Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Keegan George
|
e7a3a50d86 |
@@ -1,6 +1,5 @@
|
||||
< 3.4.0.beta1-dev: 9d887ad4ace8e33c3fe7dbb39237e882c08b4f0b
|
||||
< 3.3.0.beta5-dev: 4d8090002f6dcd8e34d41033606bf131fa221475
|
||||
< 3.3.0.beta2-dev: 61890b667c06299841ae88946f84a112f00060e1
|
||||
< 3.3.0.beta1-dev: d94234d89f50733678a5c62809445198a9fda74b
|
||||
3.2.999: d94234d89f50733678a5c62809445198a9fda74b
|
||||
< 3.2.0.beta4-dev: 493b48477a9288f2f1b6f021954088705a6673d6
|
||||
< 3.2.0.beta2-dev: 3bced1c6f525553fe2b5b79d29bd66c1cf2a47d5
|
||||
3.1.999: c0415bb7eb878b1b7abf112d65cba981030df8df
|
||||
< 3.2.0.beta1-dev: 3e7c99de894b03e9161d9481da118fe893991a1d
|
||||
3.1.0.beta3: 057fbe1ce6
|
||||
|
||||
+27
-57
@@ -1,88 +1,58 @@
|
||||
GEM
|
||||
remote: https://rubygems.org/
|
||||
specs:
|
||||
activesupport (7.1.3.4)
|
||||
base64
|
||||
bigdecimal
|
||||
concurrent-ruby (~> 1.0, >= 1.0.2)
|
||||
connection_pool (>= 2.2.5)
|
||||
drb
|
||||
i18n (>= 1.6, < 2)
|
||||
minitest (>= 5.1)
|
||||
mutex_m
|
||||
tzinfo (~> 2.0)
|
||||
ast (2.4.2)
|
||||
base64 (0.2.0)
|
||||
bigdecimal (3.1.8)
|
||||
concurrent-ruby (1.3.3)
|
||||
connection_pool (2.4.1)
|
||||
drb (2.2.1)
|
||||
i18n (1.14.5)
|
||||
concurrent-ruby (~> 1.0)
|
||||
json (2.7.2)
|
||||
json (2.6.3)
|
||||
language_server-protocol (3.17.0.3)
|
||||
minitest (5.24.1)
|
||||
mutex_m (0.2.0)
|
||||
parallel (1.25.1)
|
||||
parser (3.3.3.0)
|
||||
parallel (1.23.0)
|
||||
parser (3.2.2.4)
|
||||
ast (~> 2.4.1)
|
||||
racc
|
||||
prettier_print (1.2.1)
|
||||
racc (1.8.0)
|
||||
rack (3.1.6)
|
||||
racc (1.7.2)
|
||||
rainbow (3.1.1)
|
||||
regexp_parser (2.9.2)
|
||||
rexml (3.3.3)
|
||||
strscan
|
||||
rubocop (1.64.1)
|
||||
regexp_parser (2.8.2)
|
||||
rexml (3.2.6)
|
||||
rubocop (1.57.2)
|
||||
json (~> 2.3)
|
||||
language_server-protocol (>= 3.17.0)
|
||||
parallel (~> 1.10)
|
||||
parser (>= 3.3.0.2)
|
||||
parser (>= 3.2.2.4)
|
||||
rainbow (>= 2.2.2, < 4.0)
|
||||
regexp_parser (>= 1.8, < 3.0)
|
||||
rexml (>= 3.2.5, < 4.0)
|
||||
rubocop-ast (>= 1.31.1, < 2.0)
|
||||
rubocop-ast (>= 1.28.1, < 2.0)
|
||||
ruby-progressbar (~> 1.7)
|
||||
unicode-display_width (>= 2.4.0, < 3.0)
|
||||
rubocop-ast (1.31.3)
|
||||
parser (>= 3.3.1.0)
|
||||
rubocop-capybara (2.21.0)
|
||||
rubocop-ast (1.30.0)
|
||||
parser (>= 3.2.1.0)
|
||||
rubocop-capybara (2.19.0)
|
||||
rubocop (~> 1.41)
|
||||
rubocop-discourse (3.8.1)
|
||||
activesupport (>= 6.1)
|
||||
rubocop (>= 1.59.0)
|
||||
rubocop-capybara (>= 2.0.0)
|
||||
rubocop-factory_bot (>= 2.0.0)
|
||||
rubocop-rails (>= 2.25.0)
|
||||
rubocop-rspec (>= 3.0.1)
|
||||
rubocop-rspec_rails (>= 2.30.0)
|
||||
rubocop-factory_bot (2.26.1)
|
||||
rubocop (~> 1.61)
|
||||
rubocop-rails (2.25.1)
|
||||
activesupport (>= 4.2.0)
|
||||
rack (>= 1.1)
|
||||
rubocop (>= 1.33.0, < 2.0)
|
||||
rubocop-ast (>= 1.31.1, < 2.0)
|
||||
rubocop-rspec (3.0.2)
|
||||
rubocop (~> 1.61)
|
||||
rubocop-rspec_rails (2.30.0)
|
||||
rubocop (~> 1.61)
|
||||
rubocop-rspec (~> 3, >= 3.0.1)
|
||||
rubocop-discourse (3.4.0)
|
||||
rubocop (>= 1.1.0)
|
||||
rubocop-rspec (>= 2.0.0)
|
||||
rubocop-factory_bot (2.24.0)
|
||||
rubocop (~> 1.33)
|
||||
rubocop-rspec (2.25.0)
|
||||
rubocop (~> 1.40)
|
||||
rubocop-capybara (~> 2.17)
|
||||
rubocop-factory_bot (~> 2.22)
|
||||
ruby-progressbar (1.13.0)
|
||||
strscan (3.1.0)
|
||||
syntax_tree (6.2.0)
|
||||
prettier_print (>= 1.2.0)
|
||||
tzinfo (2.0.6)
|
||||
concurrent-ruby (~> 1.0)
|
||||
unicode-display_width (2.5.0)
|
||||
|
||||
PLATFORMS
|
||||
arm64-darwin-20
|
||||
ruby
|
||||
x86_64-darwin-18
|
||||
x86_64-darwin-19
|
||||
x86_64-darwin-20
|
||||
x86_64-linux
|
||||
|
||||
DEPENDENCIES
|
||||
rubocop-discourse
|
||||
syntax_tree
|
||||
|
||||
BUNDLED WITH
|
||||
2.5.10
|
||||
2.4.21
|
||||
|
||||
-19
@@ -1,19 +0,0 @@
|
||||
import DiscourseRoute from "discourse/routes/discourse";
|
||||
|
||||
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) {
|
||||
this._super(controller, model);
|
||||
controller.set(
|
||||
"allLlms",
|
||||
this.modelFor("adminPlugins.show.discourse-ai-llms")
|
||||
);
|
||||
},
|
||||
});
|
||||
@@ -1,7 +0,0 @@
|
||||
import DiscourseRoute from "discourse/routes/discourse";
|
||||
|
||||
export default class DiscourseAiAiLlmsRoute extends DiscourseRoute {
|
||||
model() {
|
||||
return this.store.findAll("ai-llm");
|
||||
}
|
||||
}
|
||||
-23
@@ -1,23 +0,0 @@
|
||||
import { AUTO_GROUPS } from "discourse/lib/constants";
|
||||
import DiscourseRoute from "discourse/routes/discourse";
|
||||
|
||||
export default DiscourseRoute.extend({
|
||||
async model() {
|
||||
const record = this.store.createRecord("ai-persona");
|
||||
record.set("allowed_group_ids", [AUTO_GROUPS.trust_level_0.id]);
|
||||
record.set("rag_uploads", []);
|
||||
// these match the defaults on the table
|
||||
record.set("rag_chunk_tokens", 374);
|
||||
record.set("rag_chunk_overlap_tokens", 10);
|
||||
record.set("rag_conversation_chunks", 10);
|
||||
return record;
|
||||
},
|
||||
|
||||
setupController(controller, model) {
|
||||
this._super(controller, model);
|
||||
controller.set(
|
||||
"allPersonas",
|
||||
this.modelFor("adminPlugins.show.discourse-ai-personas")
|
||||
);
|
||||
},
|
||||
});
|
||||
-15
@@ -1,15 +0,0 @@
|
||||
import DiscourseRoute from "discourse/routes/discourse";
|
||||
|
||||
export default class DiscourseAiToolsNewRoute extends DiscourseRoute {
|
||||
async model() {
|
||||
return this.store.createRecord("ai-tool");
|
||||
}
|
||||
|
||||
setupController(controller) {
|
||||
super.setupController(...arguments);
|
||||
const toolsModel = this.modelFor("adminPlugins.show.discourse-ai-tools");
|
||||
|
||||
controller.set("allTools", toolsModel);
|
||||
controller.set("presets", toolsModel.resultSetMeta.presets);
|
||||
}
|
||||
}
|
||||
-18
@@ -1,18 +0,0 @@
|
||||
import DiscourseRoute from "discourse/routes/discourse";
|
||||
|
||||
export default class DiscourseAiToolsShowRoute extends DiscourseRoute {
|
||||
async model(params) {
|
||||
const allTools = this.modelFor("adminPlugins.show.discourse-ai-tools");
|
||||
const id = parseInt(params.id, 10);
|
||||
|
||||
return allTools.find((tool) => tool.id === id);
|
||||
}
|
||||
|
||||
setupController(controller) {
|
||||
super.setupController(...arguments);
|
||||
const toolsModel = this.modelFor("adminPlugins.show.discourse-ai-tools");
|
||||
|
||||
controller.set("allTools", toolsModel);
|
||||
controller.set("presets", toolsModel.resultSetMeta.presets);
|
||||
}
|
||||
}
|
||||
@@ -1,10 +0,0 @@
|
||||
import { service } from "@ember/service";
|
||||
import DiscourseRoute from "discourse/routes/discourse";
|
||||
|
||||
export default class DiscourseAiToolsRoute extends DiscourseRoute {
|
||||
@service store;
|
||||
|
||||
model() {
|
||||
return this.store.findAll("ai-tool");
|
||||
}
|
||||
}
|
||||
-1
@@ -1 +0,0 @@
|
||||
<AiLlmsListEditor @llms={{this.model}} />
|
||||
-1
@@ -1 +0,0 @@
|
||||
<AiLlmsListEditor @llms={{this.allLlms}} @currentLlm={{this.model}} />
|
||||
-1
@@ -1 +0,0 @@
|
||||
<AiLlmsListEditor @llms={{this.allLlms}} @currentLlm={{this.model}} />
|
||||
-1
@@ -1 +0,0 @@
|
||||
<AiToolListEditor @tools={{this.model}} />
|
||||
-5
@@ -1,5 +0,0 @@
|
||||
<AiToolEditor
|
||||
@tools={{this.allTools}}
|
||||
@model={{this.model}}
|
||||
@presets={{this.presets}}
|
||||
/>
|
||||
-5
@@ -1,5 +0,0 @@
|
||||
<AiToolEditor
|
||||
@tools={{this.allTools}}
|
||||
@model={{this.model}}
|
||||
@presets={{this.presets}}
|
||||
/>
|
||||
@@ -1,148 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module DiscourseAi
|
||||
module Admin
|
||||
class AiLlmsController < ::Admin::AdminController
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
|
||||
def index
|
||||
llms = LlmModel.all.order(:display_name)
|
||||
|
||||
render json: {
|
||||
ai_llms:
|
||||
ActiveModel::ArraySerializer.new(
|
||||
llms,
|
||||
each_serializer: LlmModelSerializer,
|
||||
root: false,
|
||||
).as_json,
|
||||
meta: {
|
||||
provider_params: LlmModel.provider_params,
|
||||
presets: DiscourseAi::Completions::Llm.presets,
|
||||
providers: DiscourseAi::Completions::Llm.provider_names,
|
||||
tokenizers:
|
||||
DiscourseAi::Completions::Llm.tokenizer_names.map { |tn|
|
||||
{ id: tn, name: tn.split("::").last }
|
||||
},
|
||||
},
|
||||
}
|
||||
end
|
||||
|
||||
def show
|
||||
llm_model = LlmModel.find(params[:id])
|
||||
render json: LlmModelSerializer.new(llm_model)
|
||||
end
|
||||
|
||||
def create
|
||||
llm_model = LlmModel.new(ai_llm_params)
|
||||
if llm_model.save
|
||||
llm_model.toggle_companion_user
|
||||
render json: { ai_persona: LlmModelSerializer.new(llm_model) }, status: :created
|
||||
else
|
||||
render_json_error llm_model
|
||||
end
|
||||
end
|
||||
|
||||
def update
|
||||
llm_model = LlmModel.find(params[:id])
|
||||
|
||||
if llm_model.seeded?
|
||||
return render_json_error(I18n.t("discourse_ai.llm.cannot_edit_builtin"), status: 403)
|
||||
end
|
||||
|
||||
if llm_model.update(ai_llm_params(updating: llm_model))
|
||||
llm_model.toggle_companion_user
|
||||
render json: LlmModelSerializer.new(llm_model)
|
||||
else
|
||||
render_json_error llm_model
|
||||
end
|
||||
end
|
||||
|
||||
def destroy
|
||||
llm_model = LlmModel.find(params[:id])
|
||||
|
||||
if llm_model.seeded?
|
||||
return render_json_error(I18n.t("discourse_ai.llm.cannot_delete_builtin"), status: 403)
|
||||
end
|
||||
|
||||
in_use_by = DiscourseAi::Configuration::LlmValidator.new.modules_using(llm_model)
|
||||
|
||||
if !in_use_by.empty?
|
||||
return(
|
||||
render_json_error(
|
||||
I18n.t(
|
||||
"discourse_ai.llm.delete_failed",
|
||||
settings: in_use_by.join(", "),
|
||||
count: in_use_by.length,
|
||||
),
|
||||
status: 409,
|
||||
)
|
||||
)
|
||||
end
|
||||
|
||||
# Clean up companion users
|
||||
llm_model.enabled_chat_bot = false
|
||||
llm_model.toggle_companion_user
|
||||
|
||||
if llm_model.destroy
|
||||
head :no_content
|
||||
else
|
||||
render_json_error llm_model
|
||||
end
|
||||
end
|
||||
|
||||
def test
|
||||
RateLimiter.new(current_user, "llm_test_#{current_user.id}", 3, 1.minute).performed!
|
||||
|
||||
llm_model = LlmModel.new(ai_llm_params)
|
||||
|
||||
DiscourseAi::Configuration::LlmValidator.new.run_test(llm_model)
|
||||
|
||||
render json: { success: true }
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed => e
|
||||
render json: { success: false, error: e.message }
|
||||
end
|
||||
|
||||
private
|
||||
|
||||
def ai_llm_params(updating: nil)
|
||||
return {} if params[:ai_llm].blank?
|
||||
|
||||
permitted =
|
||||
params.require(:ai_llm).permit(
|
||||
:display_name,
|
||||
:name,
|
||||
:provider,
|
||||
:tokenizer,
|
||||
:max_prompt_tokens,
|
||||
:api_key,
|
||||
:enabled_chat_bot,
|
||||
:vision_enabled,
|
||||
)
|
||||
|
||||
provider = updating ? updating.provider : permitted[:provider]
|
||||
permit_url = provider != LlmModel::BEDROCK_PROVIDER_NAME
|
||||
|
||||
new_url = params.dig(:ai_llm, :url)
|
||||
permitted[:url] = new_url if permit_url && new_url
|
||||
|
||||
extra_field_names = LlmModel.provider_params.dig(provider&.to_sym)
|
||||
if extra_field_names.present?
|
||||
received_prov_params =
|
||||
params.dig(:ai_llm, :provider_params)&.slice(*extra_field_names.keys)
|
||||
|
||||
if received_prov_params.present?
|
||||
received_prov_params.each do |pname, value|
|
||||
if extra_field_names[pname.to_sym] == :checkbox
|
||||
received_prov_params[pname] = ActiveModel::Type::Boolean.new.cast(value)
|
||||
end
|
||||
end
|
||||
|
||||
permitted[:provider_params] = received_prov_params.permit!
|
||||
end
|
||||
end
|
||||
|
||||
permitted
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -3,10 +3,7 @@
|
||||
module DiscourseAi
|
||||
module Admin
|
||||
class AiPersonasController < ::Admin::AdminController
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
|
||||
before_action :find_ai_persona,
|
||||
only: %i[show update destroy create_user indexing_status_check]
|
||||
before_action :find_ai_persona, only: %i[show update destroy]
|
||||
|
||||
def index
|
||||
ai_personas =
|
||||
@@ -15,23 +12,11 @@ module DiscourseAi
|
||||
# localized for system personas
|
||||
LocalizedAiPersonaSerializer.new(persona, root: false)
|
||||
end
|
||||
tools =
|
||||
DiscourseAi::AiBot::Personas::Persona.all_available_tools.map do |tool|
|
||||
AiToolSerializer.new(tool, root: false)
|
||||
commands =
|
||||
DiscourseAi::AiBot::Personas::Persona.all_available_commands.map do |command|
|
||||
{ id: command.to_s.split("::").last, name: command.name.humanize.titleize }
|
||||
end
|
||||
AiTool
|
||||
.where(enabled: true)
|
||||
.each do |tool|
|
||||
tools << {
|
||||
id: "custom-#{tool.id}",
|
||||
name: I18n.t("discourse_ai.tools.custom_name", name: tool.name.capitalize),
|
||||
}
|
||||
end
|
||||
llms =
|
||||
DiscourseAi::Configuration::LlmEnumerator.values.map do |hash|
|
||||
{ id: hash[:value], name: hash[:name] }
|
||||
end
|
||||
render json: { ai_personas: ai_personas, meta: { tools: tools, llms: llms } }
|
||||
render json: { ai_personas: ai_personas, meta: { commands: commands } }
|
||||
end
|
||||
|
||||
def show
|
||||
@@ -39,29 +24,17 @@ module DiscourseAi
|
||||
end
|
||||
|
||||
def create
|
||||
ai_persona = AiPersona.new(ai_persona_params.except(:rag_uploads))
|
||||
ai_persona = AiPersona.new(ai_persona_params)
|
||||
if ai_persona.save
|
||||
RagDocumentFragment.link_persona_and_uploads(ai_persona, attached_upload_ids)
|
||||
|
||||
render json: {
|
||||
ai_persona: LocalizedAiPersonaSerializer.new(ai_persona, root: false),
|
||||
},
|
||||
status: :created
|
||||
render json: { ai_persona: ai_persona }, status: :created
|
||||
else
|
||||
render_json_error ai_persona
|
||||
end
|
||||
end
|
||||
|
||||
def create_user
|
||||
user = @ai_persona.create_user!
|
||||
render json: BasicUserSerializer.new(user, root: "user")
|
||||
end
|
||||
|
||||
def update
|
||||
if @ai_persona.update(ai_persona_params.except(:rag_uploads))
|
||||
RagDocumentFragment.update_persona_uploads(@ai_persona, attached_upload_ids)
|
||||
|
||||
render json: LocalizedAiPersonaSerializer.new(@ai_persona, root: false)
|
||||
if @ai_persona.update(ai_persona_params)
|
||||
render json: @ai_persona
|
||||
else
|
||||
render_json_error @ai_persona
|
||||
end
|
||||
@@ -75,118 +48,23 @@ module DiscourseAi
|
||||
end
|
||||
end
|
||||
|
||||
def upload_file
|
||||
file = params[:file] || params[:files].first
|
||||
|
||||
if !SiteSetting.ai_embeddings_enabled?
|
||||
raise Discourse::InvalidAccess.new("Embeddings not enabled")
|
||||
end
|
||||
|
||||
validate_extension!(file.original_filename)
|
||||
validate_file_size!(file.tempfile.size)
|
||||
|
||||
hijack do
|
||||
upload =
|
||||
UploadCreator.new(
|
||||
file.tempfile,
|
||||
file.original_filename,
|
||||
type: "discourse_ai_rag_upload",
|
||||
skip_validations: true,
|
||||
).create_for(current_user.id)
|
||||
|
||||
if upload.persisted?
|
||||
render json: UploadSerializer.new(upload)
|
||||
else
|
||||
render json: failed_json.merge(errors: upload.errors.full_messages), status: 422
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def indexing_status_check
|
||||
render json: RagDocumentFragment.indexing_status(@ai_persona, @ai_persona.uploads)
|
||||
end
|
||||
|
||||
private
|
||||
|
||||
def find_ai_persona
|
||||
@ai_persona = AiPersona.find(params[:id])
|
||||
end
|
||||
|
||||
def attached_upload_ids
|
||||
ai_persona_params[:rag_uploads].to_a.map { |h| h[:id] }
|
||||
end
|
||||
|
||||
def ai_persona_params
|
||||
permitted =
|
||||
params.require(:ai_persona).permit(
|
||||
:name,
|
||||
:description,
|
||||
:enabled,
|
||||
:system_prompt,
|
||||
:priority,
|
||||
:top_p,
|
||||
:temperature,
|
||||
:default_llm,
|
||||
:user_id,
|
||||
:mentionable,
|
||||
:max_context_posts,
|
||||
:vision_enabled,
|
||||
:vision_max_pixels,
|
||||
:rag_chunk_tokens,
|
||||
:rag_chunk_overlap_tokens,
|
||||
:rag_conversation_chunks,
|
||||
:question_consolidator_llm,
|
||||
:allow_chat,
|
||||
:tool_details,
|
||||
allowed_group_ids: [],
|
||||
rag_uploads: [:id],
|
||||
)
|
||||
|
||||
if tools = params.dig(:ai_persona, :tools)
|
||||
permitted[:tools] = permit_tools(tools)
|
||||
end
|
||||
|
||||
permitted
|
||||
end
|
||||
|
||||
def permit_tools(tools)
|
||||
return [] if !tools.is_a?(Array)
|
||||
|
||||
tools.filter_map do |tool, options|
|
||||
break nil if !tool.is_a?(String)
|
||||
options&.permit! if options && options.is_a?(ActionController::Parameters)
|
||||
|
||||
if options
|
||||
[tool, options]
|
||||
else
|
||||
tool
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def validate_extension!(filename)
|
||||
extension = File.extname(filename)[1..-1] || ""
|
||||
authorized_extensions = %w[txt md]
|
||||
if !authorized_extensions.include?(extension)
|
||||
raise Discourse::InvalidParameters.new(
|
||||
I18n.t(
|
||||
"upload.unauthorized",
|
||||
authorized_extensions: authorized_extensions.join(" "),
|
||||
),
|
||||
)
|
||||
end
|
||||
end
|
||||
|
||||
def validate_file_size!(filesize)
|
||||
max_size_bytes = 20.megabytes
|
||||
if filesize > max_size_bytes
|
||||
raise Discourse::InvalidParameters.new(
|
||||
I18n.t(
|
||||
"upload.attachments.too_large_humanized",
|
||||
max_size: ActiveSupport::NumberHelper.number_to_human_size(max_size_bytes),
|
||||
),
|
||||
)
|
||||
end
|
||||
params.require(:ai_persona).permit(
|
||||
:name,
|
||||
:description,
|
||||
:enabled,
|
||||
:system_prompt,
|
||||
:enabled,
|
||||
:priority,
|
||||
allowed_group_ids: [],
|
||||
commands: [],
|
||||
)
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -1,89 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module DiscourseAi
|
||||
module Admin
|
||||
class AiToolsController < ::Admin::AdminController
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
|
||||
before_action :find_ai_tool, only: %i[show update destroy]
|
||||
|
||||
def index
|
||||
ai_tools = AiTool.all
|
||||
render_serialized({ ai_tools: ai_tools }, AiCustomToolListSerializer, root: false)
|
||||
end
|
||||
|
||||
def show
|
||||
render_serialized(@ai_tool, AiCustomToolSerializer)
|
||||
end
|
||||
|
||||
def create
|
||||
ai_tool = AiTool.new(ai_tool_params)
|
||||
ai_tool.created_by_id = current_user.id
|
||||
|
||||
if ai_tool.save
|
||||
render_serialized(ai_tool, AiCustomToolSerializer, status: :created)
|
||||
else
|
||||
render_json_error ai_tool
|
||||
end
|
||||
end
|
||||
|
||||
def update
|
||||
if @ai_tool.update(ai_tool_params)
|
||||
render_serialized(@ai_tool, AiCustomToolSerializer)
|
||||
else
|
||||
render_json_error @ai_tool
|
||||
end
|
||||
end
|
||||
|
||||
def destroy
|
||||
if @ai_tool.destroy
|
||||
head :no_content
|
||||
else
|
||||
render_json_error @ai_tool
|
||||
end
|
||||
end
|
||||
|
||||
def test
|
||||
if params[:id].present?
|
||||
ai_tool = AiTool.find(params[:id])
|
||||
else
|
||||
ai_tool = AiTool.new(ai_tool_params)
|
||||
end
|
||||
|
||||
parameters = params[:parameters].to_unsafe_h
|
||||
|
||||
# we need an llm so we have a tokenizer
|
||||
# but will do without if none is available
|
||||
llm = LlmModel.first&.to_llm
|
||||
runner = ai_tool.runner(parameters, llm: llm, bot_user: current_user, context: {})
|
||||
result = runner.invoke
|
||||
|
||||
if result.is_a?(Hash) && result[:error]
|
||||
render_json_error result[:error]
|
||||
else
|
||||
render json: { output: result }
|
||||
end
|
||||
rescue ActiveRecord::RecordNotFound => e
|
||||
render_json_error e.message, status: 400
|
||||
rescue => e
|
||||
render_json_error "Error executing the tool: #{e.message}", status: 400
|
||||
end
|
||||
|
||||
private
|
||||
|
||||
def find_ai_tool
|
||||
@ai_tool = AiTool.find(params[:id])
|
||||
end
|
||||
|
||||
def ai_tool_params
|
||||
params.require(:ai_tool).permit(
|
||||
:name,
|
||||
:description,
|
||||
:script,
|
||||
:summary,
|
||||
parameters: [:name, :type, :description, :required, enum: []],
|
||||
)
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -6,21 +6,6 @@ module DiscourseAi
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
requires_login
|
||||
|
||||
def show_debug_info
|
||||
post = Post.find(params[:post_id])
|
||||
guardian.ensure_can_debug_ai_bot_conversation!(post)
|
||||
|
||||
posts =
|
||||
Post
|
||||
.where("post_number <= ?", post.post_number)
|
||||
.where(topic_id: post.topic_id)
|
||||
.order("post_number DESC")
|
||||
|
||||
debug_info = AiApiAuditLog.where(post: posts).order(created_at: :desc).first
|
||||
|
||||
render json: AiApiAuditLogSerializer.new(debug_info, root: false), status: 200
|
||||
end
|
||||
|
||||
def stop_streaming_response
|
||||
post = Post.find(params[:post_id])
|
||||
guardian.ensure_can_see!(post)
|
||||
@@ -31,10 +16,12 @@ module DiscourseAi
|
||||
end
|
||||
|
||||
def show_bot_username
|
||||
bot_user = DiscourseAi::AiBot::EntryPoint.find_user_from_model(params[:username])
|
||||
raise Discourse::InvalidParameters.new(:username) if !bot_user
|
||||
bot_user_id = DiscourseAi::AiBot::EntryPoint.map_bot_model_to_user_id(params[:username])
|
||||
raise Discourse::InvalidParameters.new(:username) if !bot_user_id
|
||||
|
||||
render json: { bot_username: bot_user.username_lower }, status: 200
|
||||
bot_username_lower = User.find(bot_user_id).username_lower
|
||||
|
||||
render json: { bot_username: bot_username_lower }, status: 200
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -1,111 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module DiscourseAi
|
||||
module AiBot
|
||||
class SharedAiConversationsController < ::ApplicationController
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
requires_login only: %i[create update destroy]
|
||||
before_action :require_site_settings!
|
||||
|
||||
skip_before_action :preload_json, :check_xhr, only: %i[show]
|
||||
|
||||
def create
|
||||
ensure_allowed_create!
|
||||
|
||||
RateLimiter.new(current_user, "share-ai-conversation", 10, 1.minute).performed!
|
||||
|
||||
shared_conversation = SharedAiConversation.share_conversation(current_user, @topic)
|
||||
|
||||
if shared_conversation.persisted?
|
||||
render json: success_json.merge(share_key: shared_conversation.share_key)
|
||||
else
|
||||
render json:
|
||||
failed_json.merge(error: I18n.t("discourse_ai.share_ai.errors.failed_to_share")),
|
||||
status: :unprocessable_entity
|
||||
end
|
||||
end
|
||||
|
||||
def destroy
|
||||
ensure_allowed_destroy!
|
||||
|
||||
SharedAiConversation.destroy_conversation(@shared_conversation)
|
||||
|
||||
render json:
|
||||
success_json.merge(
|
||||
message: I18n.t("discourse_ai.share_ai.errors.conversation_deleted"),
|
||||
)
|
||||
end
|
||||
|
||||
def show
|
||||
@shared_conversation = SharedAiConversation.find_by(share_key: params[:share_key])
|
||||
raise Discourse::NotFound if @shared_conversation.blank?
|
||||
|
||||
expires_in 1.minute, public: true
|
||||
response.headers["X-Robots-Tag"] = "noindex"
|
||||
|
||||
if request.format.json?
|
||||
render json: success_json.merge(@shared_conversation.to_json)
|
||||
else
|
||||
render "show", layout: false
|
||||
end
|
||||
end
|
||||
|
||||
def preview
|
||||
ensure_allowed_preview!
|
||||
data = SharedAiConversation.build_conversation_data(@topic, include_usernames: true)
|
||||
data[:error] = @error if @error
|
||||
data[:share_key] = @shared_conversation.share_key if @shared_conversation
|
||||
data[:topic_id] = @topic.id
|
||||
render json: data
|
||||
end
|
||||
|
||||
private
|
||||
|
||||
def require_site_settings!
|
||||
if !SiteSetting.discourse_ai_enabled ||
|
||||
!SiteSetting.ai_bot_public_sharing_allowed_groups_map.any? ||
|
||||
!SiteSetting.ai_bot_enabled
|
||||
raise Discourse::NotFound
|
||||
end
|
||||
end
|
||||
|
||||
def ensure_allowed_preview!
|
||||
@topic = Topic.find_by(id: params[:topic_id])
|
||||
raise Discourse::NotFound if !@topic
|
||||
|
||||
@shared_conversation = SharedAiConversation.find_by(target: @topic)
|
||||
|
||||
@error = DiscourseAi::AiBot::EntryPoint.ai_share_error(@topic, guardian)
|
||||
if @error == :not_allowed
|
||||
raise Discourse::InvalidAccess.new(
|
||||
nil,
|
||||
nil,
|
||||
custom_message: "discourse_ai.share_ai.errors.#{@error}",
|
||||
)
|
||||
end
|
||||
end
|
||||
|
||||
def ensure_allowed_destroy!
|
||||
@shared_conversation = SharedAiConversation.find_by(share_key: params[:share_key])
|
||||
|
||||
raise Discourse::InvalidAccess if @shared_conversation.blank?
|
||||
|
||||
guardian.ensure_can_destroy_shared_ai_bot_conversation!(@shared_conversation)
|
||||
end
|
||||
|
||||
def ensure_allowed_create!
|
||||
@topic = Topic.find_by(id: params[:topic_id])
|
||||
raise Discourse::NotFound if !@topic
|
||||
|
||||
error = DiscourseAi::AiBot::EntryPoint.ai_share_error(@topic, guardian)
|
||||
if error
|
||||
raise Discourse::InvalidAccess.new(
|
||||
nil,
|
||||
nil,
|
||||
custom_message: "discourse_ai.share_ai.errors.#{error}",
|
||||
)
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -8,35 +8,35 @@ module DiscourseAi
|
||||
before_action :ensure_can_request_suggestions
|
||||
before_action :rate_limiter_performed!, except: %i[prompts]
|
||||
|
||||
include SecureUploadEndpointHelpers
|
||||
def prompts
|
||||
render json:
|
||||
ActiveModel::ArraySerializer.new(
|
||||
DiscourseAi::AiHelper::Assistant.new.available_prompts,
|
||||
root: false,
|
||||
),
|
||||
status: 200
|
||||
end
|
||||
|
||||
def suggest
|
||||
input = get_text_param!
|
||||
force_default_locale = params[:force_default_locale] || false
|
||||
|
||||
prompt = CompletionPrompt.find_by(id: params[:mode])
|
||||
|
||||
raise Discourse::InvalidParameters.new(:mode) if !prompt || !prompt.enabled?
|
||||
|
||||
if prompt.id == CompletionPrompt::CUSTOM_PROMPT
|
||||
raise Discourse::InvalidParameters.new(:custom_prompt) if params[:custom_prompt].blank?
|
||||
|
||||
prompt.custom_instruction = params[:custom_prompt]
|
||||
if prompt.prompt_type == "custom_prompt" && params[:custom_prompt].blank?
|
||||
raise Discourse::InvalidParameters.new(:custom_prompt)
|
||||
end
|
||||
|
||||
suggest_thumbnails(input) if prompt.id == CompletionPrompt::ILLUSTRATE_POST
|
||||
|
||||
hijack do
|
||||
render json:
|
||||
DiscourseAi::AiHelper::Assistant.new.generate_and_send_prompt(
|
||||
prompt,
|
||||
input,
|
||||
current_user,
|
||||
force_default_locale,
|
||||
),
|
||||
status: 200
|
||||
end
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed => e
|
||||
render_json_error I18n.t("discourse_ai.ai_helper.errors.completion_request_failed"),
|
||||
status: 502
|
||||
end
|
||||
@@ -56,7 +56,7 @@ module DiscourseAi
|
||||
),
|
||||
status: 200
|
||||
end
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed => e
|
||||
render_json_error I18n.t("discourse_ai.ai_helper.errors.completion_request_failed"),
|
||||
status: 502
|
||||
end
|
||||
@@ -81,7 +81,9 @@ module DiscourseAi
|
||||
status: 200
|
||||
end
|
||||
|
||||
def suggest_thumbnails(input)
|
||||
def suggest_thumbnails
|
||||
input = get_text_param!
|
||||
|
||||
hijack do
|
||||
thumbnails = DiscourseAi::AiHelper::Painter.new.commission_thumbnails(input, current_user)
|
||||
|
||||
@@ -89,63 +91,20 @@ module DiscourseAi
|
||||
end
|
||||
end
|
||||
|
||||
def stream_suggestion
|
||||
def explain
|
||||
post_id = get_post_param!
|
||||
text = get_text_param!
|
||||
term_to_explain = get_text_param!
|
||||
post = Post.includes(:topic).find_by(id: post_id)
|
||||
prompt = CompletionPrompt.find_by(id: params[:mode])
|
||||
|
||||
raise Discourse::InvalidParameters.new(:mode) if !prompt || !prompt.enabled?
|
||||
raise Discourse::InvalidParameters.new(:post_id) unless post
|
||||
|
||||
if prompt.id == CompletionPrompt::CUSTOM_PROMPT
|
||||
raise Discourse::InvalidParameters.new(:custom_prompt) if params[:custom_prompt].blank?
|
||||
end
|
||||
|
||||
Jobs.enqueue(
|
||||
:stream_post_helper,
|
||||
post_id: post.id,
|
||||
user_id: current_user.id,
|
||||
text: text,
|
||||
prompt: prompt.name,
|
||||
custom_prompt: params[:custom_prompt],
|
||||
)
|
||||
|
||||
render json: { success: true }, status: 200
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed
|
||||
render_json_error I18n.t("discourse_ai.ai_helper.errors.completion_request_failed"),
|
||||
status: 502
|
||||
end
|
||||
|
||||
def caption_image
|
||||
image_url = params[:image_url]
|
||||
image_url_type = params[:image_url_type]
|
||||
|
||||
raise Discourse::InvalidParameters.new(:image_url) if !image_url
|
||||
raise Discourse::InvalidParameters.new(:image_url) if !image_url_type
|
||||
|
||||
if image_url_type == "short_path"
|
||||
image = Upload.find_by(sha1: Upload.sha1_from_short_path(image_url))
|
||||
elsif image_url_type == "short_url"
|
||||
image = Upload.find_by(sha1: Upload.sha1_from_short_url(image_url))
|
||||
else
|
||||
image = upload_from_full_url(image_url)
|
||||
end
|
||||
|
||||
raise Discourse::NotFound if image.blank?
|
||||
|
||||
check_secure_upload_permission(image) if image.secure?
|
||||
user = current_user
|
||||
|
||||
hijack do
|
||||
caption = DiscourseAi::AiHelper::Assistant.new.generate_image_caption(image, user)
|
||||
render json: {
|
||||
caption:
|
||||
"#{caption} (#{I18n.t("discourse_ai.ai_helper.image_caption.attribution")})",
|
||||
},
|
||||
status: 200
|
||||
end
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed, Net::HTTPBadResponse
|
||||
render json:
|
||||
DiscourseAi::AiHelper::TopicHelper.new(current_user).explain(
|
||||
term_to_explain,
|
||||
post,
|
||||
),
|
||||
status: 200
|
||||
rescue DiscourseAi::Completions::Endpoints::Base::CompletionFailed => e
|
||||
render_json_error I18n.t("discourse_ai.ai_helper.errors.completion_request_failed"),
|
||||
status: 502
|
||||
end
|
||||
@@ -165,13 +124,14 @@ module DiscourseAi
|
||||
end
|
||||
|
||||
def ensure_can_request_suggestions
|
||||
allowed_groups =
|
||||
(
|
||||
SiteSetting.composer_ai_helper_allowed_groups_map |
|
||||
SiteSetting.post_ai_helper_allowed_groups_map
|
||||
)
|
||||
user_group_ids = current_user.group_ids
|
||||
|
||||
raise Discourse::InvalidAccess if !current_user.in_any_groups?(allowed_groups)
|
||||
allowed =
|
||||
SiteSetting.ai_helper_allowed_groups_map.any? do |group_id|
|
||||
user_group_ids.include?(group_id)
|
||||
end
|
||||
|
||||
raise Discourse::InvalidAccess if !allowed
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -9,7 +9,6 @@ module DiscourseAi
|
||||
|
||||
def search
|
||||
query = params[:q].to_s
|
||||
skip_hyde = params[:hyde].downcase.to_s == "false" || params[:hyde].to_s == "0"
|
||||
|
||||
if query.length < SiteSetting.min_search_term_length
|
||||
raise Discourse::InvalidParameters.new(:q)
|
||||
@@ -21,7 +20,6 @@ module DiscourseAi
|
||||
term: query,
|
||||
search_context: guardian,
|
||||
use_pg_headlines_for_excerpt: false,
|
||||
can_lazy_load_categories: guardian.can_lazy_load_categories?,
|
||||
)
|
||||
|
||||
semantic_search = DiscourseAi::Embeddings::SemanticSearch.new(guardian)
|
||||
@@ -32,43 +30,12 @@ module DiscourseAi
|
||||
|
||||
hijack do
|
||||
semantic_search
|
||||
.search_for_topics(query, _page = 1, hyde: !skip_hyde)
|
||||
.search_for_topics(query)
|
||||
.each { |topic_post| grouped_results.add(topic_post) }
|
||||
|
||||
render_serialized(grouped_results, GroupedSearchResultSerializer, result: grouped_results)
|
||||
end
|
||||
end
|
||||
|
||||
def quick_search
|
||||
# this search function searches posts (vs: topics)
|
||||
# it requires post embeddings and a reranker
|
||||
# it will not perform a hyde expantion
|
||||
query = params[:q].to_s
|
||||
|
||||
if query.length < SiteSetting.min_search_term_length
|
||||
raise Discourse::InvalidParameters.new(:q)
|
||||
end
|
||||
|
||||
grouped_results =
|
||||
Search::GroupedSearchResults.new(
|
||||
type_filter: SEMANTIC_SEARCH_TYPE,
|
||||
term: query,
|
||||
search_context: guardian,
|
||||
use_pg_headlines_for_excerpt: false,
|
||||
)
|
||||
|
||||
semantic_search = DiscourseAi::Embeddings::SemanticSearch.new(guardian)
|
||||
|
||||
if !semantic_search.cached_query?(query)
|
||||
RateLimiter.new(current_user, "semantic-search", 60, 1.minutes).performed!
|
||||
end
|
||||
|
||||
hijack do
|
||||
semantic_search.quick_search(query).each { |topic_post| grouped_results.add(topic_post) }
|
||||
|
||||
render_serialized(grouped_results, GroupedSearchResultSerializer, result: grouped_results)
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -1,48 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module DiscourseAi
|
||||
module Summarization
|
||||
class ChatSummaryController < ::Chat::ApiController
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
requires_plugin ::Chat::PLUGIN_NAME
|
||||
|
||||
VALID_SINCE_VALUES = [1, 3, 6, 12, 24, 72, 168]
|
||||
|
||||
def show
|
||||
since = params[:since].to_i
|
||||
raise Discourse::InvalidParameters.new(:since) if !VALID_SINCE_VALUES.include?(since)
|
||||
|
||||
channel = ::Chat::Channel.find(params[:channel_id])
|
||||
guardian.ensure_can_join_chat_channel!(channel)
|
||||
|
||||
strategy = DiscourseAi::Summarization.default_strategy
|
||||
raise Discourse::NotFound.new unless strategy
|
||||
|
||||
guardian.ensure_can_request_summary!
|
||||
|
||||
RateLimiter.new(current_user, "channel_summary", 6, 5.minutes).performed!
|
||||
|
||||
hijack do
|
||||
content = { content_title: channel.name }
|
||||
|
||||
content[:contents] = channel
|
||||
.chat_messages
|
||||
.where("chat_messages.created_at > ?", since.hours.ago)
|
||||
.includes(:user)
|
||||
.order(created_at: :asc)
|
||||
.pluck(:id, :username_lower, :message)
|
||||
.map { { id: _1, poster: _2, text: _3 } }
|
||||
|
||||
summarized_text =
|
||||
if content[:contents].empty?
|
||||
I18n.t("discourse_ai.summarization.chat.no_targets")
|
||||
else
|
||||
strategy.summarize(content, current_user).dig(:summary)
|
||||
end
|
||||
|
||||
render json: { summary: summarized_text }
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,49 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module DiscourseAi
|
||||
module Summarization
|
||||
class SummaryController < ::ApplicationController
|
||||
requires_plugin ::DiscourseAi::PLUGIN_NAME
|
||||
|
||||
def show
|
||||
topic = Topic.find(params[:topic_id])
|
||||
guardian.ensure_can_see!(topic)
|
||||
|
||||
raise Discourse::NotFound if !guardian.can_see_summary?(topic)
|
||||
|
||||
RateLimiter.new(current_user, "summary", 6, 5.minutes).performed! if current_user
|
||||
|
||||
opts = params.permit(:skip_age_check)
|
||||
skip_age_check = opts[:skip_age_check] == "true"
|
||||
|
||||
if params[:stream] && current_user
|
||||
cached_summary = DiscourseAi::TopicSummarization.cached_summary(topic, current_user)
|
||||
|
||||
if cached_summary && !skip_age_check
|
||||
render_serialized(cached_summary, AiTopicSummarySerializer)
|
||||
return
|
||||
end
|
||||
|
||||
Jobs.enqueue(
|
||||
:stream_topic_ai_summary,
|
||||
topic_id: topic.id,
|
||||
user_id: current_user.id,
|
||||
skip_age_check: skip_age_check,
|
||||
)
|
||||
|
||||
render json: success_json
|
||||
else
|
||||
hijack do
|
||||
summary =
|
||||
DiscourseAi::TopicSummarization.summarize(
|
||||
topic,
|
||||
current_user,
|
||||
skip_age_check: skip_age_check,
|
||||
)
|
||||
render_serialized(summary, AiTopicSummarySerializer)
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,15 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
module DiscourseAi
|
||||
module AiBot
|
||||
module SharedAiConversationsHelper
|
||||
# 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"
|
||||
|
||||
def share_asset_url(short_path)
|
||||
::UrlHelper.absolute("/plugins/discourse-ai/ai-share/#{short_path}?#{VERSION}")
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,28 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module ::Jobs
|
||||
class CreateAiChatReply < ::Jobs::Base
|
||||
sidekiq_options retry: false
|
||||
|
||||
def execute(args)
|
||||
channel = ::Chat::Channel.find_by(id: args[:channel_id])
|
||||
return if channel.blank?
|
||||
|
||||
message = ::Chat::Message.find_by(id: args[:message_id])
|
||||
return if message.blank?
|
||||
|
||||
personaClass =
|
||||
DiscourseAi::AiBot::Personas::Persona.find_by(id: args[:persona_id], user: message.user)
|
||||
return if personaClass.blank?
|
||||
|
||||
user = User.find_by(id: personaClass.user_id)
|
||||
bot = DiscourseAi::AiBot::Bot.as(user, persona: personaClass.new)
|
||||
|
||||
DiscourseAi::AiBot::Playground.new(bot).reply_to_chat_message(
|
||||
message,
|
||||
channel,
|
||||
args[:context_post_ids],
|
||||
)
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,172 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module ::Jobs
|
||||
class DigestRagUpload < ::Jobs::Base
|
||||
CHUNK_SIZE = 1024
|
||||
CHUNK_OVERLAP = 64
|
||||
MAX_FRAGMENTS = 100_000
|
||||
|
||||
# TODO(roman): Add a way to automatically recover from errors, resulting in unindexed uploads.
|
||||
def execute(args)
|
||||
return if (upload = Upload.find_by(id: args[:upload_id])).nil?
|
||||
return if (ai_persona = AiPersona.find_by(id: args[:ai_persona_id])).nil?
|
||||
|
||||
truncation = DiscourseAi::Embeddings::Strategies::Truncation.new
|
||||
vector_rep =
|
||||
DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(truncation)
|
||||
|
||||
tokenizer = vector_rep.tokenizer
|
||||
chunk_tokens = ai_persona.rag_chunk_tokens
|
||||
overlap_tokens = ai_persona.rag_chunk_overlap_tokens
|
||||
|
||||
fragment_ids = RagDocumentFragment.where(ai_persona: ai_persona, upload: upload).pluck(:id)
|
||||
|
||||
# Check if this is the first time we process this upload.
|
||||
if fragment_ids.empty?
|
||||
document = get_uploaded_file(upload)
|
||||
return if document.nil?
|
||||
|
||||
RagDocumentFragment.publish_status(upload, { total: 0, indexed: 0, left: 0 })
|
||||
|
||||
fragment_ids = []
|
||||
idx = 0
|
||||
|
||||
ActiveRecord::Base.transaction do
|
||||
chunk_document(
|
||||
file: document,
|
||||
tokenizer: tokenizer,
|
||||
chunk_tokens: chunk_tokens,
|
||||
overlap_tokens: overlap_tokens,
|
||||
) do |chunk, metadata|
|
||||
fragment_ids << RagDocumentFragment.create!(
|
||||
ai_persona: ai_persona,
|
||||
fragment: chunk,
|
||||
fragment_number: idx + 1,
|
||||
upload: upload,
|
||||
metadata: metadata,
|
||||
).id
|
||||
|
||||
idx += 1
|
||||
|
||||
if idx > MAX_FRAGMENTS
|
||||
Rails.logger.warn("Upload #{upload.id} has too many fragments, truncating.")
|
||||
break
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
fragment_ids.each_slice(50) do |slice|
|
||||
Jobs.enqueue(:generate_rag_embeddings, fragment_ids: slice)
|
||||
end
|
||||
end
|
||||
|
||||
private
|
||||
|
||||
def chunk_document(file:, tokenizer:, chunk_tokens:, overlap_tokens:)
|
||||
buffer = +""
|
||||
current_metadata = nil
|
||||
done = false
|
||||
overlap = ""
|
||||
|
||||
# generally this will be plenty
|
||||
read_size = chunk_tokens * 10
|
||||
|
||||
while buffer.present? || !done
|
||||
if buffer.length < read_size
|
||||
read = file.read(read_size)
|
||||
done = true if read.nil?
|
||||
|
||||
read = Encodings.to_utf8(read) if read
|
||||
|
||||
buffer << (read || "")
|
||||
end
|
||||
|
||||
# at this point we unconditionally have 2x CHUNK_SIZE worth of data in the buffer
|
||||
metadata_regex = /\[\[metadata (.*?)\]\]/m
|
||||
|
||||
before_metadata, new_metadata, after_metadata = buffer.split(metadata_regex)
|
||||
to_chunk = nil
|
||||
|
||||
if before_metadata.present?
|
||||
to_chunk = before_metadata
|
||||
elsif after_metadata.present?
|
||||
current_metadata = new_metadata
|
||||
to_chunk = after_metadata
|
||||
buffer = buffer.split(metadata_regex, 2).last
|
||||
overlap = ""
|
||||
else
|
||||
current_metadata = new_metadata
|
||||
buffer = buffer.split(metadata_regex, 2).last
|
||||
overlap = ""
|
||||
next
|
||||
end
|
||||
|
||||
chunk, split_char = first_chunk(to_chunk, tokenizer: tokenizer, chunk_tokens: chunk_tokens)
|
||||
buffer = buffer[chunk.length..-1]
|
||||
|
||||
processed_chunk = overlap + chunk
|
||||
|
||||
processed_chunk.strip!
|
||||
processed_chunk.gsub!(/\n[\n]+/, "\n\n")
|
||||
|
||||
yield processed_chunk, current_metadata
|
||||
|
||||
current_chunk_tokens = tokenizer.encode(chunk)
|
||||
overlap_token_ids = current_chunk_tokens[-overlap_tokens..-1] || current_chunk_tokens
|
||||
|
||||
overlap = ""
|
||||
|
||||
while overlap_token_ids.present?
|
||||
begin
|
||||
overlap = tokenizer.decode(overlap_token_ids) + split_char
|
||||
break if overlap.encoding == Encoding::UTF_8
|
||||
rescue StandardError
|
||||
# it is possible that we truncated mid char
|
||||
end
|
||||
overlap_token_ids.shift
|
||||
end
|
||||
|
||||
# remove first word it is probably truncated
|
||||
overlap = overlap.split(" ", 2).last
|
||||
end
|
||||
end
|
||||
|
||||
def first_chunk(text, chunk_tokens:, tokenizer:, splitters: ["\n\n", "\n", ".", ""])
|
||||
return text, " " if tokenizer.tokenize(text).length <= chunk_tokens
|
||||
|
||||
splitters = splitters.find_all { |s| text.include?(s) }.compact
|
||||
|
||||
buffer = +""
|
||||
split_char = nil
|
||||
|
||||
splitters.each do |splitter|
|
||||
split_char = splitter
|
||||
|
||||
text
|
||||
.split(split_char)
|
||||
.each do |part|
|
||||
break if tokenizer.tokenize(buffer + split_char + part).length > chunk_tokens
|
||||
buffer << split_char
|
||||
buffer << part
|
||||
end
|
||||
break if buffer.length > 0
|
||||
end
|
||||
|
||||
[buffer, split_char]
|
||||
end
|
||||
|
||||
def get_uploaded_file(upload)
|
||||
store = Discourse.store
|
||||
@file ||=
|
||||
if store.external?
|
||||
# Upload#filesize could be approximate.
|
||||
# add two extra Mbs to make sure that we'll be able to download the upload.
|
||||
max_filesize = upload.filesize + 2.megabytes
|
||||
store.download(upload, max_file_size_kb: max_filesize)
|
||||
else
|
||||
File.open(store.path_for(upload))
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,26 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module Jobs
|
||||
class GenerateEmbeddings < ::Jobs::Base
|
||||
sidekiq_options queue: "low"
|
||||
|
||||
def execute(args)
|
||||
return unless SiteSetting.ai_embeddings_enabled
|
||||
return if args[:target_type].blank? || args[:target_id].blank?
|
||||
target = args[:target_type].constantize.find_by_id(args[:target_id])
|
||||
return if target.nil? || target.deleted_at.present?
|
||||
|
||||
topic = target.is_a?(Topic) ? target : target.topic
|
||||
post = target.is_a?(Post) ? target : target.first_post
|
||||
return if topic.blank? || post.blank?
|
||||
return if topic.private_message? && !SiteSetting.ai_embeddings_generate_for_pms
|
||||
return if post.raw.blank?
|
||||
|
||||
strategy = DiscourseAi::Embeddings::Strategies::Truncation.new
|
||||
vector_rep =
|
||||
DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)
|
||||
|
||||
vector_rep.generate_representation_from(target)
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,27 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module ::Jobs
|
||||
class GenerateRagEmbeddings < ::Jobs::Base
|
||||
sidekiq_options queue: "ultra_low"
|
||||
# we could also restrict concurrency but this takes so long if it is not concurrent
|
||||
|
||||
def execute(args)
|
||||
return if (fragments = RagDocumentFragment.where(id: args[:fragment_ids].to_a)).empty?
|
||||
|
||||
truncation = DiscourseAi::Embeddings::Strategies::Truncation.new
|
||||
vector_rep =
|
||||
DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(truncation)
|
||||
|
||||
# generate_representation_from checks compares the digest value to make sure
|
||||
# the embedding is only generated once per fragment unless something changes.
|
||||
fragments.map { |fragment| vector_rep.generate_representation_from(fragment) }
|
||||
|
||||
last_fragment = fragments.last
|
||||
ai_persona = last_fragment.ai_persona
|
||||
upload = last_fragment.upload
|
||||
|
||||
indexing_status = RagDocumentFragment.indexing_status(ai_persona, [upload])[upload.id]
|
||||
RagDocumentFragment.publish_status(upload, indexing_status)
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -1,51 +0,0 @@
|
||||
# frozen_string_literal: true
|
||||
|
||||
module ::Jobs
|
||||
class SharedConversationAdjustUploadSecurity < ::Jobs::Base
|
||||
def execute(args)
|
||||
if args[:conversation_id].present?
|
||||
# The conversation context includes post cooked content so this
|
||||
# must be updated when target uploads security changes.
|
||||
update_conversation(args[:conversation_id])
|
||||
elsif args[:target_id].present? && args[:target_type].present?
|
||||
# If we deleted the conversation then we just need to update the target's
|
||||
# uploads security, no need to update the conversation.
|
||||
update_target(args[:target_id], args[:target_type])
|
||||
end
|
||||
end
|
||||
|
||||
private
|
||||
|
||||
def update_conversation(conversation_id)
|
||||
conversation = SharedAiConversation.find_by(id: conversation_id)
|
||||
return if conversation.blank?
|
||||
|
||||
# NOTE: Only Topics are supported for now, in future we will need a more flexible
|
||||
# way of doing this.
|
||||
if conversation.target_type == "Topic"
|
||||
rebaked_posts = TopicUploadSecurityManager.new(conversation.target).run
|
||||
|
||||
if rebaked_posts.any?
|
||||
new_context =
|
||||
conversation.context.map do |context_post|
|
||||
rebaked_post = rebaked_posts.find { |p| p.id == context_post["id"] }
|
||||
context_post["cooked"] = rebaked_post.cooked if rebaked_post
|
||||
context_post
|
||||
end
|
||||
|
||||
conversation.update(context: new_context)
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def update_target(target_id, target_type)
|
||||
# NOTE: Only Topics are supported for now, in future we will need a more flexible
|
||||
# way of doing this.
|
||||
if target_type == "Topic"
|
||||
topic = target_type.constantize.find_by(id: target_id)
|
||||
return if topic.blank?
|
||||
TopicUploadSecurityManager.new(topic).run
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user