為程式碼擷取作業產生嵌入

這個範例示範如何使用 Vertex AI 文字嵌入模型，計算程式碼區塊和查詢的嵌入，以執行程式碼擷取工作。

深入探索

如需包含這個程式碼範例的詳細說明文件，請參閱下列文章：

• 選擇嵌入工作類型

程式碼範例

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Vertex AI 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Vertex AI Python API 參考文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

from vertexai.language_models import TextEmbeddingInput, TextEmbeddingModel

MODEL_NAME = "gemini-embedding-001"
DIMENSIONALITY = 3072


def embed_text(
    texts: list[str] = ["Retrieve a function that adds two numbers"],
    task: str = "CODE_RETRIEVAL_QUERY",
    model_name: str = "gemini-embedding-001",
    dimensionality: int | None = 3072,
) -> list[list[float]]:
    """Embeds texts with a pre-trained, foundational model."""
    model = TextEmbeddingModel.from_pretrained(model_name)
    kwargs = dict(output_dimensionality=dimensionality) if dimensionality else {}

    embeddings = []
    # gemini-embedding-001 takes one input at a time
    for text in texts:
        text_input = TextEmbeddingInput(text, task)
        embedding = model.get_embeddings([text_input], **kwargs)
        print(embedding)
        # Example response:
        # [[0.006135190837085247, -0.01462465338408947, 0.004978656303137541, ...]]
        embeddings.append(embedding[0].values)

    return embeddings


if __name__ == "__main__":
    # Embeds code block with a pre-trained, foundational model.
    # Using this function to calculate the embedding for corpus.
    texts = ["Retrieve a function that adds two numbers"]
    task = "CODE_RETRIEVAL_QUERY"
    code_block_embeddings = embed_text(
        texts=texts, task=task, model_name=MODEL_NAME, dimensionality=DIMENSIONALITY
    )

    # Embeds code retrieval with a pre-trained, foundational model.
    # Using this function to calculate the embedding for query.
    texts = [
        "def func(a, b): return a + b",
        "def func(a, b): return a - b",
        "def func(a, b): return (a ** 2 + b ** 2) ** 0.5",
    ]
    task = "RETRIEVAL_DOCUMENT"
    code_query_embeddings = embed_text(
        texts=texts, task=task, model_name=MODEL_NAME, dimensionality=DIMENSIONALITY
    )

後續步驟

如要搜尋及篩選其他 Google Cloud 產品的程式碼範例，請參閱Google Cloud 瀏覽器範例。