discourse-ai/spec/models/ai_persona_spec.rb

324 lines
9.6 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
RSpec.describe AiPersona do
subject(:basic_persona) do
AiPersona.new(
name: "test",
description: "test",
system_prompt: "test",
tools: [],
allowed_group_ids: [],
)
end
FEATURE: PDF support for rag pipeline (#1118) This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes: **1. LLM Model Association for RAG and Personas:** - **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`. - **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter. - **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes. - **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector. - **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes. **2. PDF and Image Support for RAG:** - **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`. - **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled. - **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced. - **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs. - **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments. - **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types. **3. Refactoring and Improvements:** - **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend. - **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility. - **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based. - **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing. - **Eval Script:** An evaluation script is included. **4. Testing:** - The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
2025-02-14 12:15:07 +11:00
fab!(:llm_model)
fab!(:seeded_llm_model) { Fabricate(:llm_model, id: -1) }
it "validates context settings" do
expect(basic_persona.valid?).to eq(true)
basic_persona.max_context_posts = 0
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:max_context_posts]).to eq(["must be greater than 0"])
basic_persona.max_context_posts = 1
expect(basic_persona.valid?).to eq(true)
basic_persona.max_context_posts = nil
expect(basic_persona.valid?).to eq(true)
end
it "validates tools" do
Fabricate(:ai_tool, id: 1)
Fabricate(:ai_tool, id: 2, name: "Archie search", tool_name: "search")
expect(basic_persona.valid?).to eq(true)
basic_persona.tools = %w[search image_generation]
expect(basic_persona.valid?).to eq(true)
basic_persona.tools = %w[search image_generation search]
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:tools]).to eq(["Can not have duplicate tools"])
basic_persona.tools = [
["custom-1", { test: "test" }, false],
["custom-2", { test: "test" }, false],
]
expect(basic_persona.valid?).to eq(true)
expect(basic_persona.errors[:tools]).to eq([])
basic_persona.tools = [
["custom-1", { test: "test" }, false],
["custom-1", { test: "test" }, false],
]
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:tools]).to eq(["Can not have duplicate tools"])
basic_persona.tools = [
["custom-1", { test: "test" }, false],
["custom-2", { test: "test" }, false],
"image_generation",
]
expect(basic_persona.valid?).to eq(true)
expect(basic_persona.errors[:tools]).to eq([])
basic_persona.tools = [
["custom-1", { test: "test" }, false],
["custom-2", { test: "test" }, false],
"Search",
]
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:tools]).to eq(["Can not have duplicate tools"])
end
it "allows creation of user" do
user = basic_persona.create_user!
expect(user.username).to eq("test_bot")
expect(user.name).to eq("Test")
expect(user.bot?).to be(true)
expect(user.id).to be <= AiPersona::FIRST_PERSONA_USER_ID
end
it "removes all rag embeddings when rag params change" do
persona =
AiPersona.create!(
name: "test",
description: "test",
system_prompt: "test",
tools: [],
allowed_group_ids: [],
rag_chunk_tokens: 10,
rag_chunk_overlap_tokens: 5,
)
id =
RagDocumentFragment.create!(
target: persona,
fragment: "test",
fragment_number: 1,
upload: Fabricate(:upload),
).id
persona.rag_chunk_tokens = 20
persona.save!
expect(RagDocumentFragment.exists?(id)).to eq(false)
end
it "defines singleton methods on system persona classes" do
forum_helper = AiPersona.find_by(name: "Forum Helper")
forum_helper.update!(
user_id: 1,
FEATURE: PDF support for rag pipeline (#1118) This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes: **1. LLM Model Association for RAG and Personas:** - **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`. - **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter. - **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes. - **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector. - **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes. **2. PDF and Image Support for RAG:** - **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`. - **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled. - **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced. - **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs. - **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments. - **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types. **3. Refactoring and Improvements:** - **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend. - **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility. - **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based. - **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing. - **Eval Script:** An evaluation script is included. **4. Testing:** - The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
2025-02-14 12:15:07 +11:00
default_llm_id: llm_model.id,
max_context_posts: 3,
allow_topic_mentions: true,
allow_personal_messages: true,
allow_chat_channel_mentions: true,
allow_chat_direct_messages: true,
)
klass = forum_helper.class_instance
expect(klass.id).to eq(forum_helper.id)
expect(klass.system).to eq(true)
# tl 0 by default
expect(klass.allowed_group_ids).to eq([10])
expect(klass.user_id).to eq(1)
FEATURE: PDF support for rag pipeline (#1118) This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes: **1. LLM Model Association for RAG and Personas:** - **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`. - **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter. - **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes. - **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector. - **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes. **2. PDF and Image Support for RAG:** - **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`. - **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled. - **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced. - **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs. - **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments. - **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types. **3. Refactoring and Improvements:** - **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend. - **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility. - **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based. - **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing. - **Eval Script:** An evaluation script is included. **4. Testing:** - The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
2025-02-14 12:15:07 +11:00
expect(klass.default_llm_id).to eq(llm_model.id)
expect(klass.max_context_posts).to eq(3)
expect(klass.allow_topic_mentions).to eq(true)
expect(klass.allow_personal_messages).to eq(true)
expect(klass.allow_chat_channel_mentions).to eq(true)
expect(klass.allow_chat_direct_messages).to eq(true)
end
it "defines singleton methods non persona classes" do
persona =
AiPersona.create!(
name: "test",
description: "test",
system_prompt: "test",
tools: [],
allowed_group_ids: [],
FEATURE: PDF support for rag pipeline (#1118) This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes: **1. LLM Model Association for RAG and Personas:** - **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`. - **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter. - **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes. - **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector. - **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes. **2. PDF and Image Support for RAG:** - **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`. - **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled. - **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced. - **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs. - **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments. - **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types. **3. Refactoring and Improvements:** - **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend. - **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility. - **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based. - **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing. - **Eval Script:** An evaluation script is included. **4. Testing:** - The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
2025-02-14 12:15:07 +11:00
default_llm_id: llm_model.id,
max_context_posts: 3,
allow_topic_mentions: true,
allow_personal_messages: true,
allow_chat_channel_mentions: true,
allow_chat_direct_messages: true,
user_id: 1,
)
klass = persona.class_instance
expect(klass.id).to eq(persona.id)
expect(klass.system).to eq(false)
expect(klass.allowed_group_ids).to eq([])
expect(klass.user_id).to eq(1)
FEATURE: PDF support for rag pipeline (#1118) This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes: **1. LLM Model Association for RAG and Personas:** - **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`. - **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter. - **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes. - **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector. - **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes. **2. PDF and Image Support for RAG:** - **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`. - **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled. - **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced. - **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs. - **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments. - **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types. **3. Refactoring and Improvements:** - **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend. - **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility. - **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based. - **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing. - **Eval Script:** An evaluation script is included. **4. Testing:** - The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
2025-02-14 12:15:07 +11:00
expect(klass.default_llm_id).to eq(llm_model.id)
expect(klass.max_context_posts).to eq(3)
expect(klass.allow_topic_mentions).to eq(true)
expect(klass.allow_personal_messages).to eq(true)
expect(klass.allow_chat_channel_mentions).to eq(true)
expect(klass.allow_chat_direct_messages).to eq(true)
end
it "does not allow setting allowing chat without a default_llm" do
persona =
AiPersona.create(
name: "test",
description: "test",
system_prompt: "test",
allowed_group_ids: [],
default_llm: nil,
allow_chat_channel_mentions: true,
)
expect(persona.valid?).to eq(false)
expect(persona.errors[:default_llm].first).to eq(
I18n.t("discourse_ai.ai_bot.personas.default_llm_required"),
)
persona =
AiPersona.create(
name: "test",
description: "test",
system_prompt: "test",
allowed_group_ids: [],
default_llm: nil,
allow_chat_direct_messages: true,
)
expect(persona.valid?).to eq(false)
expect(persona.errors[:default_llm].first).to eq(
I18n.t("discourse_ai.ai_bot.personas.default_llm_required"),
)
persona =
AiPersona.create(
name: "test",
description: "test",
system_prompt: "test",
allowed_group_ids: [],
default_llm: nil,
allow_topic_mentions: true,
)
expect(persona.valid?).to eq(false)
expect(persona.errors[:default_llm].first).to eq(
I18n.t("discourse_ai.ai_bot.personas.default_llm_required"),
)
end
it "validates allowed seeded model" do
basic_persona.default_llm_id = seeded_llm_model.id
SiteSetting.ai_bot_allowed_seeded_models = ""
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:default_llm]).to include(
I18n.t("discourse_ai.llm.configuration.invalid_seeded_model"),
)
SiteSetting.ai_bot_allowed_seeded_models = "-1"
expect(basic_persona.valid?).to eq(true)
end
it "does not leak caches between sites" do
AiPersona.create!(
name: "pun_bot",
description: "you write puns",
system_prompt: "you are pun bot",
tools: ["ImageCommand"],
allowed_group_ids: [Group::AUTO_GROUPS[:trust_level_0]],
)
AiPersona.all_personas
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 16:56:43 +11:00
expect(AiPersona.persona_cache[:value].length).to be > (0)
RailsMultisite::ConnectionManagement.stubs(:current_db) { "abc" }
expect(AiPersona.persona_cache[:value]).to eq(nil)
end
DEV: artifact system update (#1096) ### Why This pull request fundamentally restructures how AI bots create and update web artifacts to address critical limitations in the previous approach: 1. **Improved Artifact Context for LLMs**: Previously, artifact creation and update tools included the *entire* artifact source code directly in the tool arguments. This overloaded the Language Model (LLM) with raw code, making it difficult for the LLM to maintain a clear understanding of the artifact's current state when applying changes. The LLM would struggle to differentiate between the base artifact and the requested modifications, leading to confusion and less effective updates. 2. **Reduced Token Usage and History Bloat**: Including the full artifact source code in every tool interaction was extremely token-inefficient. As conversations progressed, this redundant code in the history consumed a significant number of tokens unnecessarily. This not only increased costs but also diluted the context for the LLM with less relevant historical information. 3. **Enabling Updates for Large Artifacts**: The lack of a practical diff or targeted update mechanism made it nearly impossible to efficiently update larger web artifacts. Sending the entire source code for every minor change was both computationally expensive and prone to errors, effectively blocking the use of AI bots for meaningful modifications of complex artifacts. **This pull request addresses these core issues by**: * Introducing methods for the AI bot to explicitly *read* and understand the current state of an artifact. * Implementing efficient update strategies that send *targeted* changes rather than the entire artifact source code. * Providing options to control the level of artifact context included in LLM prompts, optimizing token usage. ### What The main changes implemented in this PR to resolve the above issues are: 1. **`Read Artifact` Tool for Contextual Awareness**: - A new `read_artifact` tool is introduced, enabling AI bots to fetch and process the current content of a web artifact from a given URL (local or external). - This provides the LLM with a clear and up-to-date representation of the artifact's HTML, CSS, and JavaScript, improving its understanding of the base to be modified. - By cloning local artifacts, it allows the bot to work with a fresh copy, further enhancing context and control. 2. **Refactored `Update Artifact` Tool with Efficient Strategies**: - The `update_artifact` tool is redesigned to employ more efficient update strategies, minimizing token usage and improving update precision: - **`diff` strategy**: Utilizes a search-and-replace diff algorithm to apply only the necessary, targeted changes to the artifact's code. This significantly reduces the amount of code sent to the LLM and focuses its attention on the specific modifications. - **`full` strategy**: Provides the option to replace the entire content sections (HTML, CSS, JavaScript) when a complete rewrite is required. - Tool options enhance the control over the update process: - `editor_llm`: Allows selection of a specific LLM for artifact updates, potentially optimizing for code editing tasks. - `update_algorithm`: Enables choosing between `diff` and `full` update strategies based on the nature of the required changes. - `do_not_echo_artifact`: Defaults to true, and by *not* echoing the artifact in prompts, it further reduces token consumption in scenarios where the LLM might not need the full artifact context for every update step (though effectiveness might be slightly reduced in certain update scenarios). 3. **System and General Persona Tool Option Visibility and Customization**: - Tool options, including those for system personas, are made visible and editable in the admin UI. This allows administrators to fine-tune the behavior of all personas and their tools, including setting specific LLMs or update algorithms. This was previously limited or hidden for system personas. 4. **Centralized and Improved Content Security Policy (CSP) Management**: - The CSP for AI artifacts is consolidated and made more maintainable through the `ALLOWED_CDN_SOURCES` constant. This improves code organization and future updates to the allowed CDN list, while maintaining the existing security posture. 5. **Codebase Improvements**: - Refactoring of diff utilities, introduction of strategy classes, enhanced error handling, new locales, and comprehensive testing all contribute to a more robust, efficient, and maintainable artifact management system. By addressing the issues of LLM context confusion, token inefficiency, and the limitations of updating large artifacts, this pull request significantly improves the practicality and effectiveness of AI bots in managing web artifacts within Discourse.
2025-02-04 16:27:27 +11:00
describe "system persona validations" do
let(:system_persona) do
AiPersona.create!(
name: "system_persona",
description: "system persona",
system_prompt: "system persona",
tools: %w[Search Time],
response_format: [{ key: "summary", type: "string" }],
examples: [%w[user_msg1 assistant_msg1], %w[user_msg2 assistant_msg2]],
DEV: artifact system update (#1096) ### Why This pull request fundamentally restructures how AI bots create and update web artifacts to address critical limitations in the previous approach: 1. **Improved Artifact Context for LLMs**: Previously, artifact creation and update tools included the *entire* artifact source code directly in the tool arguments. This overloaded the Language Model (LLM) with raw code, making it difficult for the LLM to maintain a clear understanding of the artifact's current state when applying changes. The LLM would struggle to differentiate between the base artifact and the requested modifications, leading to confusion and less effective updates. 2. **Reduced Token Usage and History Bloat**: Including the full artifact source code in every tool interaction was extremely token-inefficient. As conversations progressed, this redundant code in the history consumed a significant number of tokens unnecessarily. This not only increased costs but also diluted the context for the LLM with less relevant historical information. 3. **Enabling Updates for Large Artifacts**: The lack of a practical diff or targeted update mechanism made it nearly impossible to efficiently update larger web artifacts. Sending the entire source code for every minor change was both computationally expensive and prone to errors, effectively blocking the use of AI bots for meaningful modifications of complex artifacts. **This pull request addresses these core issues by**: * Introducing methods for the AI bot to explicitly *read* and understand the current state of an artifact. * Implementing efficient update strategies that send *targeted* changes rather than the entire artifact source code. * Providing options to control the level of artifact context included in LLM prompts, optimizing token usage. ### What The main changes implemented in this PR to resolve the above issues are: 1. **`Read Artifact` Tool for Contextual Awareness**: - A new `read_artifact` tool is introduced, enabling AI bots to fetch and process the current content of a web artifact from a given URL (local or external). - This provides the LLM with a clear and up-to-date representation of the artifact's HTML, CSS, and JavaScript, improving its understanding of the base to be modified. - By cloning local artifacts, it allows the bot to work with a fresh copy, further enhancing context and control. 2. **Refactored `Update Artifact` Tool with Efficient Strategies**: - The `update_artifact` tool is redesigned to employ more efficient update strategies, minimizing token usage and improving update precision: - **`diff` strategy**: Utilizes a search-and-replace diff algorithm to apply only the necessary, targeted changes to the artifact's code. This significantly reduces the amount of code sent to the LLM and focuses its attention on the specific modifications. - **`full` strategy**: Provides the option to replace the entire content sections (HTML, CSS, JavaScript) when a complete rewrite is required. - Tool options enhance the control over the update process: - `editor_llm`: Allows selection of a specific LLM for artifact updates, potentially optimizing for code editing tasks. - `update_algorithm`: Enables choosing between `diff` and `full` update strategies based on the nature of the required changes. - `do_not_echo_artifact`: Defaults to true, and by *not* echoing the artifact in prompts, it further reduces token consumption in scenarios where the LLM might not need the full artifact context for every update step (though effectiveness might be slightly reduced in certain update scenarios). 3. **System and General Persona Tool Option Visibility and Customization**: - Tool options, including those for system personas, are made visible and editable in the admin UI. This allows administrators to fine-tune the behavior of all personas and their tools, including setting specific LLMs or update algorithms. This was previously limited or hidden for system personas. 4. **Centralized and Improved Content Security Policy (CSP) Management**: - The CSP for AI artifacts is consolidated and made more maintainable through the `ALLOWED_CDN_SOURCES` constant. This improves code organization and future updates to the allowed CDN list, while maintaining the existing security posture. 5. **Codebase Improvements**: - Refactoring of diff utilities, introduction of strategy classes, enhanced error handling, new locales, and comprehensive testing all contribute to a more robust, efficient, and maintainable artifact management system. By addressing the issues of LLM context confusion, token inefficiency, and the limitations of updating large artifacts, this pull request significantly improves the practicality and effectiveness of AI bots in managing web artifacts within Discourse.
2025-02-04 16:27:27 +11:00
system: true,
)
end
context "when modifying a system persona" do
it "allows changing tool options without allowing tool additions/removals" do
tools = [["Search", { "base_query" => "abc" }], ["Time"]]
system_persona.update!(tools: tools)
system_persona.reload
expect(system_persona.tools).to eq(tools)
invalid_tools = ["Time"]
system_persona.update(tools: invalid_tools)
expect(system_persona.errors[:base]).to include(
I18n.t("discourse_ai.ai_bot.personas.cannot_edit_system_persona"),
)
end
it "doesn't accept response format changes" do
new_format = [{ key: "summary2", type: "string" }]
expect { system_persona.update!(response_format: new_format) }.to raise_error(
ActiveRecord::RecordInvalid,
)
end
it "doesn't accept additional format changes" do
new_format = [{ key: "summary", type: "string" }, { key: "summary2", type: "string" }]
expect { system_persona.update!(response_format: new_format) }.to raise_error(
ActiveRecord::RecordInvalid,
)
end
it "doesn't accept changes to examples" do
other_examples = [%w[user_msg1 assistant_msg1]]
expect { system_persona.update!(examples: other_examples) }.to raise_error(
ActiveRecord::RecordInvalid,
)
end
end
end
describe "validates examples format" do
it "doesn't accept examples that are not arrays" do
basic_persona.examples = [1]
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:examples].first).to eq(
I18n.t("discourse_ai.personas.malformed_examples"),
)
end
it "doesn't accept examples that don't come in pairs" do
basic_persona.examples = [%w[user_msg1]]
expect(basic_persona.valid?).to eq(false)
expect(basic_persona.errors[:examples].first).to eq(
I18n.t("discourse_ai.personas.malformed_examples"),
)
end
it "works when example is well formatted" do
basic_persona.examples = [%w[user_msg1 assistant1]]
expect(basic_persona.valid?).to eq(true)
DEV: artifact system update (#1096) ### Why This pull request fundamentally restructures how AI bots create and update web artifacts to address critical limitations in the previous approach: 1. **Improved Artifact Context for LLMs**: Previously, artifact creation and update tools included the *entire* artifact source code directly in the tool arguments. This overloaded the Language Model (LLM) with raw code, making it difficult for the LLM to maintain a clear understanding of the artifact's current state when applying changes. The LLM would struggle to differentiate between the base artifact and the requested modifications, leading to confusion and less effective updates. 2. **Reduced Token Usage and History Bloat**: Including the full artifact source code in every tool interaction was extremely token-inefficient. As conversations progressed, this redundant code in the history consumed a significant number of tokens unnecessarily. This not only increased costs but also diluted the context for the LLM with less relevant historical information. 3. **Enabling Updates for Large Artifacts**: The lack of a practical diff or targeted update mechanism made it nearly impossible to efficiently update larger web artifacts. Sending the entire source code for every minor change was both computationally expensive and prone to errors, effectively blocking the use of AI bots for meaningful modifications of complex artifacts. **This pull request addresses these core issues by**: * Introducing methods for the AI bot to explicitly *read* and understand the current state of an artifact. * Implementing efficient update strategies that send *targeted* changes rather than the entire artifact source code. * Providing options to control the level of artifact context included in LLM prompts, optimizing token usage. ### What The main changes implemented in this PR to resolve the above issues are: 1. **`Read Artifact` Tool for Contextual Awareness**: - A new `read_artifact` tool is introduced, enabling AI bots to fetch and process the current content of a web artifact from a given URL (local or external). - This provides the LLM with a clear and up-to-date representation of the artifact's HTML, CSS, and JavaScript, improving its understanding of the base to be modified. - By cloning local artifacts, it allows the bot to work with a fresh copy, further enhancing context and control. 2. **Refactored `Update Artifact` Tool with Efficient Strategies**: - The `update_artifact` tool is redesigned to employ more efficient update strategies, minimizing token usage and improving update precision: - **`diff` strategy**: Utilizes a search-and-replace diff algorithm to apply only the necessary, targeted changes to the artifact's code. This significantly reduces the amount of code sent to the LLM and focuses its attention on the specific modifications. - **`full` strategy**: Provides the option to replace the entire content sections (HTML, CSS, JavaScript) when a complete rewrite is required. - Tool options enhance the control over the update process: - `editor_llm`: Allows selection of a specific LLM for artifact updates, potentially optimizing for code editing tasks. - `update_algorithm`: Enables choosing between `diff` and `full` update strategies based on the nature of the required changes. - `do_not_echo_artifact`: Defaults to true, and by *not* echoing the artifact in prompts, it further reduces token consumption in scenarios where the LLM might not need the full artifact context for every update step (though effectiveness might be slightly reduced in certain update scenarios). 3. **System and General Persona Tool Option Visibility and Customization**: - Tool options, including those for system personas, are made visible and editable in the admin UI. This allows administrators to fine-tune the behavior of all personas and their tools, including setting specific LLMs or update algorithms. This was previously limited or hidden for system personas. 4. **Centralized and Improved Content Security Policy (CSP) Management**: - The CSP for AI artifacts is consolidated and made more maintainable through the `ALLOWED_CDN_SOURCES` constant. This improves code organization and future updates to the allowed CDN list, while maintaining the existing security posture. 5. **Codebase Improvements**: - Refactoring of diff utilities, introduction of strategy classes, enhanced error handling, new locales, and comprehensive testing all contribute to a more robust, efficient, and maintainable artifact management system. By addressing the issues of LLM context confusion, token inefficiency, and the limitations of updating large artifacts, this pull request significantly improves the practicality and effectiveness of AI bots in managing web artifacts within Discourse.
2025-02-04 16:27:27 +11:00
end
end
end