使用 Google Cloud Model Garden 部署 Voyage AI模型

from vertexai import model_garden
MODEL_NAME = "mongodb/voyage-4@latest"
model = model_garden.OpenModel(MODEL_NAME)
deploy_options = model.list_deploy_options(concise=True)
print(deploy_options)

# Choose whether to deploy a new model or use an existing endpoint:
deployment_option = "deploy_new"  # ["deploy_new", "use_existing"]
# If using existing endpoint, provide the endpoint ID:
ENDPOINT_ID = ""  # {type:"string"}
if deployment_option == "deploy_new":
    print("Deploying new model...")
    endpoint = model.deploy(
        machine_type="a3-highgpu-1g",
        accelerator_type="NVIDIA_H100_80GB",
        accelerator_count=1,
        accept_eula=True,
        use_dedicated_endpoint=True,
    )
    print(f"Endpoint deployed: {endpoint.display_name}")
    print(f"Endpoint resource name: {endpoint.resource_name}")
else:
    if not ENDPOINT_ID:
        raise ValueError("Please provide an ENDPOINT_ID when using existing endpoint")
    from google.cloud import aiplatform
    print(f"Connecting to existing endpoint: {ENDPOINT_ID}")
    endpoint = aiplatform.Endpoint(
        endpoint_name=f"projects/{PROJECT_ID}/locations/{LOCATION}/endpoints/{ENDPOINT_ID}"
    )
    print(f"Using endpoint: {endpoint.display_name}")
    print(f"Endpoint resource name: {endpoint.resource_name}")

import json
# Multiple texts to embed
texts = [
    "Machine learning enables computers to learn from data.",
    "Natural language processing helps computers understand human language.",
    "Computer vision allows machines to interpret visual information.",
    "Deep learning uses neural networks with multiple layers."
]
# Prepare the batch request and make invoke call
body = {
    "input": texts,
    "output_dimension": 1024,
    "input_type": "document"
}
response = endpoint.invoke(
    request_path="/embeddings",
    body=json.dumps(body).encode("utf-8"),
    headers={"Content-Type": "application/json"}
)
# Extract embeddings
result = response.json()
embeddings = [item["embedding"] for item in result["data"]]
print(f"Number of texts embedded: {len(embeddings)}")
print(f"Embedding dimension: {len(embeddings[0])}")
print(f"\nFirst embedding (first 5 values): {embeddings[0][:5]}")
print(f"Second embedding (first 5 values): {embeddings[1][:5]}")