MarkBase Admin
79 lines
3.2 KiB
Swift
79 lines
3.2 KiB
Swift
import XCTest
|
|
@testable import MarkBase
|
|
|
|
final class MultilangEmbeddingTest: XCTestCase {
|
|
var engine: MarkBaseEngine!
|
|
var embeddingModel: TextEmbeddingModel!
|
|
let modelDir = "/Users/accusys/MarkBaseEngine/models/E4B-MarkBase"
|
|
|
|
override func setUp() {
|
|
super.setUp()
|
|
guard FileManager.default.fileExists(atPath: modelDir + "/model.safetensors") else { return }
|
|
engine = try? MarkBaseEngine(autoCompile: true)
|
|
embeddingModel = try? TextEmbeddingModel(modelDir: modelDir, engine: engine, config: TextEmbeddingConfig())
|
|
}
|
|
|
|
func testMultilangEmbeddings() throws {
|
|
try XCTSkipIf(embeddingModel == nil, "Model not found")
|
|
|
|
let texts: [String: String] = [
|
|
"en": "The weather is beautiful today",
|
|
"zh": "今天天氣很好",
|
|
"ja": "今日は天気がいいです",
|
|
"ko": "오늘 날씨가 좋습니다",
|
|
"es": "El clima está hermoso hoy",
|
|
"fr": "Il fait beau aujourd'hui",
|
|
"de": "Das Wetter ist heute schön",
|
|
"ru": "Сегодня прекрасная погода",
|
|
"ar": "الطقس جميل اليوم",
|
|
"hi": "आज मौसम बहुत सुंदर है"
|
|
]
|
|
|
|
var embeddings: [String: [Float]] = [:]
|
|
for (lang, text) in texts {
|
|
let emb = try embeddingModel.embed(text: text)
|
|
XCTAssertEqual(emb.count, 2560, "\(lang) embedding dimension")
|
|
let norm = sqrt(emb.reduce(0) { $0 + $1 * $1 })
|
|
XCTAssertEqual(norm, 1.0, accuracy: 0.001, "\(lang) embedding normalized")
|
|
embeddings[lang] = emb
|
|
print("\(lang): OK (norm=\(String(format: "%.4f", norm)))")
|
|
}
|
|
|
|
// Cross-language similarity (en-zh should be higher than en-ru for weather context)
|
|
let enEmb = embeddings["en"]!
|
|
let zhEmb = embeddings["zh"]!
|
|
let jaEmb = embeddings["ja"]!
|
|
|
|
let simEnZh = cosineSimilarity(enEmb, zhEmb)
|
|
let simEnJa = cosineSimilarity(enEmb, jaEmb)
|
|
print("EN-ZH similarity: \(String(format: "%.4f", simEnZh))")
|
|
print("EN-JA similarity: \(String(format: "%.4f", simEnJa))")
|
|
}
|
|
|
|
func testCrossLingualSemanticSimilarity() throws {
|
|
try XCTSkipIf(embeddingModel == nil, "Model not found")
|
|
|
|
// Same meaning, different languages
|
|
let enCat = try embeddingModel.embed(text: "The cat is sleeping")
|
|
let zhCat = try embeddingModel.embed(text: "貓在睡覺")
|
|
let enDog = try embeddingModel.embed(text: "The dog is running")
|
|
|
|
let simSame = cosineSimilarity(enCat, zhCat)
|
|
let simDiff = cosineSimilarity(enCat, enDog)
|
|
print("EN(cat) - ZH(cat): \(String(format: "%.4f", simSame))")
|
|
print("EN(cat) - EN(dog): \(String(format: "%.4f", simDiff))")
|
|
print("Cross-lingual > Same-lingual different topic: \(simSame > simDiff)")
|
|
}
|
|
|
|
private func cosineSimilarity(_ a: [Float], _ b: [Float]) -> Float {
|
|
guard a.count == b.count, !a.isEmpty else { return 0 }
|
|
var dot: Float = 0, normA: Float = 0, normB: Float = 0
|
|
for i in 0..<a.count {
|
|
dot += a[i] * b[i]
|
|
normA += a[i] * a[i]
|
|
normB += b[i] * b[i]
|
|
}
|
|
return dot / (sqrt(normA) * sqrt(normB))
|
|
}
|
|
}
|