**feat(tests, docs): add test coverage for database operations and vector dimension standardization**

- **Tests**:
  - Introduced `database-operations.test.ts` to validate core database functionalities, including initialization, CRUD operations, statistics retrieval, and search capabilities.
  - Added `dimension-standardization.test.ts` to ensure vector dimension consistency (fixed at 512) throughout operations like embedding, configuration, and validation.
  - Enhanced test cases to include scenarios for adding, retrieving, and handling errors for incorrect vector dimensions.

- **Documentation**:
  - Created `VECTOR_DIMENSION_STANDARDIZATION.md` to detail the transition to standardizing vectors to 512 dimensions, rationale for the change, potential impacts, and migration steps.
  - Includes best practices for handling vectors and utilizing the built-in embedding functions.

**Purpose**: Improve system robustness with comprehensive test coverage focusing on critical database and vector operations while providing clear documentation for developers to adapt to the standardized vector dimensions.
This commit is contained in:
David Snelling 2025-07-25 13:45:44 -07:00
parent a010d3a92c
commit d130dabf33
3 changed files with 181 additions and 0 deletions

View 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)
})
})

View 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)
})
})