LibreChat/api/app/clients/tools/structured/specs/DALLE3.spec.js
Danny Avila 9a5d7eaa4e
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Waiting to run
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
refactor: Replace tiktoken with ai-tokenizer (#12175)
* chore: Update dependencies by adding ai-tokenizer and removing tiktoken

- Added ai-tokenizer version 1.0.6 to package.json and package-lock.json across multiple packages.
- Removed tiktoken version 1.0.15 from package.json and package-lock.json in the same locations, streamlining dependency management.

* refactor: replace js-tiktoken with ai-tokenizer

- Added support for 'claude' encoding in the AgentClient class to improve model compatibility.
- Updated Tokenizer class to utilize 'ai-tokenizer' for both 'o200k_base' and 'claude' encodings, replacing the previous 'tiktoken' dependency.
- Refactored tests to reflect changes in tokenizer behavior and ensure accurate token counting for both encoding types.
- Removed deprecated references to 'tiktoken' and adjusted related tests for improved clarity and functionality.

* chore: remove tiktoken mocks from DALLE3 tests

- Eliminated mock implementations of 'tiktoken' from DALLE3-related test files to streamline test setup and align with recent dependency updates.
- Adjusted related test structures to ensure compatibility with the new tokenizer implementation.

* chore: Add distinct encoding support for Anthropic Claude models

- Introduced a new method `getEncoding` in the AgentClient class to handle the specific BPE tokenizer for Claude models, ensuring compatibility with the distinct encoding requirements.
- Updated documentation to clarify the encoding logic for Claude and other models.

* docs: Update return type documentation for getEncoding method in AgentClient

- Clarified the return type of the getEncoding method to specify that it can return an EncodingName or undefined, enhancing code readability and type safety.

* refactor: Tokenizer class and error handling

- Exported the EncodingName type for broader usage.
- Renamed encodingMap to encodingData for clarity.
- Improved error handling in getTokenCount method to ensure recovery attempts are logged and return 0 on failure.
- Updated countTokens function documentation to specify the use of 'o200k_base' encoding.

* refactor: Simplify encoding documentation and export type

- Updated the getEncoding method documentation to clarify the default behavior for non-Anthropic Claude models.
- Exported the EncodingName type separately from the Tokenizer module for improved clarity and usage.

* test: Update text processing tests for token limits

- Adjusted test cases to handle smaller text sizes, changing scenarios from ~120k tokens to ~20k tokens for both the real tokenizer and countTokens functions.
- Updated token limits in tests to reflect new constraints, ensuring tests accurately assess performance and call reduction.
- Enhanced console log messages for clarity regarding token counts and reductions in the updated scenarios.

* refactor: Update Tokenizer imports and exports

- Moved Tokenizer and countTokens exports to the tokenizer module for better organization.
- Adjusted imports in memory.ts to reflect the new structure, ensuring consistent usage across the codebase.
- Updated memory.test.ts to mock the Tokenizer from the correct module path, enhancing test accuracy.

* refactor: Tokenizer initialization and error handling

- Introduced an async `initEncoding` method to preload tokenizers, improving performance and accuracy in token counting.
- Updated `getTokenCount` to handle uninitialized tokenizers more gracefully, ensuring proper recovery and logging on errors.
- Removed deprecated synchronous tokenizer retrieval, streamlining the overall tokenizer management process.

* test: Enhance tokenizer tests with initialization and encoding checks

- Added `beforeAll` hooks to initialize tokenizers for 'o200k_base' and 'claude' encodings before running tests, ensuring proper setup.
- Updated tests to validate the loading of encodings and the correctness of token counts for both 'o200k_base' and 'claude'.
- Improved test structure to deduplicate concurrent initialization calls, enhancing performance and reliability.
2026-03-10 23:14:52 -04:00

207 lines
6 KiB
JavaScript

const OpenAI = require('openai');
const { logger } = require('@librechat/data-schemas');
const DALLE3 = require('../DALLE3');
jest.mock('openai');
jest.mock('@librechat/data-schemas', () => {
return {
logger: {
info: jest.fn(),
warn: jest.fn(),
debug: jest.fn(),
error: jest.fn(),
},
};
});
const processFileURL = jest.fn();
const generate = jest.fn();
OpenAI.mockImplementation(() => ({
images: {
generate,
},
}));
jest.mock('fs', () => {
return {
existsSync: jest.fn(),
mkdirSync: jest.fn(),
promises: {
writeFile: jest.fn(),
readFile: jest.fn(),
unlink: jest.fn(),
},
};
});
jest.mock('path', () => {
return {
resolve: jest.fn(),
join: jest.fn(),
relative: jest.fn(),
extname: jest.fn().mockImplementation((filename) => {
return filename.slice(filename.lastIndexOf('.'));
}),
};
});
describe('DALLE3', () => {
let originalEnv;
let dalle; // Keep this declaration if you need to use dalle in other tests
const mockApiKey = 'mock_api_key';
beforeAll(() => {
// Save the original process.env
originalEnv = { ...process.env };
});
beforeEach(() => {
// Reset the process.env before each test
jest.resetModules();
process.env = { ...originalEnv, DALLE_API_KEY: mockApiKey };
// Instantiate DALLE3 for tests that do not depend on DALLE3_SYSTEM_PROMPT
dalle = new DALLE3({ processFileURL });
});
afterEach(() => {
jest.clearAllMocks();
// Restore the original process.env after each test
process.env = originalEnv;
});
it('should throw an error if all potential API keys are missing', () => {
delete process.env.DALLE3_API_KEY;
delete process.env.DALLE_API_KEY;
expect(() => new DALLE3()).toThrow('Missing DALLE_API_KEY environment variable.');
});
it('should replace unwanted characters in input string', () => {
const input = 'This is a test\nstring with "quotes" and new lines.';
const expectedOutput = 'This is a test string with quotes and new lines.';
expect(dalle.replaceUnwantedChars(input)).toBe(expectedOutput);
});
it('should generate markdown image URL correctly', () => {
const imageName = 'test.png';
const markdownImage = dalle.wrapInMarkdown(imageName);
expect(markdownImage).toBe('![generated image](test.png)');
});
it('should call OpenAI API with correct parameters', async () => {
const mockData = {
prompt: 'A test prompt',
quality: 'standard',
size: '1024x1024',
style: 'vivid',
};
const mockResponse = {
data: [
{
url: 'http://example.com/img-test.png',
},
],
};
generate.mockResolvedValue(mockResponse);
processFileURL.mockResolvedValue({
filepath: 'http://example.com/img-test.png',
});
const result = await dalle._call(mockData);
expect(generate).toHaveBeenCalledWith({
model: 'dall-e-3',
quality: mockData.quality,
style: mockData.style,
size: mockData.size,
prompt: mockData.prompt,
n: 1,
});
expect(result).toContain('![generated image]');
});
it('should use the system prompt if provided', () => {
process.env.DALLE3_SYSTEM_PROMPT = 'System prompt for testing';
jest.resetModules(); // This will ensure the module is fresh and will read the new env var
const DALLE3 = require('../DALLE3'); // Re-require after setting the env var
const dalleWithSystemPrompt = new DALLE3();
expect(dalleWithSystemPrompt.description_for_model).toBe('System prompt for testing');
});
it('should not use the system prompt if not provided', async () => {
delete process.env.DALLE3_SYSTEM_PROMPT;
const dalleWithoutSystemPrompt = new DALLE3();
expect(dalleWithoutSystemPrompt.description_for_model).not.toBe('System prompt for testing');
});
it('should throw an error if prompt is missing', async () => {
const mockData = {
quality: 'standard',
size: '1024x1024',
style: 'vivid',
};
await expect(dalle._call(mockData)).rejects.toThrow('Missing required field: prompt');
});
it('should log appropriate debug values', async () => {
const mockData = {
prompt: 'A test prompt',
};
const mockResponse = {
data: [
{
url: 'http://example.com/invalid-url',
},
],
};
generate.mockResolvedValue(mockResponse);
await dalle._call(mockData);
expect(logger.debug).toHaveBeenCalledWith('[DALL-E-3]', {
data: { url: 'http://example.com/invalid-url' },
theImageUrl: 'http://example.com/invalid-url',
extension: expect.any(String),
imageBasename: expect.any(String),
imageExt: expect.any(String),
imageName: expect.any(String),
});
});
it('should log an error and return the image URL if there is an error saving the image', async () => {
const mockData = {
prompt: 'A test prompt',
};
const mockResponse = {
data: [
{
url: 'http://example.com/img-test.png',
},
],
};
const error = new Error('Error while saving the image');
generate.mockResolvedValue(mockResponse);
processFileURL.mockRejectedValue(error);
const result = await dalle._call(mockData);
expect(logger.error).toHaveBeenCalledWith('Error while saving the image:', error);
expect(result).toBe('Failed to save the image locally. Error while saving the image');
});
it('should handle error when saving image to Firebase Storage fails', async () => {
const mockData = {
prompt: 'A test prompt',
};
const mockImageUrl = 'http://example.com/img-test.png';
const mockResponse = { data: [{ url: mockImageUrl }] };
const error = new Error('Error while saving to Firebase');
generate.mockResolvedValue(mockResponse);
processFileURL.mockRejectedValue(error);
const result = await dalle._call(mockData);
expect(logger.error).toHaveBeenCalledWith('Error while saving the image:', error);
expect(result).toContain('Failed to save the image');
});
});