端侧语义搜索: 无需服务器的AI驱动搜索

// iOS使用ONNX Runtime
let session = try ORTSession(env: env, modelPath: embeddingModelPath)
let inputTensor = try ORTValue(tensorData: tokenizedInput, shape: shape)
let outputs = try session.run(withInputs: ["input_ids": inputTensor])
let embedding = outputs["embeddings"]!.tensorData()

// Android: 存储嵌入
fun storeEmbedding(db: SQLiteDatabase, contentId: Long, embedding: FloatArray) {
    val blob = ByteBuffer.allocate(embedding.size * 4)
    embedding.forEach { blob.putFloat(it) }
    db.execSQL(
        "INSERT INTO embeddings (content_id, vector) VALUES (?, ?)",
        arrayOf(contentId, blob.array())
    )
}

// 按相似度搜索
fun search(db: SQLiteDatabase, queryEmbedding: FloatArray, limit: Int): List<SearchResult> {
    val cursor = db.rawQuery("SELECT content_id, vector FROM embeddings", null)
    val results = mutableListOf<SearchResult>()

    while (cursor.moveToNext()) {
        val blob = cursor.getBlob(1)
        val stored = FloatArray(blob.size / 4)
        ByteBuffer.wrap(blob).asFloatBuffer().get(stored)

        val similarity = cosineSimilarity(queryEmbedding, stored)
        results.add(SearchResult(cursor.getLong(0), similarity))
    }

    return results.sortedByDescending { it.similarity }.take(limit)
}

func indexContent(_ content: Content) async {
    let embedding = await embeddingModel.encode(content.text)
    database.storeEmbedding(contentId: content.id, vector: embedding)
}

func search(query: String) async -> [Content] {
    let queryEmbedding = await embeddingModel.encode(query)
    let results = database.similaritySearch(queryEmbedding, limit: 10)
    return results.map { fetchContent($0.contentId) }
}