Merge remote-tracking branch 'origin/main'
# Conflicts: # CHANGES.md # package-lock.json # package.json # src/storage/adapters/fileSystemStorage.ts
This commit is contained in:
commit
3337c9f78e
49 changed files with 5099 additions and 4391 deletions
|
|
@ -5,6 +5,17 @@
|
|||
|
||||
import { describe, it, expect, beforeAll } from 'vitest'
|
||||
|
||||
/**
|
||||
* 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('Brainy Core Functionality', () => {
|
||||
let brainy: any
|
||||
|
||||
|
|
@ -42,17 +53,14 @@ describe('Brainy Core Functionality', () => {
|
|||
|
||||
describe('BrainyData Configuration', () => {
|
||||
it('should create instance with minimal configuration', () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 3
|
||||
})
|
||||
const data = new brainy.BrainyData({})
|
||||
|
||||
expect(data).toBeDefined()
|
||||
expect(data.dimensions).toBe(3)
|
||||
expect(data.dimensions).toBe(512)
|
||||
})
|
||||
|
||||
it('should create instance with full configuration', () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 128,
|
||||
metric: 'cosine',
|
||||
maxConnections: 32,
|
||||
efConstruction: 200,
|
||||
|
|
@ -60,29 +68,28 @@ describe('Brainy Core Functionality', () => {
|
|||
})
|
||||
|
||||
expect(data).toBeDefined()
|
||||
expect(data.dimensions).toBe(128)
|
||||
expect(data.dimensions).toBe(512)
|
||||
})
|
||||
|
||||
it('should validate configuration parameters', () => {
|
||||
it('should not throw with valid configuration parameters', () => {
|
||||
// Dimensions are now fixed at 512 and not configurable
|
||||
expect(() => {
|
||||
new brainy.BrainyData({
|
||||
dimensions: 0 // Invalid dimensions
|
||||
metric: 'cosine'
|
||||
})
|
||||
}).toThrow()
|
||||
}).not.toThrow()
|
||||
|
||||
expect(() => {
|
||||
new brainy.BrainyData({
|
||||
dimensions: -1 // Invalid dimensions
|
||||
metric: 'euclidean'
|
||||
})
|
||||
}).toThrow()
|
||||
}).not.toThrow()
|
||||
})
|
||||
|
||||
it('should use default values for optional parameters', () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 10
|
||||
})
|
||||
const data = new brainy.BrainyData({})
|
||||
|
||||
expect(data.dimensions).toBe(10)
|
||||
expect(data.dimensions).toBe(512)
|
||||
// Should have reasonable defaults for other parameters
|
||||
expect(data.maxConnections).toBeGreaterThan(0)
|
||||
expect(data.efConstruction).toBeGreaterThan(0)
|
||||
|
|
@ -92,20 +99,19 @@ describe('Brainy Core Functionality', () => {
|
|||
describe('Vector Operations', () => {
|
||||
it('should handle vector addition and search', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 3,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
await data.init()
|
||||
await data.clear() // Clear any existing data
|
||||
|
||||
// Add vectors
|
||||
await data.add([1, 0, 0], { id: 'v1', label: 'x-axis' })
|
||||
await data.add([0, 1, 0], { id: 'v2', label: 'y-axis' })
|
||||
await data.add([0, 0, 1], { id: 'v3', label: 'z-axis' })
|
||||
// Add vectors using helper function
|
||||
await data.add(createTestVector(0), { id: 'v1', label: 'x-axis' })
|
||||
await data.add(createTestVector(1), { id: 'v2', label: 'y-axis' })
|
||||
await data.add(createTestVector(2), { id: 'v3', label: 'z-axis' })
|
||||
|
||||
// Search for similar vector
|
||||
const results = await data.search([1, 0, 0], 1)
|
||||
const results = await data.search(createTestVector(0), 1)
|
||||
|
||||
expect(results).toBeDefined()
|
||||
expect(results.length).toBe(1)
|
||||
|
|
@ -114,7 +120,6 @@ describe('Brainy Core Functionality', () => {
|
|||
|
||||
it('should handle batch vector operations', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
|
|
@ -123,9 +128,9 @@ describe('Brainy Core Functionality', () => {
|
|||
|
||||
// Add multiple vectors
|
||||
const vectors = [
|
||||
{ vector: [1, 1], metadata: { id: 'batch1' } },
|
||||
{ vector: [2, 2], metadata: { id: 'batch2' } },
|
||||
{ vector: [3, 3], metadata: { id: 'batch3' } }
|
||||
{ vector: createTestVector(10), metadata: { id: 'batch1' } },
|
||||
{ vector: createTestVector(20), metadata: { id: 'batch2' } },
|
||||
{ vector: createTestVector(30), metadata: { id: 'batch3' } }
|
||||
]
|
||||
|
||||
for (const { vector, metadata } of vectors) {
|
||||
|
|
@ -133,18 +138,16 @@ describe('Brainy Core Functionality', () => {
|
|||
}
|
||||
|
||||
// Search should return results
|
||||
const results = await data.search([1.5, 1.5], 3)
|
||||
const results = await data.search(createTestVector(15), 3)
|
||||
expect(results.length).toBe(3)
|
||||
})
|
||||
|
||||
it('should handle different distance metrics', async () => {
|
||||
const euclideanData = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
const cosineData = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'cosine'
|
||||
})
|
||||
|
||||
|
|
@ -155,7 +158,7 @@ describe('Brainy Core Functionality', () => {
|
|||
await euclideanData.clear()
|
||||
await cosineData.clear()
|
||||
|
||||
const vector = [1, 1]
|
||||
const vector = createTestVector(5)
|
||||
const metadata = { id: 'test' }
|
||||
|
||||
await euclideanData.add(vector, metadata)
|
||||
|
|
@ -237,7 +240,6 @@ describe('Brainy Core Functionality', () => {
|
|||
describe('Error Handling', () => {
|
||||
it('should handle invalid vector dimensions', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 3,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
|
|
@ -245,22 +247,20 @@ describe('Brainy Core Functionality', () => {
|
|||
|
||||
// Try to add vector with wrong dimensions
|
||||
await expect(data.add([1, 2], { id: 'wrong' })).rejects.toThrow()
|
||||
await expect(data.add([1, 2, 3, 4], { id: 'wrong' })).rejects.toThrow()
|
||||
await expect(data.add(new Array(100).fill(0), { id: 'wrong' })).rejects.toThrow()
|
||||
})
|
||||
|
||||
it('should handle search before initialization', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
// Try to search without initialization
|
||||
await expect(data.search([1, 2], 1)).rejects.toThrow()
|
||||
await expect(data.search(createTestVector(0), 1)).rejects.toThrow()
|
||||
})
|
||||
|
||||
it('should handle empty search results gracefully', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
|
|
@ -268,7 +268,7 @@ describe('Brainy Core Functionality', () => {
|
|||
await data.clear() // Clear any existing data
|
||||
|
||||
// Search in empty database
|
||||
const results = await data.search([1, 2], 1)
|
||||
const results = await data.search(createTestVector(0), 1)
|
||||
expect(results).toBeDefined()
|
||||
expect(Array.isArray(results)).toBe(true)
|
||||
expect(results.length).toBe(0)
|
||||
|
|
@ -278,7 +278,6 @@ describe('Brainy Core Functionality', () => {
|
|||
describe('Performance and Scalability', () => {
|
||||
it('should handle moderate number of vectors efficiently', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
dimensions: 10,
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
|
|
@ -288,21 +287,14 @@ describe('Brainy Core Functionality', () => {
|
|||
|
||||
// Add 100 test vectors
|
||||
for (let i = 0; i < 100; i++) {
|
||||
const vector =
|
||||
globalThis.testUtils?.createTestVector(10) ||
|
||||
Array.from({ length: 10 }, (_, i) => (i + 1) / 10)
|
||||
await data.add(vector, { id: `item_${i}`, index: i })
|
||||
await data.add(createTestVector(i), { id: `item_${i}`, index: i })
|
||||
}
|
||||
|
||||
const addTime = Date.now() - startTime
|
||||
|
||||
// Search should be fast
|
||||
const searchStart = Date.now()
|
||||
const results = await data.search(
|
||||
globalThis.testUtils?.createTestVector(10) ||
|
||||
Array.from({ length: 10 }, (_, i) => (i + 1) / 10),
|
||||
10
|
||||
)
|
||||
const results = await data.search(createTestVector(50), 10)
|
||||
const searchTime = Date.now() - searchStart
|
||||
|
||||
expect(results.length).toBeLessThanOrEqual(10)
|
||||
|
|
@ -342,4 +334,51 @@ describe('Brainy Core Functionality', () => {
|
|||
expect(results[0].metadata?.id).toBe('known')
|
||||
})
|
||||
})
|
||||
|
||||
describe('Database Statistics', () => {
|
||||
it('should provide accurate statistics about the database', async () => {
|
||||
const data = new brainy.BrainyData({
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
await data.init()
|
||||
await data.clear() // Clear any existing data
|
||||
|
||||
// Add some vectors (nouns)
|
||||
await data.add(createTestVector(0), { id: 'v1', label: 'x-axis' })
|
||||
await data.add(createTestVector(1), { id: 'v2', label: 'y-axis' })
|
||||
await data.add(createTestVector(2), { id: 'v3', label: 'z-axis' })
|
||||
|
||||
// Add some connections (verbs)
|
||||
await data.connect('v1', 'v2', 'related_to')
|
||||
await data.connect('v2', 'v3', 'related_to')
|
||||
|
||||
// Get statistics
|
||||
const stats = await data.getStatistics()
|
||||
|
||||
// Debug: Log all nouns in the database
|
||||
const allNouns = await data.getAllNouns()
|
||||
console.log('All nouns in database:', allNouns.map(n => n.id))
|
||||
|
||||
// Debug: Log all verbs in the database
|
||||
const allVerbs = await data.getAllVerbs()
|
||||
console.log('All verbs in database:', allVerbs.map(v => v.id))
|
||||
|
||||
// Debug: Log the verb IDs set used in getStatistics
|
||||
const verbIds = new Set(allVerbs.map(verb => verb.id))
|
||||
console.log('Verb IDs set:', Array.from(verbIds))
|
||||
|
||||
// Verify statistics
|
||||
expect(stats).toBeDefined()
|
||||
expect(stats).toHaveProperty('nounCount')
|
||||
expect(stats).toHaveProperty('verbCount')
|
||||
expect(stats).toHaveProperty('metadataCount')
|
||||
expect(stats).toHaveProperty('hnswIndexSize')
|
||||
|
||||
// Verify counts
|
||||
expect(stats.nounCount).toBe(3)
|
||||
expect(stats.verbCount).toBe(2)
|
||||
expect(stats.hnswIndexSize).toBe(3)
|
||||
})
|
||||
})
|
||||
})
|
||||
|
|
|
|||
64
tests/database-operations.test.ts
Normal file
64
tests/database-operations.test.ts
Normal file
|
|
@ -0,0 +1,64 @@
|
|||
import { describe, it, expect } from 'vitest'
|
||||
import { BrainyData } from '../dist/brainyData.js'
|
||||
|
||||
describe('Database Operations', () => {
|
||||
let db: BrainyData
|
||||
|
||||
beforeEach(async () => {
|
||||
db = new BrainyData()
|
||||
await db.init()
|
||||
})
|
||||
|
||||
it('should initialize and return database status', async () => {
|
||||
const status = await db.status()
|
||||
expect(status).toBeDefined()
|
||||
// The structure of status might vary, just check it exists
|
||||
})
|
||||
|
||||
it('should return statistics', async () => {
|
||||
const stats = await db.getStatistics()
|
||||
expect(stats).toBeDefined()
|
||||
// The structure of stats might vary, just check it exists
|
||||
})
|
||||
|
||||
it('should retrieve all nouns', async () => {
|
||||
const nouns = await db.getAllNouns()
|
||||
expect(Array.isArray(nouns)).toBe(true)
|
||||
})
|
||||
|
||||
it('should retrieve all verbs', async () => {
|
||||
const verbs = await db.getAllVerbs()
|
||||
expect(Array.isArray(verbs)).toBe(true)
|
||||
})
|
||||
|
||||
it('should perform a search operation', async () => {
|
||||
const searchResults = await db.searchText('test', 10)
|
||||
expect(Array.isArray(searchResults)).toBe(true)
|
||||
})
|
||||
|
||||
it('should add and retrieve an item', async () => {
|
||||
// Add a test item
|
||||
const testText = 'This is a test item for searching'
|
||||
const metadata = { noun: 'Thing', category: 'test' }
|
||||
const id = await db.add(testText, metadata)
|
||||
|
||||
// Verify the item was added
|
||||
expect(id).toBeDefined()
|
||||
|
||||
// Retrieve the item
|
||||
const noun = await db.get(id)
|
||||
expect(noun).toBeDefined()
|
||||
expect(noun.id).toBe(id)
|
||||
|
||||
// Check that the metadata contains our properties
|
||||
// (The system might add additional properties)
|
||||
expect(noun.metadata.category).toBe('test')
|
||||
|
||||
// Search for the item
|
||||
const searchResults = await db.searchText('test', 10)
|
||||
expect(searchResults.length).toBeGreaterThan(0)
|
||||
|
||||
// Clean up
|
||||
await db.delete(id)
|
||||
})
|
||||
})
|
||||
58
tests/dimension-standardization.test.ts
Normal file
58
tests/dimension-standardization.test.ts
Normal file
|
|
@ -0,0 +1,58 @@
|
|||
import { describe, it, expect } from 'vitest'
|
||||
import { BrainyData } from '../dist/brainyData.js'
|
||||
|
||||
describe('Vector Dimension Standardization', () => {
|
||||
it('should initialize BrainyData with 512 dimensions', async () => {
|
||||
// Initialize BrainyData
|
||||
const db = new BrainyData()
|
||||
await db.init()
|
||||
|
||||
// Check the dimensions property
|
||||
expect(db.dimensions).toBe(512)
|
||||
})
|
||||
|
||||
it('should reject vectors with incorrect dimensions', async () => {
|
||||
const db = new BrainyData()
|
||||
await db.init()
|
||||
|
||||
// Test with a simple vector (this should throw an error because it's not 512 dimensions)
|
||||
const smallVector = [0.1, 0.2, 0.3]
|
||||
|
||||
// Expect the add operation to throw an error
|
||||
await expect(db.add(smallVector, { test: 'small-vector' }))
|
||||
.rejects.toThrow()
|
||||
})
|
||||
|
||||
it('should successfully embed text to 512 dimensions', async () => {
|
||||
const db = new BrainyData()
|
||||
await db.init()
|
||||
|
||||
// Test with text that will be embedded to 512 dimensions
|
||||
const id = await db.add('This is a test text that will be embedded to 512 dimensions', { test: 'text-embedding' })
|
||||
|
||||
// Retrieve the vector and check its dimensions
|
||||
const noun = await db.get(id)
|
||||
expect(noun.vector.length).toBe(512)
|
||||
})
|
||||
|
||||
it('should directly embed text to 512 dimensions', async () => {
|
||||
const db = new BrainyData()
|
||||
await db.init()
|
||||
|
||||
// Test direct embedding
|
||||
const vector = await db.embed('Another test text')
|
||||
expect(vector.length).toBe(512)
|
||||
})
|
||||
|
||||
it('should use the configured dimensions', async () => {
|
||||
// Create a BrainyData instance with a specific dimension
|
||||
const customDimension = 300
|
||||
const db = new BrainyData({
|
||||
dimensions: customDimension
|
||||
})
|
||||
await db.init()
|
||||
|
||||
// The API appears to respect the configured dimensions
|
||||
expect(db.dimensions).toBe(customDimension)
|
||||
})
|
||||
})
|
||||
|
|
@ -6,6 +6,17 @@
|
|||
|
||||
import { describe, it, expect, beforeAll, vi } from 'vitest'
|
||||
|
||||
/**
|
||||
* 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('Brainy in Browser Environment', () => {
|
||||
let brainy: any
|
||||
|
||||
|
|
@ -53,7 +64,6 @@ describe('Brainy in Browser Environment', () => {
|
|||
describe('Core Functionality - Add Data and Search', () => {
|
||||
it('should create database and add vector data', async () => {
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 3,
|
||||
metric: 'euclidean',
|
||||
storage: {
|
||||
forceMemoryStorage: true
|
||||
|
|
@ -63,12 +73,12 @@ describe('Brainy in Browser Environment', () => {
|
|||
await db.init()
|
||||
|
||||
// Add some test vectors
|
||||
await db.add([1, 0, 0], { id: 'item1', label: 'x-axis' })
|
||||
await db.add([0, 1, 0], { id: 'item2', label: 'y-axis' })
|
||||
await db.add([0, 0, 1], { id: 'item3', label: 'z-axis' })
|
||||
await db.add(createTestVector(0), { id: 'item1', label: 'x-axis' })
|
||||
await db.add(createTestVector(1), { id: 'item2', label: 'y-axis' })
|
||||
await db.add(createTestVector(2), { id: 'item3', label: 'z-axis' })
|
||||
|
||||
// Search should work
|
||||
const results = await db.search([1, 0, 0], 1)
|
||||
const results = await db.search(createTestVector(0), 1)
|
||||
expect(results).toBeDefined()
|
||||
expect(results.length).toBe(1)
|
||||
expect(results[0].metadata.id).toBe('item1')
|
||||
|
|
@ -102,7 +112,6 @@ describe('Brainy in Browser Environment', () => {
|
|||
|
||||
it('should handle multiple data types', async () => {
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean',
|
||||
storage: {
|
||||
forceMemoryStorage: true
|
||||
|
|
@ -113,9 +122,9 @@ describe('Brainy in Browser Environment', () => {
|
|||
|
||||
// Add different types of data
|
||||
const testData = [
|
||||
{ vector: [1, 1], metadata: { type: 'point', name: 'A' } },
|
||||
{ vector: [2, 2], metadata: { type: 'point', name: 'B' } },
|
||||
{ vector: [3, 3], metadata: { type: 'point', name: 'C' } }
|
||||
{ vector: createTestVector(10), metadata: { type: 'point', name: 'A' } },
|
||||
{ vector: createTestVector(20), metadata: { type: 'point', name: 'B' } },
|
||||
{ vector: createTestVector(30), metadata: { type: 'point', name: 'C' } }
|
||||
]
|
||||
|
||||
for (const item of testData) {
|
||||
|
|
@ -123,7 +132,7 @@ describe('Brainy in Browser Environment', () => {
|
|||
}
|
||||
|
||||
// Search should return relevant results
|
||||
const results = await db.search([1.5, 1.5], 2)
|
||||
const results = await db.search(createTestVector(15), 2)
|
||||
expect(results.length).toBe(2)
|
||||
expect(
|
||||
results.every(
|
||||
|
|
@ -134,15 +143,14 @@ describe('Brainy in Browser Environment', () => {
|
|||
})
|
||||
|
||||
describe('Error Handling', () => {
|
||||
it('should handle invalid configurations gracefully', () => {
|
||||
it('should not throw with valid configuration', () => {
|
||||
expect(() => {
|
||||
new brainy.BrainyData({ dimensions: 0 })
|
||||
}).toThrow()
|
||||
new brainy.BrainyData({ metric: 'euclidean' })
|
||||
}).not.toThrow()
|
||||
})
|
||||
|
||||
it('should handle search on empty database', async () => {
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean',
|
||||
storage: {
|
||||
forceMemoryStorage: true
|
||||
|
|
@ -151,7 +159,7 @@ describe('Brainy in Browser Environment', () => {
|
|||
|
||||
await db.init()
|
||||
|
||||
const results = await db.search([1, 2], 5)
|
||||
const results = await db.search(createTestVector(0), 5)
|
||||
expect(results).toBeDefined()
|
||||
expect(Array.isArray(results)).toBe(true)
|
||||
expect(results.length).toBe(0)
|
||||
|
|
|
|||
|
|
@ -5,6 +5,17 @@
|
|||
|
||||
import { describe, it, expect, beforeAll } from 'vitest'
|
||||
|
||||
/**
|
||||
* 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('Brainy in Node.js Environment', () => {
|
||||
let brainy: any
|
||||
|
||||
|
|
@ -53,7 +64,6 @@ describe('Brainy in Node.js Environment', () => {
|
|||
return
|
||||
}
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 3,
|
||||
metric: 'euclidean',
|
||||
storage: {
|
||||
forceMemoryStorage: true
|
||||
|
|
@ -64,12 +74,12 @@ describe('Brainy in Node.js Environment', () => {
|
|||
await db.clear() // Clear any existing data
|
||||
|
||||
// Add some test vectors
|
||||
await db.add([1, 0, 0], { id: 'item1', label: 'x-axis' })
|
||||
await db.add([0, 1, 0], { id: 'item2', label: 'y-axis' })
|
||||
await db.add([0, 0, 1], { id: 'item3', label: 'z-axis' })
|
||||
await db.add(createTestVector(0), { id: 'item1', label: 'x-axis' })
|
||||
await db.add(createTestVector(1), { id: 'item2', label: 'y-axis' })
|
||||
await db.add(createTestVector(2), { id: 'item3', label: 'z-axis' })
|
||||
|
||||
// Search should work
|
||||
const results = await db.search([1, 0, 0], 1)
|
||||
const results = await db.search(createTestVector(0), 1)
|
||||
expect(results).toBeDefined()
|
||||
expect(results.length).toBe(1)
|
||||
expect(results[0].metadata.id).toBe('item1')
|
||||
|
|
@ -114,7 +124,6 @@ describe('Brainy in Node.js Environment', () => {
|
|||
return
|
||||
}
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean',
|
||||
storage: {
|
||||
forceMemoryStorage: true
|
||||
|
|
@ -126,9 +135,9 @@ describe('Brainy in Node.js Environment', () => {
|
|||
|
||||
// Add different types of data
|
||||
const testData = [
|
||||
{ vector: [1, 1], metadata: { type: 'point', name: 'A' } },
|
||||
{ vector: [2, 2], metadata: { type: 'point', name: 'B' } },
|
||||
{ vector: [3, 3], metadata: { type: 'point', name: 'C' } }
|
||||
{ vector: createTestVector(10), metadata: { type: 'point', name: 'A' } },
|
||||
{ vector: createTestVector(20), metadata: { type: 'point', name: 'B' } },
|
||||
{ vector: createTestVector(30), metadata: { type: 'point', name: 'C' } }
|
||||
]
|
||||
|
||||
for (const item of testData) {
|
||||
|
|
@ -136,7 +145,7 @@ describe('Brainy in Node.js Environment', () => {
|
|||
}
|
||||
|
||||
// Search should return relevant results
|
||||
const results = await db.search([1.5, 1.5], 2)
|
||||
const results = await db.search(createTestVector(15), 2)
|
||||
expect(results.length).toBe(2)
|
||||
expect(
|
||||
results.every(
|
||||
|
|
@ -147,14 +156,14 @@ describe('Brainy in Node.js Environment', () => {
|
|||
})
|
||||
|
||||
describe('Error Handling', () => {
|
||||
it('should handle invalid configurations gracefully', () => {
|
||||
it('should not throw with valid configuration', () => {
|
||||
if (brainy === null) {
|
||||
console.warn('Skipping test due to TensorFlow.js initialization issue')
|
||||
return
|
||||
}
|
||||
expect(() => {
|
||||
new brainy.BrainyData({ dimensions: 0 })
|
||||
}).toThrow()
|
||||
new brainy.BrainyData({ metric: 'euclidean' })
|
||||
}).not.toThrow()
|
||||
})
|
||||
|
||||
it('should handle search on empty database', async () => {
|
||||
|
|
@ -163,7 +172,6 @@ describe('Brainy in Node.js Environment', () => {
|
|||
return
|
||||
}
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
metric: 'euclidean',
|
||||
storage: {
|
||||
forceMemoryStorage: true
|
||||
|
|
@ -173,7 +181,7 @@ describe('Brainy in Node.js Environment', () => {
|
|||
await db.init()
|
||||
await db.clear() // Clear any existing data
|
||||
|
||||
const results = await db.search([1, 2], 5)
|
||||
const results = await db.search(createTestVector(0), 5)
|
||||
expect(results).toBeDefined()
|
||||
expect(Array.isArray(results)).toBe(true)
|
||||
expect(results.length).toBe(0)
|
||||
|
|
|
|||
|
|
@ -120,15 +120,25 @@ describe('OPFSStorage', () => {
|
|||
|
||||
// Create test verb
|
||||
const testVector: Vector = [0.1, 0.2, 0.3, 0.4, 0.5]
|
||||
const timestamp = {
|
||||
seconds: Math.floor(Date.now() / 1000),
|
||||
nanoseconds: (Date.now() % 1000) * 1000000
|
||||
}
|
||||
const testVerb = {
|
||||
id: 'test-verb-1',
|
||||
vector: testVector,
|
||||
connections: new Map(),
|
||||
sourceId: 'source-noun-1',
|
||||
targetId: 'target-noun-1',
|
||||
type: 'test-relation',
|
||||
source: 'source-noun-1',
|
||||
target: 'target-noun-1',
|
||||
verb: 'test-relation',
|
||||
weight: 0.75,
|
||||
metadata: { description: 'Test relation' }
|
||||
metadata: { description: 'Test relation' },
|
||||
createdAt: timestamp,
|
||||
updatedAt: timestamp,
|
||||
createdBy: {
|
||||
augmentation: 'test-service',
|
||||
version: '1.0'
|
||||
}
|
||||
}
|
||||
|
||||
// Save the verb
|
||||
|
|
@ -141,11 +151,17 @@ describe('OPFSStorage', () => {
|
|||
expect(retrievedVerb).toBeDefined()
|
||||
expect(retrievedVerb?.id).toBe('test-verb-1')
|
||||
expect(retrievedVerb?.vector).toEqual(testVector)
|
||||
expect(retrievedVerb?.sourceId).toBe('source-noun-1')
|
||||
expect(retrievedVerb?.targetId).toBe('target-noun-1')
|
||||
expect(retrievedVerb?.type).toBe('test-relation')
|
||||
expect(retrievedVerb?.source).toBe('source-noun-1')
|
||||
expect(retrievedVerb?.target).toBe('target-noun-1')
|
||||
expect(retrievedVerb?.verb).toBe('test-relation')
|
||||
expect(retrievedVerb?.weight).toBe(0.75)
|
||||
expect(retrievedVerb?.metadata).toEqual({ description: 'Test relation' })
|
||||
expect(retrievedVerb?.createdAt).toEqual(timestamp)
|
||||
expect(retrievedVerb?.updatedAt).toEqual(timestamp)
|
||||
expect(retrievedVerb?.createdBy).toEqual({
|
||||
augmentation: 'test-service',
|
||||
version: '1.0'
|
||||
})
|
||||
|
||||
// Test getAllVerbs
|
||||
const allVerbs = await opfsStorage.getAllVerbs()
|
||||
|
|
|
|||
|
|
@ -3,64 +3,64 @@
|
|||
* Tests the predicted npm package size to ensure it stays within acceptable limits
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { execSync } from 'child_process'
|
||||
import {describe, expect, it} from 'vitest'
|
||||
import {execSync} from 'child_process'
|
||||
|
||||
const CURRENT_UNPACKED_SIZE_MB = 10.4
|
||||
const CURRENT_PACKED_SIZE_MB = 1.9
|
||||
const CURRENT_UNPACKED_SIZE_MB = 11.1
|
||||
const CURRENT_PACKED_SIZE_MB = 2.5
|
||||
const ALLOWED_SIZE_INCREASE_PERCENTAGE = 5 // 5% increase threshold
|
||||
|
||||
/**
|
||||
* Parses npm pack --dry-run output to extract package size information
|
||||
*/
|
||||
function parseNpmPackOutput(output: string): {
|
||||
packedSizeMB: number
|
||||
unpackedSizeMB: number
|
||||
totalFiles: number
|
||||
packedSizeMB: number
|
||||
unpackedSizeMB: number
|
||||
totalFiles: number
|
||||
} {
|
||||
const packageSizeMatch = output.match(
|
||||
/npm notice package size:\s*([\d.]+)\s*([KMGT]?B)/
|
||||
)
|
||||
const unpackedSizeMatch = output.match(
|
||||
/npm notice unpacked size:\s*([\d.]+)\s*([KMGT]?B)/
|
||||
)
|
||||
const totalFilesMatch = output.match(/npm notice total files:\s*(\d+)/)
|
||||
const packageSizeMatch = output.match(
|
||||
/npm notice package size:\s*([\d.]+)\s*([KMGT]?B)/
|
||||
)
|
||||
const unpackedSizeMatch = output.match(
|
||||
/npm notice unpacked size:\s*([\d.]+)\s*([KMGT]?B)/
|
||||
)
|
||||
const totalFilesMatch = output.match(/npm notice total files:\s*(\d+)/)
|
||||
|
||||
const convertToMB = (size: number, unit: string): number => {
|
||||
switch (unit) {
|
||||
case 'B':
|
||||
return size / (1024 * 1024)
|
||||
case 'KB':
|
||||
return size / 1024
|
||||
case 'MB':
|
||||
return size
|
||||
case 'GB':
|
||||
return size * 1024
|
||||
default:
|
||||
return size / (1024 * 1024) // assume bytes
|
||||
const convertToMB = (size: number, unit: string): number => {
|
||||
switch (unit) {
|
||||
case 'B':
|
||||
return size / (1024 * 1024)
|
||||
case 'KB':
|
||||
return size / 1024
|
||||
case 'MB':
|
||||
return size
|
||||
case 'GB':
|
||||
return size * 1024
|
||||
default:
|
||||
return size / (1024 * 1024) // assume bytes
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const packedSizeMB = packageSizeMatch
|
||||
? convertToMB(parseFloat(packageSizeMatch[1]), packageSizeMatch[2])
|
||||
: 0
|
||||
const packedSizeMB = packageSizeMatch
|
||||
? convertToMB(parseFloat(packageSizeMatch[1]), packageSizeMatch[2])
|
||||
: 0
|
||||
|
||||
const unpackedSizeMB = unpackedSizeMatch
|
||||
? convertToMB(parseFloat(unpackedSizeMatch[1]), unpackedSizeMatch[2])
|
||||
: 0
|
||||
const unpackedSizeMB = unpackedSizeMatch
|
||||
? convertToMB(parseFloat(unpackedSizeMatch[1]), unpackedSizeMatch[2])
|
||||
: 0
|
||||
|
||||
const totalFiles = totalFilesMatch ? parseInt(totalFilesMatch[1], 10) : 0
|
||||
const totalFiles = totalFilesMatch ? parseInt(totalFilesMatch[1], 10) : 0
|
||||
|
||||
return { packedSizeMB, unpackedSizeMB, totalFiles }
|
||||
return {packedSizeMB, unpackedSizeMB, totalFiles}
|
||||
}
|
||||
|
||||
/**
|
||||
* Cached npm package size result to avoid multiple expensive npm pack calls
|
||||
*/
|
||||
let cachedPackageSize: {
|
||||
packedSizeMB: number
|
||||
unpackedSizeMB: number
|
||||
totalFiles: number
|
||||
packedSizeMB: number
|
||||
unpackedSizeMB: number
|
||||
totalFiles: number
|
||||
} | null = null
|
||||
|
||||
/**
|
||||
|
|
@ -68,79 +68,79 @@ let cachedPackageSize: {
|
|||
* Results are cached to avoid multiple expensive executions
|
||||
*/
|
||||
async function getNpmPackageSize(): Promise<{
|
||||
packedSizeMB: number
|
||||
unpackedSizeMB: number
|
||||
totalFiles: number
|
||||
packedSizeMB: number
|
||||
unpackedSizeMB: number
|
||||
totalFiles: number
|
||||
}> {
|
||||
// Return cached result if available
|
||||
if (cachedPackageSize) {
|
||||
return cachedPackageSize
|
||||
}
|
||||
// Return cached result if available
|
||||
if (cachedPackageSize) {
|
||||
return cachedPackageSize
|
||||
}
|
||||
|
||||
try {
|
||||
// Use 2>&1 to capture both stdout and stderr in one command
|
||||
const output = execSync('npm pack --dry-run 2>&1', {
|
||||
encoding: 'utf8',
|
||||
cwd: process.cwd(),
|
||||
timeout: 45000 // 45 second timeout to prevent hanging
|
||||
})
|
||||
try {
|
||||
// Use 2>&1 to capture both stdout and stderr in one command
|
||||
const output = execSync('npm pack --dry-run 2>&1', {
|
||||
encoding: 'utf8',
|
||||
cwd: process.cwd(),
|
||||
timeout: 45000 // 45 second timeout to prevent hanging
|
||||
})
|
||||
|
||||
const result = parseNpmPackOutput(output)
|
||||
|
||||
// Cache the result for subsequent calls
|
||||
cachedPackageSize = result
|
||||
|
||||
return result
|
||||
} catch (error) {
|
||||
throw new Error(`Failed to get npm package size: ${error}`)
|
||||
}
|
||||
const result = parseNpmPackOutput(output)
|
||||
|
||||
// Cache the result for subsequent calls
|
||||
cachedPackageSize = result
|
||||
|
||||
return result
|
||||
} catch (error) {
|
||||
throw new Error(`Failed to get npm package size: ${error}`)
|
||||
}
|
||||
}
|
||||
|
||||
describe('Package Size Limits', () => {
|
||||
it('should not exceed unpacked size threshold for npm package', async () => {
|
||||
const { unpackedSizeMB } = await getNpmPackageSize()
|
||||
const maxAllowedSize =
|
||||
CURRENT_UNPACKED_SIZE_MB * (1 + ALLOWED_SIZE_INCREASE_PERCENTAGE / 100)
|
||||
it('should not exceed unpacked size threshold for npm package', async () => {
|
||||
const {unpackedSizeMB} = await getNpmPackageSize()
|
||||
const maxAllowedSize =
|
||||
CURRENT_UNPACKED_SIZE_MB * (1 + ALLOWED_SIZE_INCREASE_PERCENTAGE / 100)
|
||||
|
||||
console.log(`Current unpacked package size: ${unpackedSizeMB.toFixed(2)}MB`)
|
||||
console.log(`Maximum allowed unpacked size: ${maxAllowedSize.toFixed(2)}MB`)
|
||||
console.log(`Current unpacked package size: ${unpackedSizeMB.toFixed(2)}MB`)
|
||||
console.log(`Maximum allowed unpacked size: ${maxAllowedSize.toFixed(2)}MB`)
|
||||
|
||||
expect(
|
||||
unpackedSizeMB,
|
||||
`Unpacked package size (${unpackedSizeMB.toFixed(2)}MB) exceeds maximum allowed size (${maxAllowedSize.toFixed(2)}MB)`
|
||||
).toBeLessThanOrEqual(maxAllowedSize)
|
||||
})
|
||||
expect(
|
||||
unpackedSizeMB,
|
||||
`Unpacked package size (${unpackedSizeMB.toFixed(2)}MB) exceeds maximum allowed size (${maxAllowedSize.toFixed(2)}MB)`
|
||||
).toBeLessThanOrEqual(maxAllowedSize)
|
||||
})
|
||||
|
||||
it('should not exceed packed size threshold for npm package', async () => {
|
||||
const { packedSizeMB } = await getNpmPackageSize()
|
||||
const maxAllowedSize =
|
||||
CURRENT_PACKED_SIZE_MB * (1 + ALLOWED_SIZE_INCREASE_PERCENTAGE / 100)
|
||||
it('should not exceed packed size threshold for npm package', async () => {
|
||||
const {packedSizeMB} = await getNpmPackageSize()
|
||||
const maxAllowedSize =
|
||||
CURRENT_PACKED_SIZE_MB * (1 + ALLOWED_SIZE_INCREASE_PERCENTAGE / 100)
|
||||
|
||||
console.log(`Current packed package size: ${packedSizeMB.toFixed(2)}MB`)
|
||||
console.log(`Maximum allowed packed size: ${maxAllowedSize.toFixed(2)}MB`)
|
||||
console.log(`Current packed package size: ${packedSizeMB.toFixed(2)}MB`)
|
||||
console.log(`Maximum allowed packed size: ${maxAllowedSize.toFixed(2)}MB`)
|
||||
|
||||
expect(
|
||||
packedSizeMB,
|
||||
`Packed package size (${packedSizeMB.toFixed(2)}MB) exceeds maximum allowed size (${maxAllowedSize.toFixed(2)}MB)`
|
||||
).toBeLessThanOrEqual(maxAllowedSize)
|
||||
})
|
||||
expect(
|
||||
packedSizeMB,
|
||||
`Packed package size (${packedSizeMB.toFixed(2)}MB) exceeds maximum allowed size (${maxAllowedSize.toFixed(2)}MB)`
|
||||
).toBeLessThanOrEqual(maxAllowedSize)
|
||||
})
|
||||
|
||||
it('should report package composition details', async () => {
|
||||
const { packedSizeMB, unpackedSizeMB, totalFiles } =
|
||||
await getNpmPackageSize()
|
||||
it('should report package composition details', async () => {
|
||||
const {packedSizeMB, unpackedSizeMB, totalFiles} =
|
||||
await getNpmPackageSize()
|
||||
|
||||
console.log(`\nPackage composition:`)
|
||||
console.log(`- Total files: ${totalFiles}`)
|
||||
console.log(`- Packed size: ${packedSizeMB.toFixed(2)}MB`)
|
||||
console.log(`- Unpacked size: ${unpackedSizeMB.toFixed(2)}MB`)
|
||||
console.log(
|
||||
`- Compression ratio: ${((1 - packedSizeMB / unpackedSizeMB) * 100).toFixed(1)}%`
|
||||
)
|
||||
console.log(`\nPackage composition:`)
|
||||
console.log(`- Total files: ${totalFiles}`)
|
||||
console.log(`- Packed size: ${packedSizeMB.toFixed(2)}MB`)
|
||||
console.log(`- Unpacked size: ${unpackedSizeMB.toFixed(2)}MB`)
|
||||
console.log(
|
||||
`- Compression ratio: ${((1 - packedSizeMB / unpackedSizeMB) * 100).toFixed(1)}%`
|
||||
)
|
||||
|
||||
// Basic sanity checks
|
||||
expect(totalFiles).toBeGreaterThan(0)
|
||||
expect(packedSizeMB).toBeGreaterThan(0)
|
||||
expect(unpackedSizeMB).toBeGreaterThan(0)
|
||||
expect(packedSizeMB).toBeLessThan(unpackedSizeMB)
|
||||
})
|
||||
// Basic sanity checks
|
||||
expect(totalFiles).toBeGreaterThan(0)
|
||||
expect(packedSizeMB).toBeGreaterThan(0)
|
||||
expect(unpackedSizeMB).toBeGreaterThan(0)
|
||||
expect(packedSizeMB).toBeLessThan(unpackedSizeMB)
|
||||
})
|
||||
})
|
||||
|
|
|
|||
|
|
@ -222,15 +222,25 @@ describe('S3CompatibleStorage', () => {
|
|||
|
||||
// Create test verb
|
||||
const testVector: Vector = [0.1, 0.2, 0.3, 0.4, 0.5]
|
||||
const timestamp = {
|
||||
seconds: Math.floor(Date.now() / 1000),
|
||||
nanoseconds: (Date.now() % 1000) * 1000000
|
||||
}
|
||||
const testVerb = {
|
||||
id: 'test-verb-1',
|
||||
vector: testVector,
|
||||
connections: new Map(),
|
||||
sourceId: 'source-noun-1',
|
||||
targetId: 'target-noun-1',
|
||||
type: 'test-relation',
|
||||
source: 'source-noun-1',
|
||||
target: 'target-noun-1',
|
||||
verb: 'test-relation',
|
||||
weight: 0.75,
|
||||
metadata: { description: 'Test relation' }
|
||||
metadata: { description: 'Test relation' },
|
||||
createdAt: timestamp,
|
||||
updatedAt: timestamp,
|
||||
createdBy: {
|
||||
augmentation: 'test-service',
|
||||
version: '1.0'
|
||||
}
|
||||
}
|
||||
|
||||
// Save the verb
|
||||
|
|
|
|||
158
tests/statistics-storage.test.ts
Normal file
158
tests/statistics-storage.test.ts
Normal file
|
|
@ -0,0 +1,158 @@
|
|||
/**
|
||||
* Test script for the statistics storage implementation
|
||||
*
|
||||
* This script tests:
|
||||
* 1. Saving statistics data
|
||||
* 2. Retrieving statistics data
|
||||
* 3. Verifying that the data is correctly saved and retrieved
|
||||
* 4. Checking that time-based partitioning works correctly
|
||||
* 5. Checking that backward compatibility is maintained
|
||||
*/
|
||||
|
||||
// Import required modules
|
||||
// @ts-expect-error - dotenv doesn't have TypeScript types
|
||||
import { config } from 'dotenv'
|
||||
import { setTimeout } from 'timers/promises'
|
||||
import { describe, it, expect, beforeAll, beforeEach } from 'vitest'
|
||||
import { S3Client, ListObjectsV2Command } from '@aws-sdk/client-s3'
|
||||
import * as process from 'process'
|
||||
|
||||
// Define types for statistics data
|
||||
interface ServiceStatistics {
|
||||
nounCount: number
|
||||
verbCount: number
|
||||
metadataCount: number
|
||||
}
|
||||
|
||||
interface StatisticsData {
|
||||
nounCount: Record<string, number>
|
||||
verbCount: Record<string, number>
|
||||
metadataCount: Record<string, number>
|
||||
hnswIndexSize: number
|
||||
lastUpdated: string
|
||||
}
|
||||
|
||||
// Define types for storage configuration
|
||||
interface S3StorageConfig {
|
||||
endpoint: string
|
||||
region: string
|
||||
bucketName: string
|
||||
accessKeyId: string
|
||||
secretAccessKey: string
|
||||
prefix: string
|
||||
serviceType?: string
|
||||
sessionToken?: string
|
||||
accountId?: string
|
||||
}
|
||||
|
||||
// Load environment variables
|
||||
config()
|
||||
|
||||
// Create test statistics data
|
||||
const testStatistics: StatisticsData = {
|
||||
nounCount: { 'test-service': 100, 'another-service': 50 },
|
||||
verbCount: { 'test-service': 75, 'another-service': 25 },
|
||||
metadataCount: { 'test-service': 100, 'another-service': 50 },
|
||||
hnswIndexSize: 150,
|
||||
lastUpdated: new Date().toISOString()
|
||||
}
|
||||
|
||||
// Test configuration
|
||||
const storageConfig: S3StorageConfig = {
|
||||
endpoint: process.env.S3_ENDPOINT || 'http://localhost:9000',
|
||||
region: process.env.S3_REGION || 'us-east-1',
|
||||
bucketName: process.env.S3_BUCKET || 'test-bucket',
|
||||
accessKeyId: process.env.S3_ACCESS_KEY,
|
||||
secretAccessKey: process.env.S3_SECRET_KEY,
|
||||
prefix: 'test-statistics/'
|
||||
}
|
||||
|
||||
// Check if required S3 credentials are available
|
||||
const hasS3Credentials = !!process.env.S3_ACCESS_KEY && !!process.env.S3_SECRET_KEY;
|
||||
|
||||
// Use conditional describe to skip all tests if credentials are missing
|
||||
(hasS3Credentials ? describe : describe.skip)('Statistics Storage', () => {
|
||||
let storage: any
|
||||
let s3Client: S3Client
|
||||
|
||||
beforeAll(async () => {
|
||||
if (!hasS3Credentials) {
|
||||
console.log('Skipping S3 storage tests: S3_ACCESS_KEY or S3_SECRET_KEY environment variables not set')
|
||||
return
|
||||
}
|
||||
|
||||
try {
|
||||
// Import S3CompatibleStorage dynamically to avoid issues with dynamic imports
|
||||
const { S3CompatibleStorage } = await import('../dist/storage/adapters/s3CompatibleStorage')
|
||||
|
||||
// Create storage instance
|
||||
storage = new S3CompatibleStorage(storageConfig)
|
||||
await storage.init()
|
||||
|
||||
// Initialize S3 client for checking files
|
||||
s3Client = new S3Client({
|
||||
endpoint: storageConfig.endpoint,
|
||||
region: storageConfig.region,
|
||||
credentials: {
|
||||
accessKeyId: storageConfig.accessKeyId,
|
||||
secretAccessKey: storageConfig.secretAccessKey
|
||||
}
|
||||
})
|
||||
} catch (error) {
|
||||
console.log('Error initializing S3 storage:', error)
|
||||
throw error // Let the test fail with a clear error message
|
||||
}
|
||||
})
|
||||
|
||||
it('should save statistics data', async () => {
|
||||
await storage.saveStatistics(testStatistics)
|
||||
expect(true).toBe(true) // If no error is thrown, the test passes
|
||||
})
|
||||
|
||||
it('should retrieve statistics data after batch update completes', async () => {
|
||||
// Wait for the batch update to complete (longer than MAX_FLUSH_DELAY_MS)
|
||||
await setTimeout(35000)
|
||||
|
||||
const retrievedStats = await storage.getStatistics()
|
||||
expect(retrievedStats).not.toBeNull()
|
||||
|
||||
// Check that all properties match
|
||||
expect(JSON.stringify(retrievedStats.nounCount)).toBe(JSON.stringify(testStatistics.nounCount))
|
||||
expect(JSON.stringify(retrievedStats.verbCount)).toBe(JSON.stringify(testStatistics.verbCount))
|
||||
expect(JSON.stringify(retrievedStats.metadataCount)).toBe(JSON.stringify(testStatistics.metadataCount))
|
||||
expect(retrievedStats.hnswIndexSize).toBe(testStatistics.hnswIndexSize)
|
||||
})
|
||||
|
||||
it('should store statistics in time-partitioned files', async () => {
|
||||
// Get current date in YYYYMMDD format
|
||||
const now = new Date()
|
||||
const year = now.getUTCFullYear()
|
||||
const month = String(now.getUTCMonth() + 1).padStart(2, '0')
|
||||
const day = String(now.getUTCDate()).padStart(2, '0')
|
||||
const dateStr = `${year}${month}${day}`
|
||||
|
||||
// Check if the file exists in the expected location
|
||||
const listResponse = await s3Client.send(new ListObjectsV2Command({
|
||||
Bucket: storageConfig.bucketName,
|
||||
Prefix: `${storageConfig.prefix}index/statistics_${dateStr}`
|
||||
}))
|
||||
|
||||
expect(listResponse.Contents).toBeDefined()
|
||||
expect(listResponse.Contents?.length).toBeGreaterThan(0)
|
||||
})
|
||||
|
||||
it('should maintain backward compatibility with legacy statistics file', async () => {
|
||||
// Check if the legacy file exists
|
||||
const legacyListResponse = await s3Client.send(new ListObjectsV2Command({
|
||||
Bucket: storageConfig.bucketName,
|
||||
Prefix: `${storageConfig.prefix}index/statistics.json`
|
||||
}))
|
||||
|
||||
// This test is informational - the legacy file may not exist if the 10% random update didn't trigger
|
||||
if (legacyListResponse.Contents && legacyListResponse.Contents.length > 0) {
|
||||
expect(legacyListResponse.Contents.length).toBeGreaterThan(0)
|
||||
} else {
|
||||
console.log('Legacy statistics file not found. This is expected if the 10% random update didn\'t trigger.')
|
||||
}
|
||||
})
|
||||
})
|
||||
132
tests/statistics.test.ts
Normal file
132
tests/statistics.test.ts
Normal file
|
|
@ -0,0 +1,132 @@
|
|||
/**
|
||||
* Statistics Functionality Tests
|
||||
* Tests the getStatistics function as a consumer would use it
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeAll } from 'vitest'
|
||||
|
||||
/**
|
||||
* 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('Brainy Statistics Functionality', () => {
|
||||
let brainy: any
|
||||
|
||||
beforeAll(async () => {
|
||||
// Load brainy library as a consumer would
|
||||
brainy = await import('../dist/unified.js')
|
||||
})
|
||||
|
||||
describe('Library Exports', () => {
|
||||
it('should export getStatistics function at the root level', () => {
|
||||
expect(brainy.getStatistics).toBeDefined()
|
||||
expect(typeof brainy.getStatistics).toBe('function')
|
||||
})
|
||||
})
|
||||
|
||||
describe('getStatistics Functionality', () => {
|
||||
it('should retrieve statistics from a BrainyData instance', async () => {
|
||||
// Create a BrainyData instance
|
||||
const data = new brainy.BrainyData({
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
await data.init()
|
||||
await data.clear() // Clear any existing data
|
||||
|
||||
// Add some test data
|
||||
await data.add(createTestVector(0), { id: 'v1', label: 'x-axis' })
|
||||
await data.add(createTestVector(1), { id: 'v2', label: 'y-axis' })
|
||||
await data.add(createTestVector(2), { id: 'v3', label: 'z-axis' })
|
||||
|
||||
// Add a verb
|
||||
await data.addVerb('v1', 'v2', createTestVector(3), { type: 'connected_to' })
|
||||
|
||||
// Get statistics using the standalone function
|
||||
const stats = await brainy.getStatistics(data)
|
||||
|
||||
// Verify statistics
|
||||
expect(stats).toBeDefined()
|
||||
expect(stats.nounCount).toBe(3)
|
||||
expect(stats.verbCount).toBe(1)
|
||||
expect(stats.metadataCount).toBe(3) // Each noun has metadata
|
||||
expect(stats.hnswIndexSize).toBe(3)
|
||||
})
|
||||
|
||||
it('should throw an error when no instance is provided', async () => {
|
||||
await expect(brainy.getStatistics()).rejects.toThrow('BrainyData instance must be provided')
|
||||
})
|
||||
|
||||
it('should match the instance method results', async () => {
|
||||
// Create a BrainyData instance
|
||||
const data = new brainy.BrainyData({})
|
||||
|
||||
await data.init()
|
||||
|
||||
// Add some test data
|
||||
await data.add(createTestVector(5), { id: 'test1' })
|
||||
|
||||
// Get statistics using both methods
|
||||
const instanceStats = await data.getStatistics()
|
||||
const functionStats = await brainy.getStatistics(data)
|
||||
|
||||
// Verify they match
|
||||
expect(functionStats).toEqual(instanceStats)
|
||||
})
|
||||
|
||||
it('should track statistics by service', async () => {
|
||||
// Create a BrainyData instance
|
||||
const data = new brainy.BrainyData({
|
||||
metric: 'euclidean'
|
||||
})
|
||||
|
||||
await data.init()
|
||||
await data.clear() // Clear any existing data
|
||||
|
||||
// Add data from different services
|
||||
await data.add(createTestVector(10), { id: 'v1', label: 'service1-item' }, { service: 'service1' })
|
||||
await data.add(createTestVector(20), { id: 'v2', label: 'service1-item' }, { service: 'service1' })
|
||||
await data.add(createTestVector(30), { id: 'v3', label: 'service2-item' }, { service: 'service2' })
|
||||
|
||||
// Add verbs from different services
|
||||
await data.addVerb('v1', 'v2', undefined, { type: 'related_to', service: 'service1' })
|
||||
await data.addVerb('v2', 'v3', undefined, { type: 'related_to', service: 'service2' })
|
||||
|
||||
// Get statistics for all services
|
||||
const allStats = await data.getStatistics()
|
||||
|
||||
// Verify total counts
|
||||
expect(allStats.nounCount).toBe(3)
|
||||
expect(allStats.verbCount).toBe(2)
|
||||
expect(allStats.metadataCount).toBe(3)
|
||||
|
||||
// Verify service breakdown exists
|
||||
expect(allStats.serviceBreakdown).toBeDefined()
|
||||
|
||||
// Verify service1 statistics
|
||||
const service1Stats = await data.getStatistics({ service: 'service1' })
|
||||
expect(service1Stats.nounCount).toBe(2)
|
||||
expect(service1Stats.verbCount).toBe(1)
|
||||
expect(service1Stats.metadataCount).toBe(2)
|
||||
|
||||
// Verify service2 statistics
|
||||
const service2Stats = await data.getStatistics({ service: 'service2' })
|
||||
expect(service2Stats.nounCount).toBe(1)
|
||||
expect(service2Stats.verbCount).toBe(1)
|
||||
expect(service2Stats.metadataCount).toBe(1)
|
||||
|
||||
// Verify multiple services filter
|
||||
const combinedStats = await data.getStatistics({ service: ['service1', 'service2'] })
|
||||
expect(combinedStats.nounCount).toBe(3)
|
||||
expect(combinedStats.verbCount).toBe(2)
|
||||
expect(combinedStats.metadataCount).toBe(3)
|
||||
})
|
||||
})
|
||||
})
|
||||
|
|
@ -1,6 +1,17 @@
|
|||
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')
|
||||
|
|
@ -14,23 +25,21 @@ describe('Vector Operations', () => {
|
|||
const brainy = await import('../dist/unified.js')
|
||||
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 3,
|
||||
distanceFunction: euclideanDistance
|
||||
})
|
||||
|
||||
expect(db).toBeDefined()
|
||||
expect(db.dimensions).toBe(3)
|
||||
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 2D vector operations', async () => {
|
||||
it('should handle simple vector operations', async () => {
|
||||
const brainy = await import('../dist/unified.js')
|
||||
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 2,
|
||||
distanceFunction: euclideanDistance
|
||||
})
|
||||
|
||||
|
|
@ -38,10 +47,11 @@ describe('Vector Operations', () => {
|
|||
await db.clear() // Clear any existing data
|
||||
|
||||
// Add a simple vector
|
||||
await db.add([1, 2], { id: 'test' })
|
||||
const testVector = createTestVector(1)
|
||||
await db.add(testVector, { id: 'test' })
|
||||
|
||||
// Search for the same vector
|
||||
const results = await db.search([1, 2], 1)
|
||||
const results = await db.search(testVector, 1)
|
||||
|
||||
expect(results).toBeDefined()
|
||||
expect(results.length).toBeGreaterThan(0)
|
||||
|
|
@ -52,7 +62,6 @@ describe('Vector Operations', () => {
|
|||
const brainy = await import('../dist/unified.js')
|
||||
|
||||
const db = new brainy.BrainyData({
|
||||
dimensions: 3,
|
||||
distanceFunction: euclideanDistance
|
||||
})
|
||||
|
||||
|
|
@ -60,13 +69,17 @@ describe('Vector Operations', () => {
|
|||
await db.clear() // Clear any existing data
|
||||
|
||||
// Add multiple vectors
|
||||
await db.add([1, 0, 0], { id: 'vec1', type: 'unit' })
|
||||
await db.add([0, 1, 0], { id: 'vec2', type: 'unit' })
|
||||
await db.add([0, 0, 1], { id: 'vec3', type: 'unit' })
|
||||
await db.add([0.5, 0.5, 0], { id: 'vec4', type: 'mixed' })
|
||||
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([1, 0, 0], 3)
|
||||
const results = await db.search(createTestVector(0), 3)
|
||||
|
||||
expect(results).toBeDefined()
|
||||
expect(results.length).toBeGreaterThanOrEqual(1)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue