dpsifr
86fb1220b6
- **Core**: - Added `check-database.js` to verify database status and validate search functionality. - Created `fix-dimension-mismatch.js` to handle re-embedding of existing data to resolve dimension mismatch from 3 to 512. - Improved test cases by updating vector operations to support 512 dimensions, replacing previously hardcoded dimensions. - **Migration**: - Developed `DIMENSION_MISMATCH_SUMMARY.md`, detailing the root cause, solution, and preventive strategies for dimension mismatch issues. - Added `production-migration-guide.md` for structured production migration with detailed steps on re-embedding strategies, batching, and error handling. - **Tests**: - Enhanced test coverage with 512-dimensional vector validation. - Introduced helper functions for consistent vector testing behavior and streamlined search test cases. - **Documentation**: - Updated project documentation to highlight the resolution process for dimension mismatches, emphasizing preventive mechanisms such as auto-migration and version tracking. **Purpose**: Address critical dimension mismatch issues caused by embedding changes, restore functionality, and provide a roadmap for robust prevention strategies and migration processes.
91 lines
2.8 KiB
TypeScript
91 lines
2.8 KiB
TypeScript
import { describe, it, expect } from 'vitest'
|
|
import { euclideanDistance } from '../src/utils/distance.js'
|
|
|
|
/**
|
|
* Helper function to create a 512-dimensional vector for testing
|
|
* @param primaryIndex The index to set to 1.0, all other indices will be 0.0
|
|
* @returns A 512-dimensional vector with a single 1.0 value at the specified index
|
|
*/
|
|
function createTestVector(primaryIndex: number = 0): number[] {
|
|
const vector = new Array(512).fill(0)
|
|
vector[primaryIndex % 512] = 1.0
|
|
return vector
|
|
}
|
|
|
|
describe('Vector Operations', () => {
|
|
it('should load brainy library successfully', async () => {
|
|
const brainy = await import('../dist/unified.js')
|
|
|
|
expect(brainy).toBeDefined()
|
|
expect(typeof brainy.BrainyData).toBe('function')
|
|
expect(brainy.environment).toBeDefined()
|
|
})
|
|
|
|
it('should create and initialize BrainyData instance', async () => {
|
|
const brainy = await import('../dist/unified.js')
|
|
|
|
const db = new brainy.BrainyData({
|
|
distanceFunction: euclideanDistance
|
|
})
|
|
|
|
expect(db).toBeDefined()
|
|
expect(db.dimensions).toBe(512)
|
|
|
|
await db.init()
|
|
// If we get here without throwing, initialization was successful
|
|
expect(true).toBe(true)
|
|
})
|
|
|
|
it('should handle simple vector operations', async () => {
|
|
const brainy = await import('../dist/unified.js')
|
|
|
|
const db = new brainy.BrainyData({
|
|
distanceFunction: euclideanDistance
|
|
})
|
|
|
|
await db.init()
|
|
await db.clear() // Clear any existing data
|
|
|
|
// Add a simple vector
|
|
const testVector = createTestVector(1)
|
|
await db.add(testVector, { id: 'test' })
|
|
|
|
// Search for the same vector
|
|
const results = await db.search(testVector, 1)
|
|
|
|
expect(results).toBeDefined()
|
|
expect(results.length).toBeGreaterThan(0)
|
|
expect(results[0].metadata.id).toBe('test')
|
|
})
|
|
|
|
it('should handle multiple vector searches correctly', async () => {
|
|
const brainy = await import('../dist/unified.js')
|
|
|
|
const db = new brainy.BrainyData({
|
|
distanceFunction: euclideanDistance
|
|
})
|
|
|
|
await db.init()
|
|
await db.clear() // Clear any existing data
|
|
|
|
// Add multiple vectors
|
|
await db.add(createTestVector(0), { id: 'vec1', type: 'unit' })
|
|
await db.add(createTestVector(1), { id: 'vec2', type: 'unit' })
|
|
await db.add(createTestVector(2), { id: 'vec3', type: 'unit' })
|
|
|
|
// Create a mixed vector with two non-zero elements
|
|
const mixedVector = createTestVector(3)
|
|
mixedVector[4] = 0.5
|
|
await db.add(mixedVector, { id: 'vec4', type: 'mixed' })
|
|
|
|
// Search for multiple results
|
|
const results = await db.search(createTestVector(0), 3)
|
|
|
|
expect(results).toBeDefined()
|
|
expect(results.length).toBeGreaterThanOrEqual(1)
|
|
expect(results.length).toBeLessThanOrEqual(3)
|
|
|
|
// The closest should be the exact match
|
|
expect(results[0].metadata.id).toBe('vec1')
|
|
})
|
|
})
|