2024-06-27 17:27:40 +10:00
|
|
|
# frozen_string_literal: true
|
|
|
|
|
|
|
|
RSpec.describe DiscourseAi::Admin::AiToolsController do
|
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)
|
2024-06-27 17:27:40 +10:00
|
|
|
fab!(:admin)
|
|
|
|
fab!(:ai_tool) do
|
|
|
|
AiTool.create!(
|
|
|
|
name: "Test Tool",
|
2025-02-07 14:34:47 +11:00
|
|
|
tool_name: "test_tool",
|
2024-06-27 17:27:40 +10:00
|
|
|
description: "A test tool",
|
|
|
|
script: "function invoke(params) { return params; }",
|
2024-07-16 14:23:17 -03:00
|
|
|
parameters: [
|
|
|
|
{
|
|
|
|
name: "unit",
|
|
|
|
type: "string",
|
|
|
|
description: "the unit of measurement celcius c or fahrenheit f",
|
|
|
|
enum: %w[c f],
|
|
|
|
required: true,
|
|
|
|
},
|
|
|
|
],
|
2024-06-27 17:27:40 +10:00
|
|
|
summary: "Test tool summary",
|
|
|
|
created_by_id: -1,
|
|
|
|
)
|
|
|
|
end
|
|
|
|
|
|
|
|
before do
|
|
|
|
sign_in(admin)
|
|
|
|
SiteSetting.ai_embeddings_enabled = true
|
|
|
|
end
|
|
|
|
|
|
|
|
describe "GET #index" do
|
|
|
|
it "returns a success response" do
|
|
|
|
get "/admin/plugins/discourse-ai/ai-tools.json"
|
|
|
|
expect(response).to be_successful
|
|
|
|
expect(response.parsed_body["ai_tools"].length).to eq(AiTool.count)
|
|
|
|
expect(response.parsed_body["meta"]["presets"].length).to be > 0
|
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(response.parsed_body["meta"]["llms"].length).to be > 0
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2024-12-12 10:48:58 +11:00
|
|
|
describe "GET #edit" do
|
2024-06-27 17:27:40 +10:00
|
|
|
it "returns a success response" do
|
2024-12-12 10:48:58 +11:00
|
|
|
get "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/edit.json"
|
2024-06-27 17:27:40 +10:00
|
|
|
expect(response).to be_successful
|
|
|
|
expect(response.parsed_body["ai_tool"]["name"]).to eq(ai_tool.name)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
describe "POST #create" do
|
|
|
|
let(:valid_attributes) do
|
|
|
|
{
|
2025-02-07 14:34:47 +11:00
|
|
|
name: "Test Tool 1",
|
|
|
|
tool_name: "test_tool_1",
|
2024-06-27 17:27:40 +10:00
|
|
|
description: "A test tool",
|
|
|
|
parameters: [{ name: "query", type: "string", description: "perform a search" }],
|
|
|
|
script: "function invoke(params) { return params; }",
|
|
|
|
summary: "Test tool summary",
|
|
|
|
}
|
|
|
|
end
|
|
|
|
|
|
|
|
it "creates a new AiTool" do
|
|
|
|
expect {
|
|
|
|
post "/admin/plugins/discourse-ai/ai-tools.json",
|
|
|
|
params: { ai_tool: valid_attributes }.to_json,
|
|
|
|
headers: {
|
|
|
|
"CONTENT_TYPE" => "application/json",
|
|
|
|
}
|
|
|
|
}.to change(AiTool, :count).by(1)
|
|
|
|
|
|
|
|
expect(response).to have_http_status(:created)
|
2025-02-07 14:34:47 +11:00
|
|
|
expect(response.parsed_body["ai_tool"]["name"]).to eq("Test Tool 1")
|
|
|
|
expect(response.parsed_body["ai_tool"]["tool_name"]).to eq("test_tool_1")
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
2024-07-16 14:23:17 -03:00
|
|
|
|
2025-06-12 12:39:58 -07:00
|
|
|
it "logs the creation with StaffActionLogger" do
|
|
|
|
expect {
|
|
|
|
post "/admin/plugins/discourse-ai/ai-tools.json",
|
|
|
|
params: { ai_tool: valid_attributes }.to_json,
|
|
|
|
headers: {
|
|
|
|
"CONTENT_TYPE" => "application/json",
|
|
|
|
}
|
|
|
|
}.to change {
|
|
|
|
UserHistory.where(
|
|
|
|
action: UserHistory.actions[:custom_staff],
|
|
|
|
custom_type: "create_ai_tool",
|
|
|
|
).count
|
|
|
|
}.by(1)
|
|
|
|
|
|
|
|
history =
|
|
|
|
UserHistory.where(
|
|
|
|
action: UserHistory.actions[:custom_staff],
|
|
|
|
custom_type: "create_ai_tool",
|
|
|
|
).last
|
|
|
|
expect(history.details).to include("name: Test Tool 1")
|
|
|
|
expect(history.details).to include("tool_name: test_tool_1")
|
|
|
|
expect(history.subject).to eq("Test Tool 1") # Verify subject field is included
|
|
|
|
end
|
|
|
|
|
2024-07-16 14:23:17 -03:00
|
|
|
context "when the parameter is a enum" do
|
|
|
|
it "creates the tool with the correct parameters" do
|
|
|
|
attrs = valid_attributes
|
|
|
|
attrs[:parameters] = [attrs[:parameters].first.merge(enum: %w[c f])]
|
|
|
|
|
|
|
|
expect {
|
|
|
|
post "/admin/plugins/discourse-ai/ai-tools.json",
|
|
|
|
params: { ai_tool: valid_attributes }.to_json,
|
|
|
|
headers: {
|
|
|
|
"CONTENT_TYPE" => "application/json",
|
|
|
|
}
|
|
|
|
}.to change(AiTool, :count).by(1)
|
|
|
|
|
|
|
|
expect(response).to have_http_status(:created)
|
|
|
|
expect(response.parsed_body.dig("ai_tool", "parameters", 0, "enum")).to contain_exactly(
|
|
|
|
"c",
|
|
|
|
"f",
|
|
|
|
)
|
|
|
|
end
|
|
|
|
end
|
2025-05-30 17:12:24 +10:00
|
|
|
|
|
|
|
context "when enum validation fails" do
|
|
|
|
it "fails to create tool with empty enum" do
|
|
|
|
attrs = valid_attributes
|
|
|
|
attrs[:parameters] = [attrs[:parameters].first.merge(enum: [])]
|
|
|
|
|
|
|
|
expect {
|
|
|
|
post "/admin/plugins/discourse-ai/ai-tools.json",
|
|
|
|
params: { ai_tool: attrs }.to_json,
|
|
|
|
headers: {
|
|
|
|
"CONTENT_TYPE" => "application/json",
|
|
|
|
}
|
|
|
|
}.not_to change(AiTool, :count)
|
|
|
|
|
|
|
|
expect(response).to have_http_status(:unprocessable_entity)
|
|
|
|
expect(response.parsed_body["errors"]).to include(match(/enum cannot be empty/))
|
|
|
|
end
|
|
|
|
|
|
|
|
it "fails to create tool with duplicate enum values" do
|
|
|
|
attrs = valid_attributes
|
|
|
|
attrs[:parameters] = [attrs[:parameters].first.merge(enum: %w[c f c])]
|
|
|
|
|
|
|
|
expect {
|
|
|
|
post "/admin/plugins/discourse-ai/ai-tools.json",
|
|
|
|
params: { ai_tool: attrs }.to_json,
|
|
|
|
headers: {
|
|
|
|
"CONTENT_TYPE" => "application/json",
|
|
|
|
}
|
|
|
|
}.not_to change(AiTool, :count)
|
|
|
|
|
|
|
|
expect(response).to have_http_status(:unprocessable_entity)
|
|
|
|
expect(response.parsed_body["errors"]).to include(match(/enum values must be unique/))
|
|
|
|
end
|
|
|
|
end
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
|
|
|
|
|
|
|
describe "PUT #update" do
|
|
|
|
it "updates the requested ai_tool" do
|
|
|
|
put "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}.json",
|
|
|
|
params: {
|
|
|
|
ai_tool: {
|
|
|
|
name: "Updated Tool",
|
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
expect(response).to be_successful
|
|
|
|
expect(ai_tool.reload.name).to eq("Updated Tool")
|
|
|
|
end
|
2024-07-16 14:23:17 -03:00
|
|
|
|
2025-06-12 12:39:58 -07:00
|
|
|
it "logs the update with StaffActionLogger" do
|
|
|
|
expect {
|
|
|
|
put "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}.json",
|
|
|
|
params: {
|
|
|
|
ai_tool: {
|
|
|
|
name: "Updated Tool",
|
|
|
|
description: "Updated description",
|
|
|
|
},
|
|
|
|
}
|
|
|
|
}.to change {
|
|
|
|
UserHistory.where(
|
|
|
|
action: UserHistory.actions[:custom_staff],
|
|
|
|
custom_type: "update_ai_tool",
|
|
|
|
).count
|
|
|
|
}.by(1)
|
|
|
|
|
|
|
|
history =
|
|
|
|
UserHistory.where(
|
|
|
|
action: UserHistory.actions[:custom_staff],
|
|
|
|
custom_type: "update_ai_tool",
|
|
|
|
).last
|
|
|
|
expect(history.details).to include("tool_id: #{ai_tool.id}")
|
|
|
|
expect(history.details).to include("name")
|
|
|
|
expect(history.details).to include("description")
|
|
|
|
expect(history.subject).to eq("Updated Tool")
|
|
|
|
end
|
|
|
|
|
2024-07-16 14:23:17 -03:00
|
|
|
context "when updating an enum parameters" do
|
|
|
|
it "updates the enum fixed values" do
|
|
|
|
put "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}.json",
|
|
|
|
params: {
|
|
|
|
ai_tool: {
|
|
|
|
parameters: [
|
|
|
|
{
|
|
|
|
name: "unit",
|
|
|
|
type: "string",
|
|
|
|
description: "the unit of measurement celcius c or fahrenheit f",
|
|
|
|
enum: %w[g d],
|
|
|
|
},
|
|
|
|
],
|
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
expect(response).to be_successful
|
|
|
|
expect(ai_tool.reload.parameters.dig(0, "enum")).to contain_exactly("g", "d")
|
|
|
|
end
|
|
|
|
end
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
|
|
|
|
|
|
|
describe "DELETE #destroy" do
|
|
|
|
it "destroys the requested ai_tool" do
|
|
|
|
expect { delete "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}.json" }.to change(
|
|
|
|
AiTool,
|
|
|
|
:count,
|
|
|
|
).by(-1)
|
|
|
|
|
|
|
|
expect(response).to have_http_status(:no_content)
|
|
|
|
end
|
2025-06-12 12:39:58 -07:00
|
|
|
|
|
|
|
it "logs the deletion with StaffActionLogger" do
|
|
|
|
tool_id = ai_tool.id
|
|
|
|
|
|
|
|
expect { delete "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}.json" }.to change {
|
|
|
|
UserHistory.where(
|
|
|
|
action: UserHistory.actions[:custom_staff],
|
|
|
|
custom_type: "delete_ai_tool",
|
|
|
|
).count
|
|
|
|
}.by(1)
|
|
|
|
|
|
|
|
history =
|
|
|
|
UserHistory.where(
|
|
|
|
action: UserHistory.actions[:custom_staff],
|
|
|
|
custom_type: "delete_ai_tool",
|
|
|
|
).last
|
|
|
|
expect(history.details).to include("tool_id: #{tool_id}")
|
|
|
|
expect(history.subject).to eq("Test Tool") # Verify subject field is included
|
|
|
|
end
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
|
|
|
|
|
|
|
describe "#test" do
|
|
|
|
it "runs an existing tool and returns the result" do
|
2024-10-25 16:01:25 +11:00
|
|
|
post "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/test.json",
|
2024-06-27 17:27:40 +10:00
|
|
|
params: {
|
|
|
|
parameters: {
|
|
|
|
input: "Hello, World!",
|
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
expect(response.status).to eq(200)
|
|
|
|
expect(response.parsed_body["output"]).to eq("input" => "Hello, World!")
|
|
|
|
end
|
|
|
|
|
2024-10-25 16:01:25 +11:00
|
|
|
it "accept changes to the ai_tool parameters that redefine stuff" do
|
|
|
|
post "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/test.json",
|
2024-06-27 17:27:40 +10:00
|
|
|
params: {
|
|
|
|
ai_tool: {
|
2024-10-25 16:01:25 +11:00
|
|
|
script: "function invoke(params) { return 'hi there'; }",
|
2024-06-27 17:27:40 +10:00
|
|
|
},
|
|
|
|
parameters: {
|
2024-10-25 16:01:25 +11:00
|
|
|
input: "Hello, World!",
|
2024-06-27 17:27:40 +10:00
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
expect(response.status).to eq(200)
|
2024-10-25 16:01:25 +11:00
|
|
|
expect(response.parsed_body["output"]).to eq("hi there")
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
|
|
|
|
|
|
|
it "returns an error for invalid tool_id" do
|
2024-10-25 16:01:25 +11:00
|
|
|
post "/admin/plugins/discourse-ai/ai-tools/-1/test.json",
|
2024-06-27 17:27:40 +10:00
|
|
|
params: {
|
|
|
|
parameters: {
|
|
|
|
input: "Hello, World!",
|
|
|
|
},
|
|
|
|
}
|
|
|
|
|
2024-10-25 16:01:25 +11:00
|
|
|
expect(response.status).to eq(404)
|
2024-06-27 17:27:40 +10:00
|
|
|
end
|
|
|
|
|
|
|
|
it "handles exceptions during tool execution" do
|
|
|
|
ai_tool.update!(script: "function invoke(params) { throw new Error('Test error'); }")
|
|
|
|
|
2024-10-25 16:01:25 +11:00
|
|
|
post "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/test.json",
|
2024-06-27 17:27:40 +10:00
|
|
|
params: {
|
|
|
|
id: ai_tool.id,
|
|
|
|
parameters: {
|
|
|
|
input: "Hello, World!",
|
|
|
|
},
|
|
|
|
}
|
|
|
|
|
|
|
|
expect(response.status).to eq(400)
|
|
|
|
expect(response.parsed_body["errors"].to_s).to include("Error executing the tool")
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|