() {
const record = this.store.createRecord("ai-persona");
record.set("allowed_group_ids", [AUTO_GROUPS.trust_level_0.id]);
@@ -13,13 +13,13 @@ export default class AdminPluginsShowDiscourseAiPersonasNew extends DiscourseRou
record.set("allow_personal_messages", true);
record.set("tool_details", false);
return record;
}
},
setupController(controller, model) {
super.setupController(controller, model);
this._super(controller, model);
controller.set(
"allPersonas",
this.modelFor("adminPlugins.show.discourse-ai-personas")
);
}
}
},
});
@@ -1,19 +1,19 @@
import DiscourseRoute from "discourse/routes/discourse";
export default class AdminPluginsShowDiscourseAiPersonasShow extends DiscourseRoute {
export default DiscourseRoute.extend({
async model(params) {
const allPersonas = this.modelFor(
"adminPlugins.show.discourse-ai-personas"
);
const id = parseInt(params.id, 10);
return allPersonas.findBy("id", id);
}
},
setupController(controller, model) {
super.setupController(controller, model);
this._super(controller, model);
controller.set(
"allPersonas",
this.modelFor("adminPlugins.show.discourse-ai-personas")
);
}
}
},
});
@@ -1,11 +0,0 @@
import { service } from "@ember/service";
import { ajax } from "discourse/lib/ajax";
import DiscourseRoute from "discourse/routes/discourse";
export default class DiscourseAiUsageRoute extends DiscourseRoute {
@service store;
model() {
return ajax("/admin/plugins/discourse-ai/ai-usage.json");
}
}
@@ -1,7 +1,5 @@
<section class="ai-persona-tool-editor__current admin-detail pull-left">
<AiToolEditor
@tools={{this.allTools}}
@model={{this.model}}
@presets={{this.presets}}
/>
</section>
<AiToolEditor
@tools={{this.allTools}}
@model={{this.model}}
@presets={{this.presets}}
/>
@@ -1,7 +1,5 @@
<section class="ai-persona-tool-editor__current admin-detail pull-left">
<AiToolEditor
@tools={{this.allTools}}
@model={{this.model}}
@presets={{this.presets}}
/>
</section>
<AiToolEditor
@tools={{this.allTools}}
@model={{this.model}}
@presets={{this.presets}}
/>
@@ -1 +0,0 @@
<AiUsage @model={{this.model}} />
@@ -1,27 +0,0 @@
# frozen_string_literal: true
module DiscourseAi
module Admin
class AiUsageController < ::Admin::AdminController
requires_plugin "discourse-ai"
def show
render json: AiUsageSerializer.new(create_report, root: false)
end
private
def create_report
report =
DiscourseAi::Completions::Report.new(
start_date: params[:start_date]&.to_date || 30.days.ago,
end_date: params[:end_date]&.to_date || Time.current,
)
report = report.filter_by_feature(params[:feature]) if params[:feature].present?
report = report.filter_by_model(params[:model]) if params[:model].present?
report
end
end
end
end
@@ -1,87 +0,0 @@
# frozen_string_literal: true
module DiscourseAi
module AiBot
class ArtifactsController < ApplicationController
requires_plugin DiscourseAi::PLUGIN_NAME
before_action :require_site_settings!
skip_before_action :preload_json, :check_xhr, only: %i[show]
def show
artifact = AiArtifact.find(params[:id])
post = Post.find_by(id: artifact.post_id)
if artifact.metadata&.dig("public")
# no guardian needed
else
raise Discourse::NotFound if !post&.topic&.private_message?
raise Discourse::NotFound if !guardian.can_see?(post)
end
# Prepare the inner (untrusted) HTML document
untrusted_html = <<~HTML
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>#{ERB::Util.html_escape(artifact.name)}</title>
<style>
#{artifact.css}
</style>
</head>
<body>
#{artifact.html}
<script>
#{artifact.js}
</script>
</body>
</html>
HTML
# Prepare the outer (trusted) HTML document
trusted_html = <<~HTML
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>#{ERB::Util.html_escape(artifact.name)}</title>
<style>
html, body, iframe {
margin: 0;
padding: 0;
width: 100%;
height: 100%;
border: 0;
overflow: hidden;
}
iframe {
overflow: auto;
}
</style>
</head>
<body>
<iframe sandbox="allow-scripts allow-forms" height="100%" width="100%" srcdoc="#{ERB::Util.html_escape(untrusted_html)}" frameborder="0"></iframe>
</body>
</html>
HTML
response.headers.delete("X-Frame-Options")
response.headers["Content-Security-Policy"] = "script-src 'unsafe-inline';"
response.headers["X-Robots-Tag"] = "noindex"
# Render the content
render html: trusted_html.html_safe, layout: false, content_type: "text/html"
end
private
def require_site_settings!
if !SiteSetting.discourse_ai_enabled ||
!SiteSetting.ai_artifact_security.in?(%w[lax strict])
raise Discourse::NotFound
end
end
end
end
end
@@ -6,14 +6,6 @@ module DiscourseAi
requires_plugin ::DiscourseAi::PLUGIN_NAME
requires_login
def show_debug_info_by_id
log = AiApiAuditLog.find(params[:id])
raise Discourse::NotFound if !log.topic
guardian.ensure_can_debug_ai_bot_conversation!(log.topic)
render json: AiApiAuditLogSerializer.new(log, root: false), status: 200
end
def show_debug_info
post = Post.find(params[:post_id])
guardian.ensure_can_debug_ai_bot_conversation!(post)
@@ -7,8 +7,7 @@ module DiscourseAi
requires_login only: %i[create update destroy]
before_action :require_site_settings!
skip_before_action :preload_json, :check_xhr, only: %i[show asset]
skip_before_action :verify_authenticity_token, only: ["asset"]
skip_before_action :preload_json, :check_xhr, only: %i[show]
def create
ensure_allowed_create!
@@ -51,30 +50,6 @@ module DiscourseAi
end
end
def asset
no_cookies
name = params[:name]
path, content_type =
if name == "share"
%w[share.css text/css]
elsif name == "highlight"
%w[highlight.min.js application/javascript]
else
raise Discourse::NotFound
end
content = File.read(DiscourseAi.public_asset_path("ai-share/#{path}"))
# note, path contains a ":version" which automatically busts the cache
# based on file content, so this is safe
response.headers["Last-Modified"] = 10.years.ago.httpdate
response.headers["Content-Length"] = content.bytesize.to_s
immutable_for 1.year
render plain: content, disposition: :nil, content_type: content_type
end
def preview
ensure_allowed_preview!
data = SharedAiConversation.build_conversation_data(@topic, include_usernames: true)
@@ -35,7 +35,7 @@ module DiscourseAi
prompt.custom_instruction = params[:custom_prompt]
end
return suggest_thumbnails(input) if prompt.id == CompletionPrompt::ILLUSTRATE_POST
suggest_thumbnails(input) if prompt.id == CompletionPrompt::ILLUSTRATE_POST
hijack do
render json:
@@ -2,29 +2,13 @@
module DiscourseAi
module AiBot
module SharedAiConversationsHelper
# keeping it here for caching
def self.share_asset_url(asset_name)
if !%w[share.css highlight.js].include?(asset_name)
raise StandardError, "unknown asset type #{asset_name}"
end
# bump up version when assets change
# long term we may want to change this cause it is hard to remember
# to bump versions, but for now this does the job
VERSION = "1"
@urls ||= {}
url = @urls[asset_name]
return url if url
path = asset_name
path = "highlight.min.js" if asset_name == "highlight.js"
content = File.read(DiscourseAi.public_asset_path("ai-share/#{path}"))
sha1 = Digest::SHA1.hexdigest(content)
url = "/discourse-ai/ai-bot/shared-ai-conversations/asset/#{sha1}/#{asset_name}"
@urls[asset_name] = GlobalPath.cdn_path(url)
end
def share_asset_url(asset_name)
DiscourseAi::AiBot::SharedAiConversationsHelper.share_asset_url(asset_name)
def share_asset_url(short_path)
::UrlHelper.absolute("/plugins/discourse-ai/ai-share/#{short_path}?#{VERSION}")
end
end
end
+22
View File
@@ -0,0 +1,22 @@
# frozen_string_literal: true
module ::Jobs
class HotTopicsGistBatch < ::Jobs::Base
def execute(_args)
return if !SiteSetting.discourse_ai_enabled
return if !SiteSetting.ai_summarization_enabled
return if SiteSetting.ai_summarize_max_hot_topics_gists_per_batch.zero?
Topic
.joins("JOIN topic_hot_scores on topics.id = topic_hot_scores.topic_id")
.order("topic_hot_scores.score DESC")
.limit(SiteSetting.ai_summarize_max_hot_topics_gists_per_batch)
.each do |topic|
summarizer = DiscourseAi::Summarization.topic_gist(topic)
gist = summarizer.existing_summary
summarizer.force_summarize(Discourse.system_user) if gist.blank? || gist.outdated
end
end
end
end
+3 -1
View File
@@ -9,7 +9,9 @@ module ::Jobs
post = Post.find_by(id: post_id, post_type: Post.types[:regular])
return if post&.raw.blank?
DiscourseAi::Sentiment::PostClassification.new.classify!(post)
DiscourseAi::PostClassificator.new(
DiscourseAi::Sentiment::SentimentClassification.new,
).classify!(post)
end
end
end
@@ -1,20 +1,23 @@
# frozen_string_literal: true
module ::Jobs
class FastTrackTopicGist < ::Jobs::Base
class UpdateHotTopicGist < ::Jobs::Base
sidekiq_options retry: false
def execute(args)
return if !SiteSetting.discourse_ai_enabled
return if !SiteSetting.ai_summarization_enabled
return if !SiteSetting.ai_summary_gists_enabled
return if SiteSetting.ai_summarize_max_hot_topics_gists_per_batch.zero?
topic = Topic.find_by(id: args[:topic_id])
return if topic.blank?
return if !TopicHotScore.where(topic: topic).exists?
summarizer = DiscourseAi::Summarization.topic_gist(topic)
gist = summarizer.existing_summary
return if gist.present? && !gist.outdated
return if gist.blank?
return if !gist.outdated
summarizer.force_summarize(Discourse.system_user)
end
+21 -25
View File
@@ -70,15 +70,14 @@ module Jobs
Post
.joins("LEFT JOIN #{table_name} ON #{table_name}.post_id = posts.id")
.where(deleted_at: nil)
.where(post_type: Post.types[:regular])
.limit(limit - rebaked)
# First, we'll try to backfill embeddings for posts that have none
posts
.where("#{table_name}.post_id IS NULL")
.find_in_batches do |batch|
vector_rep.gen_bulk_reprensentations(batch)
rebaked += batch.size
.find_each do |t|
vector_rep.generate_representation_from(t)
rebaked += 1
end
return if rebaked >= limit
@@ -91,28 +90,24 @@ module Jobs
OR
#{table_name}.strategy_version < #{strategy.version}
SQL
.find_in_batches do |batch|
vector_rep.gen_bulk_reprensentations(batch)
rebaked += batch.size
.find_each do |t|
vector_rep.generate_representation_from(t)
rebaked += 1
end
return if rebaked >= limit
# Finally, we'll try to backfill embeddings for posts that have outdated
# embeddings due to edits. Here we only do 10% of the limit
posts_batch_size = 1000
outdated_post_ids =
posts
.where("#{table_name}.updated_at < ?", 7.days.ago)
.order("random()")
.limit((limit - rebaked) / 10)
.pluck(:id)
outdated_post_ids.each_slice(posts_batch_size) do |batch|
vector_rep.gen_bulk_reprensentations(Post.where(id: batch))
rebaked += batch.length
end
posts
.where("#{table_name}.updated_at < ?", 7.days.ago)
.order("random()")
.limit((limit - rebaked) / 10)
.pluck(:id)
.each do |id|
vector_rep.generate_representation_from(Post.find_by(id: id))
rebaked += 1
end
rebaked
end
@@ -125,13 +120,14 @@ module Jobs
topics = topics.where("#{vector_rep.topic_table_name}.topic_id IS NULL") if !force
ids = topics.pluck("topics.id")
batch_size = 1000
ids.each_slice(batch_size) do |batch|
vector_rep.gen_bulk_reprensentations(Topic.where(id: batch).order("topics.bumped_at DESC"))
done += batch.length
ids.each do |id|
topic = Topic.find_by(id: id)
if topic
vector_rep.generate_representation_from(topic)
done += 1
end
end
done
end
end
+3 -5
View File
@@ -19,8 +19,6 @@ module ::Jobs
DiscourseAi::Summarization.topic_summary(topic).force_summarize(system_user)
end
return unless SiteSetting.ai_summary_gists_enabled
gist_t = AiSummary.summary_types[:gist]
backfill_candidates(gist_t)
.limit(current_budget(gist_t))
@@ -31,9 +29,9 @@ module ::Jobs
Topic
.where("topics.word_count >= ?", SiteSetting.ai_summary_backfill_minimum_word_count)
.joins(<<~SQL)
LEFT OUTER JOIN ai_summaries ais ON
topics.id = ais.target_id AND
ais.target_type = 'Topic' AND
LEFT OUTER JOIN ai_summaries ais ON
topics.id = ais.target_id AND
ais.target_type = 'Topic' AND
ais.summary_type = '#{summary_type}'
SQL
.where(
-17
View File
@@ -3,7 +3,6 @@
class AiApiAuditLog < ActiveRecord::Base
belongs_to :post
belongs_to :topic
belongs_to :user
module Provider
OpenAI = 1
@@ -14,15 +13,6 @@ class AiApiAuditLog < ActiveRecord::Base
Cohere = 6
Ollama = 7
SambaNova = 8
Mistral = 9
end
def next_log_id
self.class.where("id > ?", id).where(topic_id: topic_id).order(id: :asc).pluck(:id).first
end
def prev_log_id
self.class.where("id < ?", id).where(topic_id: topic_id).order(id: :desc).pluck(:id).first
end
end
@@ -44,10 +34,3 @@ end
# feature_name :string(255)
# language_model :string(255)
# feature_context :jsonb
# cached_tokens :integer
#
# Indexes
#
# index_ai_api_audit_logs_on_created_at_and_feature_name (created_at,feature_name)
# index_ai_api_audit_logs_on_created_at_and_language_model (created_at,language_model)
#
-52
View File
@@ -1,52 +0,0 @@
# frozen_string_literal: true
class AiArtifact < ActiveRecord::Base
belongs_to :user
belongs_to :post
validates :html, length: { maximum: 65_535 }
validates :css, length: { maximum: 65_535 }
validates :js, length: { maximum: 65_535 }
def self.iframe_for(id)
<<~HTML
<div class='ai-artifact'>
<iframe src='#{url(id)}' frameborder="0" height="100%" width="100%"></iframe>
<a href='#{url(id)}' target='_blank'>#{I18n.t("discourse_ai.ai_artifact.link")}</a>
</div>
HTML
end
def self.url(id)
Discourse.base_url + "/discourse-ai/ai-bot/artifacts/#{id}"
end
def self.share_publicly(id:, post:)
artifact = AiArtifact.find_by(id: id)
artifact.update!(metadata: { public: true }) if artifact&.post&.topic&.id == post.topic.id
end
def self.unshare_publicly(id:)
artifact = AiArtifact.find_by(id: id)
artifact&.update!(metadata: { public: false })
end
def url
self.class.url(id)
end
end
# == Schema Information
#
# Table name: ai_artifacts
#
# id :bigint not null, primary key
# user_id :integer not null
# post_id :integer not null
# name :string(255) not null
# html :string(65535)
# css :string(65535)
# js :string(65535)
# metadata :jsonb
# created_at :datetime not null
# updated_at :datetime not null
#
+10 -19
View File
@@ -9,23 +9,15 @@ class AiSummary < ActiveRecord::Base
def self.store!(strategy, llm_model, summary, og_content, human:)
content_ids = og_content.map { |c| c[:id] }
AiSummary
.upsert(
{
target_id: strategy.target.id,
target_type: strategy.target.class.name,
algorithm: llm_model.name,
content_range: (content_ids.first..content_ids.last),
summarized_text: summary,
original_content_sha: build_sha(content_ids.join),
summary_type: strategy.type,
origin: !!human ? origins[:human] : origins[:system],
},
unique_by: %i[target_id target_type summary_type],
update_only: %i[summarized_text original_content_sha algorithm origin content_range],
)
.first
.then { AiSummary.find_by(id: _1["id"]) }
AiSummary.create!(
target: strategy.target,
algorithm: llm_model.name,
content_range: (content_ids.first..content_ids.last),
summarized_text: summary,
original_content_sha: build_sha(content_ids.join),
summary_type: strategy.type,
origin: !!human ? origins[:human] : origins[:system],
)
end
def self.build_sha(joined_ids)
@@ -59,6 +51,5 @@ end
#
# Indexes
#
# idx_on_target_id_target_type_summary_type_3355609fbb (target_id,target_type,summary_type) UNIQUE
# index_ai_summaries_on_target_type_and_target_id (target_type,target_id)
# index_ai_summaries_on_target_type_and_target_id (target_type,target_id)
#
-1
View File
@@ -8,7 +8,6 @@ class CompletionPrompt < ActiveRecord::Base
CUSTOM_PROMPT = -305
EXPLAIN = -306
ILLUSTRATE_POST = -308
DETECT_TEXT_LOCALE = -309
enum :prompt_type, { text: 0, list: 1, diff: 2 }
-10
View File
@@ -26,16 +26,6 @@ class LlmModel < ActiveRecord::Base
},
open_ai: {
organization: :text,
disable_native_tools: :checkbox,
},
mistral: {
disable_native_tools: :checkbox,
},
google: {
disable_native_tools: :checkbox,
},
azure: {
disable_native_tools: :checkbox,
},
hugging_face: {
disable_system_prompt: :checkbox,
-1
View File
@@ -172,7 +172,6 @@ end
# updated_at :datetime not null
# force_review :boolean default(FALSE), not null
# reject_reason :text
# potentially_illegal :boolean default(FALSE)
#
# Indexes
#
-1
View File
@@ -229,7 +229,6 @@ end
# updated_at :datetime not null
# force_review :boolean default(FALSE), not null
# reject_reason :text
# potentially_illegal :boolean default(FALSE)
#
# Indexes
#
+1 -25
View File
@@ -34,12 +34,6 @@ class SharedAiConversation < ActiveRecord::Base
def self.destroy_conversation(conversation)
conversation.destroy
maybe_topic = conversation.target
if maybe_topic.is_a?(Topic)
AiArtifact.where(post: maybe_topic.posts).update_all(metadata: { public: false })
end
::Jobs.enqueue(
:shared_conversation_adjust_upload_security,
target_id: conversation.target_id,
@@ -171,7 +165,7 @@ class SharedAiConversation < ActiveRecord::Base
id: post.id,
user_id: post.user_id,
created_at: post.created_at,
cooked: cook_artifacts(post),
cooked: post.cooked,
}
mapped[:persona] = persona if ai_bot_participant&.id == post.user_id
@@ -181,24 +175,6 @@ class SharedAiConversation < ActiveRecord::Base
}
end
def self.cook_artifacts(post)
html = post.cooked
return html if !%w[lax strict].include?(SiteSetting.ai_artifact_security)
doc = Nokogiri::HTML5.fragment(html)
doc
.css("div.ai-artifact")
.each do |node|
id = node["data-ai-artifact-id"].to_i
if id > 0
AiArtifact.share_publicly(id: id, post: post)
node.replace(AiArtifact.iframe_for(id))
end
end
doc.to_s
end
private
def populate_user_info!(posts)
@@ -12,7 +12,5 @@ class AiApiAuditLogSerializer < ApplicationSerializer
:post_id,
:feature_name,
:language_model,
:created_at,
:prev_log_id,
:next_log_id
:created_at
end
-69
View File
@@ -1,69 +0,0 @@
# frozen_string_literal: true
class AiUsageSerializer < ApplicationSerializer
attributes :data, :features, :models, :users, :summary, :period
def data
object.tokens_by_period.as_json(
only: %i[period total_tokens total_cached_tokens total_request_tokens total_response_tokens],
)
end
def period
object.guess_period
end
def features
object.feature_breakdown.as_json(
only: %i[
feature_name
usage_count
total_tokens
total_cached_tokens
total_request_tokens
total_response_tokens
],
)
end
def models
object.model_breakdown.as_json(
only: %i[
llm
usage_count
total_tokens
total_cached_tokens
total_request_tokens
total_response_tokens
],
)
end
def users
object.user_breakdown.map do |user|
{
avatar_template: User.avatar_template(user.username, user.uploaded_avatar_id),
username: user.username,
usage_count: user.usage_count,
total_tokens: user.total_tokens,
total_cached_tokens: user.total_cached_tokens,
total_request_tokens: user.total_request_tokens,
total_response_tokens: user.total_response_tokens,
}
end
end
def summary
{
total_tokens: object.total_tokens,
total_cached_tokens: object.total_cached_tokens,
total_request_tokens: object.total_request_tokens,
total_response_tokens: object.total_response_tokens,
total_requests: object.total_requests,
date_range: {
start: object.start_date,
end: object.end_date,
},
}
end
end

Some files were not shown because too many files have changed in this diff Show More