brainy/tests/setup.ts

91 lines
2.4 KiB
TypeScript
Raw Normal View History

/**
* Simple test setup for Brainy library
* No direct TensorFlow references - patches are handled internally by Brainy
*/
import { beforeEach, afterEach, afterAll } from 'vitest'
import { existsSync, rmSync } from 'fs'
import { join } from 'path'
// Define the test utilities type for reuse
type TestUtilsType = {
createTestVector: (dimensions: number) => number[]
timeout: number
}
// Extend global type definitions for both global and globalThis
declare global {
let testUtils: TestUtilsType | undefined
let __ENV__: any
}
// Explicitly declare globalThis interface to ensure TypeScript recognizes these properties
declare global {
interface globalThis {
testUtils?: TestUtilsType | undefined
__ENV__?: any
}
}
// Clean up between tests
beforeEach(() => {
// Clear any global state that might interfere with tests
if (typeof globalThis !== 'undefined' && globalThis.__ENV__) {
delete globalThis.__ENV__
}
if (typeof global !== 'undefined' && global.__ENV__) {
delete global.__ENV__
}
// Clean up test data directory to prevent file accumulation
const testDataDir = join(process.cwd(), 'brainy-data')
if (existsSync(testDataDir)) {
try {
rmSync(testDataDir, { recursive: true, force: true })
} catch (error) {
// Ignore errors during cleanup
}
}
})
// Clean up after each test
afterEach(() => {
// Force garbage collection if available (requires --expose-gc flag)
if (global.gc) {
global.gc()
}
})
// Final cleanup after all tests
afterAll(() => {
// Clean up test data directory
const testDataDir = join(process.cwd(), 'brainy-data')
if (existsSync(testDataDir)) {
try {
rmSync(testDataDir, { recursive: true, force: true })
} catch (error) {
// Ignore errors during cleanup
}
}
})
// Add simple test utilities to both global and globalThis for compatibility
const testUtilsObject = {
// Create a simple test vector with predictable values
createTestVector: (dimensions: number): number[] => {
return Array.from({ length: dimensions }, (_, i) => (i + 1) / dimensions)
},
// Standard timeout for async operations
timeout: 30000
}
global.testUtils = testUtilsObject
globalThis.testUtils = testUtilsObject
feat\!: migrate from TensorFlow.js to Transformers.js with ONNX Runtime BREAKING CHANGE: Complete migration from TensorFlow.js to Transformers.js for embedding generation This is a major architectural change that replaces TensorFlow.js (USE model) with Transformers.js (all-MiniLM-L6-v2) for significantly improved performance and reduced complexity. Key Changes: - Replace TensorFlow.js Universal Sentence Encoder with Transformers.js all-MiniLM-L6-v2 - Reduce model size from 525MB to 87MB (83% reduction) - Reduce embedding dimensions from 512 to 384 (faster distance calculations) - Remove TensorFlow.js Float32Array patching (caused ONNX conflicts) - Implement smart bundled model detection for offline operation - Add explicit model download script for Docker deployments - Remove complex environment variables in favor of simple configuration - Update all distance functions to use optimized pure JavaScript - Remove TensorFlow-specific utilities and type definitions Performance Improvements: - Model loading: 5x faster (87MB vs 525MB) - Memory usage: 75% reduction (~200-400MB vs ~1.5GB) - Distance calculations: Faster pure JS vs GPU overhead for small vectors - Cold start performance: Significantly improved Files Changed: - Updated package.json: New dependencies, simplified scripts - Rewrote src/utils/embedding.ts: Complete Transformers.js implementation - Updated src/utils/distance.ts: Optimized JavaScript distance functions - Simplified src/setup.ts: Removed TensorFlow-specific patching - Simplified src/utils/textEncoding.ts: Only Node.js TextEncoder/Decoder patches - Deleted src/utils/robustModelLoader.ts: TensorFlow-specific loader - Deleted src/types/tensorflowTypes.ts: TensorFlow type definitions - Added scripts/download-models.cjs: Docker-compatible model downloader - Added comprehensive documentation: README.md, OFFLINE_MODELS.md, analysis docs Testing: - All 19 tests passing - Removed test mocking in favor of real implementation testing - Updated test environment for Transformers.js compatibility - Performance tests validate improved efficiency This migration resolves production issues with Docker egress limitations and provides a more robust, performant foundation for vector operations.
2025-08-05 19:29:59 -07:00
// Set a clear test environment flag for embedding system
globalThis.__BRAINY_TEST_ENV__ = true
if (typeof global !== 'undefined') {
(global as any).__BRAINY_TEST_ENV__ = true
}