2024-12-27 07:12:29 +09:00
|
|
|
# frozen_string_literal: true
|
|
|
|
|
|
|
|
RSpec.describe DiscourseAi::Configuration::LlmEnumerator do
|
|
|
|
fab!(:fake_model)
|
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_model)
|
2025-04-24 17:22:19 +11:00
|
|
|
fab!(:automation) do
|
|
|
|
Fabricate(:automation, script: "llm_report", name: "some automation", enabled: true)
|
|
|
|
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
|
|
|
|
|
|
|
describe "#values_for_serialization" do
|
|
|
|
it "returns an array for that can be used for serialization" do
|
|
|
|
fake_model.destroy!
|
|
|
|
|
|
|
|
expect(described_class.values_for_serialization).to eq(
|
|
|
|
[
|
|
|
|
{
|
|
|
|
id: llm_model.id,
|
|
|
|
name: llm_model.display_name,
|
|
|
|
vision_enabled: llm_model.vision_enabled,
|
|
|
|
},
|
|
|
|
],
|
|
|
|
)
|
|
|
|
|
|
|
|
expect(
|
|
|
|
described_class.values_for_serialization(allowed_seeded_llm_ids: [seeded_model.id.to_s]),
|
|
|
|
).to contain_exactly(
|
|
|
|
{
|
|
|
|
id: seeded_model.id,
|
|
|
|
name: seeded_model.display_name,
|
|
|
|
vision_enabled: seeded_model.vision_enabled,
|
|
|
|
},
|
|
|
|
{
|
|
|
|
id: llm_model.id,
|
|
|
|
name: llm_model.display_name,
|
|
|
|
vision_enabled: llm_model.vision_enabled,
|
|
|
|
},
|
|
|
|
)
|
|
|
|
end
|
|
|
|
end
|
2024-12-27 07:12:29 +09:00
|
|
|
|
|
|
|
describe "#global_usage" do
|
2025-04-24 17:22:19 +11:00
|
|
|
it "returns a hash of Llm models in use globally" do
|
2024-12-27 07:12:29 +09:00
|
|
|
SiteSetting.ai_helper_model = "custom:#{fake_model.id}"
|
|
|
|
SiteSetting.ai_helper_enabled = true
|
2025-04-24 17:22:19 +11:00
|
|
|
expect(described_class.global_usage).to eq(fake_model.id => [{ type: :ai_helper }])
|
2024-12-27 07:12:29 +09:00
|
|
|
end
|
|
|
|
|
2025-04-24 17:22:19 +11:00
|
|
|
it "returns information about automation rules" do
|
|
|
|
automation.fields.create!(
|
|
|
|
component: "text",
|
|
|
|
name: "model",
|
|
|
|
metadata: {
|
|
|
|
value: "custom:#{fake_model.id}",
|
|
|
|
},
|
|
|
|
target: "script",
|
|
|
|
)
|
|
|
|
|
|
|
|
usage = described_class.global_usage
|
|
|
|
|
|
|
|
expect(usage).to eq(
|
|
|
|
{ fake_model.id => [{ type: :automation, name: "some automation", id: automation.id }] },
|
|
|
|
)
|
2024-12-27 07:12:29 +09:00
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|