discourse-ai/spec/requests/admin/ai_tools_controller_spec.rb
Sam 5e80f93e4c
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

198 lines
5.8 KiB
Ruby

# frozen_string_literal: true
RSpec.describe DiscourseAi::Admin::AiToolsController do
fab!(:llm_model)
fab!(:admin)
fab!(:ai_tool) do
AiTool.create!(
name: "Test Tool",
tool_name: "test_tool",
description: "A test tool",
script: "function invoke(params) { return params; }",
parameters: [
{
name: "unit",
type: "string",
description: "the unit of measurement celcius c or fahrenheit f",
enum: %w[c f],
required: true,
},
],
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
expect(response.parsed_body["meta"]["llms"].length).to be > 0
end
end
describe "GET #edit" do
it "returns a success response" do
get "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/edit.json"
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
{
name: "Test Tool 1",
tool_name: "test_tool_1",
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)
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")
end
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
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
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
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
end
describe "#test" do
it "runs an existing tool and returns the result" do
post "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/test.json",
params: {
parameters: {
input: "Hello, World!",
},
}
expect(response.status).to eq(200)
expect(response.parsed_body["output"]).to eq("input" => "Hello, World!")
end
it "accept changes to the ai_tool parameters that redefine stuff" do
post "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/test.json",
params: {
ai_tool: {
script: "function invoke(params) { return 'hi there'; }",
},
parameters: {
input: "Hello, World!",
},
}
expect(response.status).to eq(200)
expect(response.parsed_body["output"]).to eq("hi there")
end
it "returns an error for invalid tool_id" do
post "/admin/plugins/discourse-ai/ai-tools/-1/test.json",
params: {
parameters: {
input: "Hello, World!",
},
}
expect(response.status).to eq(404)
end
it "handles exceptions during tool execution" do
ai_tool.update!(script: "function invoke(params) { throw new Error('Test error'); }")
post "/admin/plugins/discourse-ai/ai-tools/#{ai_tool.id}/test.json",
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