Merge branch 'main' into assistants-page

Author: krschacht

README.md

@@ -368,6 +368,46 @@ HostedGPT requires these services to be running:
 
 Every time you pull new changes down, kill `bin/dev` and then re-run it. This will ensure your local app picks up changes to Gemfile and migrations.
 
+## Language models
+
+Each User has their own list of Language Models they can use.
+
+When a new User is created (when a person registers for the first time), they are initialized with a long list of models. This list is loaded from `models.yml`.
+
+When an administrator upgrades their deployment of HostedGPT, they can update the available models for all users with a task `rails models:import`.
+
+### Refreshing language models
+
+There is a shared list of known LLM models for OpenAI, Anthropic, and Groq in `models.yml` and a Rake task to import them into all users:
+
+```plain
+rails models:import
+```
+
+### Update models.yml
+
+The `models.yml` file in the root of the project is used by HostedGPT applications to refresh their local list of models.
+
+To refresh the `models.yml` file using the models in local DB, run:
+
+```plain
+rails models:export
+```
+
+### Alternate export file
+
+If you want to export the models in the local DB to another file, either `.json` or `.yaml`, pass in an argument:
+
+```plain
+rails models:export[tmp/models.json]
+```
+
+To import from another file, similarly provide the path as an argument:
+
+```plain
+rails models:import[tmp/models.json]
+```
+
 ### Running tests
 
 If you're set up with Docker you run `docker compose run base rails test`. Note that the system tests, which use a headless browser, are not able to run in Docker. They will be run automatically for you if you create a Pull Request against the project.

app/controllers/settings/memories_controller.rb

@@ -1,10 +1,23 @@
 class Settings::MemoriesController < Settings::ApplicationController
+  before_action :set_memory, only: :destroy
+
   def index
     @memories = Current.user.memories.includes(:message)
   end
 
   def destroy
+    @memory.destroy!
+    redirect_to settings_memories_url, notice: "Forgotten", status: :see_other
+  end
+
+  def destroy_all
     Current.user.memories.delete_all
     redirect_to settings_memories_url, notice: "Cleared memory", status: :see_other
   end
+
+  private
+
+  def set_memory
+    @memory = Current.user.memories.find_by(id: params[:id])
+  end
 end

app/models/language_model.rb

@@ -1,5 +1,7 @@
 # We don"t care about large or not
 class LanguageModel < ApplicationRecord
+  include Export
+
   belongs_to :user
   belongs_to :api_service
 
@@ -18,6 +20,7 @@ class LanguageModel < ApplicationRecord
   scope :best_for_api_service, ->(api_service) { where(best: true, api_service: api_service) }
 
   delegate :ai_backend, to: :api_service
+  delegate :name, to: :api_service, prefix: true, allow_nil: true
 
   def created_by_current_user?
     user == Current.user

app/models/language_model/export.rb

@@ -0,0 +1,58 @@
+module LanguageModel::Export
+  extend ActiveSupport::Concern
+
+  DEFAULT_EXPORT_ONLY = %i[
+    api_name
+    name
+    best
+    api_service_name
+    supports_images
+    supports_tools
+    supports_system_message
+    input_token_cost_cents
+    output_token_cost_cents
+  ]
+
+  DEFAULT_MODEL_FILE = "models.yml"
+
+  def attributes
+    super.merge("api_service_name" => api_service_name)
+  end
+
+  # Unsure why this needs to re-defined, but the original ActiveModel::Serialization
+  # implementation is ignoring the #attributes method above.
+  def attribute_names_for_serialization
+    attributes.keys
+  end
+
+  class_methods do
+    def export_to_file(path: Rails.root.join(LanguageModel::Export::DEFAULT_MODEL_FILE), models:, only: DEFAULT_EXPORT_ONLY)
+      path = path.to_s
+      storage = {
+        "models" => models.as_json(only:)
+      }
+      if path.ends_with?(".json")
+        File.write(path, storage.to_json)
+      else
+        File.write(path, storage.to_yaml)
+      end
+    end
+
+    def import_from_file(path: Rails.root.join(LanguageModel::Export::DEFAULT_MODEL_FILE), users: User.all)
+      users = Array.wrap(users)
+      storage = YAML.load_file(path)
+      models = storage["models"]
+      models.each do |model|
+        model = model.with_indifferent_access
+        users.each do |user|
+          lm = user.language_models.find_or_initialize_by(api_name: model[:api_name])
+          lm.api_service = user.api_services.find_by(name: model[:api_service_name]) if model[:api_service_name]
+          lm.attributes = model.except(:api_service_name)
+          lm.save!
+        rescue ActiveRecord::RecordInvalid => e
+          warn "Failed to import '#{model[:api_name]}': #{e.message} for #{model.inspect}"
+        end
+      end
+    end
+  end
+end

app/models/user/registerable.rb

@@ -12,68 +12,7 @@ def create_initial_assistants_etc
     anthropic_api_service = api_services.create!(url: APIService::URL_ANTHROPIC, driver: :anthropic, name: "Anthropic")
     groq_api_service = api_services.create!(url: APIService::URL_GROQ, driver: :openai, name: "Groq")
 
-    best_models = %w[gpt-4o claude-3-5-sonnet-20240620 llama3-70b-8192]
-    [
-      ["gpt-4o", "GPT-4o (latest)", true, open_ai_api_service, 250, 1000],
-      ["gpt-4o-2024-08-06", "GPT-4o Omni Multimodal (2024-08-06)", true, open_ai_api_service, 250, 1000],
-      ["gpt-4o-2024-05-13", "GPT-4o Omni Multimodal (2024-05-13)", true, open_ai_api_service, 500, 1500],
-
-      ["gpt-4-turbo", "GPT-4 Turbo with Vision (latest)", true, open_ai_api_service, 1000, 3000],
-      ["gpt-4-turbo-2024-04-09", "GPT-4 Turbo with Vision (2024-04-09)", true, open_ai_api_service, 1000, 3000],
-      ["gpt-4-turbo-preview", "GPT-4 Turbo Preview", false, open_ai_api_service, 1000, 3000],
-      ["gpt-4-0125-preview", "GPT-4 Turbo Preview (2024-01-25)", false, open_ai_api_service, 1000, 3000],
-      ["gpt-4-1106-preview", "GPT-4 Turbo Preview (2023-11-06)", false, open_ai_api_service, 1000, 3000],
-      ["gpt-4-vision-preview", "GPT-4 Turbo with Vision Preview (2023-11-06)", true, open_ai_api_service, 1000, 3000],
-      ["gpt-4-1106-vision-preview", "GPT-4 Turbo with Vision Preview (2023-11-06)", true, open_ai_api_service, 1000, 3000],
-
-      ["gpt-4", "GPT-4 (latest)", false, open_ai_api_service, 3000, 6000],
-      ["gpt-4-0613", "GPT-4 Snapshot improved function calling (2023-06-13)", false, open_ai_api_service, 1000, 3000],
-
-      ["gpt-3.5-turbo", "GPT-3.5 Turbo (latest)", false, open_ai_api_service, 300, 600],
-      ["gpt-3.5-turbo-0125", "GPT-3.5 Turbo (2022-01-25)", false, open_ai_api_service, 50, 150],
-      ["gpt-3.5-turbo-1106", "GPT-3.5 Turbo (2022-11-06)", false, open_ai_api_service, 100, 200],
-
-      ["claude-3-5-sonnet-20240620", "Claude 3.5 Sonnet (2024-06-20)", true, anthropic_api_service, 300, 1500],
-      ["claude-3-opus-20240229", "Claude 3 Opus (2024-02-29)", true, anthropic_api_service, 1500, 7500],
-      ["claude-3-sonnet-20240229", "Claude 3 Sonnet (2024-02-29)", true, anthropic_api_service, 300, 1500],
-      ["claude-3-haiku-20240307", "Claude 3 Haiku (2024-03-07)", true, anthropic_api_service, 25, 125],
-      ["claude-2.1", "Claude 2.1", false, anthropic_api_service, 800, 2400],
-      ["claude-2.0", "Claude 2.0", false, anthropic_api_service, 800, 2400],
-      ["claude-instant-1.2", "Claude Instant 1.2", false, anthropic_api_service, 80, 240],
-
-      ["llama3-70b-8192", "Meta Llama 3 70b", false, groq_api_service, 59, 79],
-      ["llama3-8b-8192", "Meta Llama 3 8b", false, groq_api_service, 5, 8],
-      ["mixtral-8x7b-32768", "Mistral 8 7b", false, groq_api_service, 24, 24],
-      ["gemma-7b-it", "Google Gemma 7b", false, groq_api_service, 7, 7],
-    ].each do |api_name, name, supports_images, api_service, input_token_cost_per_million, output_token_cost_per_million|
-      million = BigDecimal(1_000_000)
-      input_token_cost_cents = input_token_cost_per_million/million
-      output_token_cost_cents = output_token_cost_per_million/million
-
-      language_models.create!(
-        api_name:,
-        api_service:,
-        name:,
-        best: best_models.include?(api_name),
-        supports_tools: true,
-        supports_system_message: true,
-        supports_images:,
-        input_token_cost_cents:,
-        output_token_cost_cents:,
-      )
-    end
-
-    # Only these don't support tools:
-    [
-      ["gpt-3.5-turbo-instruct", "GPT-3.5 Turbo Instruct", false, open_ai_api_service, 150, 200],
-      ["gpt-3.5-turbo-16k-0613", "GPT-3.5 Turbo (2022-06-13)", false, open_ai_api_service, 300, 400],
-    ].each do |api_name, name, supports_images, api_service, input_token_cost_per_million, output_token_cost_per_million|
-      million = BigDecimal(1_000_000)
-      input_token_cost_cents = input_token_cost_per_million/million
-      output_token_cost_cents = output_token_cost_per_million/million
-
-      language_models.create!(api_name:, api_service:, name:, supports_tools: false, supports_system_message: false, supports_images:, input_token_cost_cents:, output_token_cost_cents:)
-    end
+    LanguageModel.import_from_file(users: [self])
 
     [
       ["GPT-4o", open_ai_api_service],

app/views/settings/memories/_memory.html.erb

@@ -1,4 +1,20 @@
-<li class="list-disc py-1">
-  <%= memory.detail %>
-  <%= link_to_source(memory).html_safe %>
-</li>
+<tr class="py-1 <%= cycle('bg-gray-100 dark:bg-gray-600', 'bg-white dark:bg-gray-900') %>">
+  <td>
+    <%= memory.detail %>
+    <%= link_to_source(memory).html_safe if memory.message.present? %>
+  </td>
+  <td>
+    <%= button_to settings_memory_path(memory), method: :delete, class: "inline-block cursor-pointer py-1 pt-0 align-middle" do %>
+      <%= icon "trash",
+        variant: :outline,
+        size: 22,
+        class: %|
+          stroke-2
+          text-zinc-600 group-hover:text-zinc-900 dark:text-zinc-400 dark:group-hover:text-white
+          |,
+          title: "Forget",
+          tooltip: :bottom
+      %>
+    <% end %>
+  </td>
+</tr>

app/views/settings/memories/index.html.erb

@@ -25,8 +25,14 @@
     <% end %>
   </p>
 
-  <ul class="pl-6">
+  <table id="memories" class="w-full table-auto border-b border-gray-300 dark:border-b-0">
+    <thead>
+      <tr class="bg-gray-200 dark:bg-gray-900">
+        <th>Memory</th>
+        <th></th>
+      </tr>
+    </thead>
     <%= render @memories %>
-  </ul>
+  </table>
 
 </div>

config/routes.rb

@@ -18,8 +18,8 @@
     resource :person, only: [:edit, :update]
     resources :language_models
     resources :api_services, except: [:show]
-    resources :memories, only: [:index] do
-      delete :destroy, on: :collection
+    resources :memories, only: [:index, :destroy] do
+      delete :destroy, to: 'memories#destroy_all', on: :collection
     end
   end
 

db/migrate/20240624100000_add_groq.rb

@@ -7,28 +7,8 @@ def up
 
     User.all.find_each do |user|
       groq_api_service = user.api_services.create!(url: APIService::URL_GROQ, driver: :openai, name: "Groq")
-      language_model = user.language_models.create!(position: 3, api_name: LanguageModel::BEST_GROQ, api_service: groq_api_service, name: "Best Open-Source Model", supports_images: false)
-      user.language_models.where("position >= 3").where.not(id: language_model.id).find_each do |model|
-        model.update(position: model.position + 1)
-      end
 
-      [
-        ["llama3-70b-8192", "Meta Llama 3 70b", false, groq_api_service],
-        ["llama3-8b-8192", "Meta Llama 3 8b", false, groq_api_service],
-        ["mixtral-8x7b-32768", "Mistral 8 7b", false, groq_api_service],
-        ["gemma-7b-it", "Google Gemma 7b", false, groq_api_service],
-      ].each do |api_name, name, supports_images, api_service|
-        user.language_models.create!(api_name: api_name, api_service: api_service, name: name, supports_images: supports_images)
-      end
-
-      [ "GPT-3.5", "Claude 3 Opus" ].each do |name|
-        asst = user.assistants.find_by(name: name)
-        next if asst.nil?
-        asst.deleted! if asst.conversations.count == 0
-        asst.deleted! if asst.conversations.count == 1 && asst.conversations.first.messages.count <= 2
-      end
-
-      user.assistants.create!(name: "Meta Llama 3 70b", language_model: language_model)
+      user.assistants.create! name: "Meta Llama 3 70b", language_model: language_models.best_for_api_service(groq_api_service).first
     end
   end