Vertex AI 批处理的安全设置（Gemini Flash API）

Question

如何为 Vertex AI 的批量预测作业设置安全设置？

似乎无法在谷歌/文档上找到任何关于此的内容。

TypeError: BatchPredictionJob.submit() got an unexpected keyword argument 'model_parameters'

# File Format
# {"request":{"contents": [{"role": "user", "parts": [{"text": "Translate this sentence to French: Hello, how are you today?"}]}]}}

import os
import vertexai
from vertexai.preview.batch_prediction import BatchPredictionJob

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def batch_predict_gemini_createjob(
    input_uri: str, output_uri: str
) -> BatchPredictionJob:
    """Perform batch text prediction using a Gemini AI model.
    Args:
        input_uri (str): URI of the input file in BigQuery table or Google Cloud Storage.
            Example: "gs://[BUCKET]/[DATASET].jsonl" OR "bq://[PROJECT].[DATASET].[TABLE]"

        output_uri (str): URI of the output folder,  in BigQuery table or Google Cloud Storage.
            Example: "gs://[BUCKET]/[OUTPUT].jsonl" OR "bq://[PROJECT].[DATASET].[TABLE]"
    Returns:
        batch_prediction_job: The batch prediction job object containing details of the job.
    """

    import time

    input_uri ="gs://ge/in/vertex_batch_input.jsonl"
    output_uri ="gs://ge/out/"

    # Initialize vertexai
    vertexai.init(project=PROJECT_ID, location="us-central1")

    # Submit a batch prediction job with Gemini model
    batch_prediction_job = BatchPredictionJob.submit(
        source_model="gemini-1.5-flash-002",
        input_dataset=input_uri,
        output_uri_prefix=output_uri,
        model_parameters={
            "safety_settings": [
                {
                    "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
                    "method": "SEVERITY",
                    "threshold": "BLOCK_ONLY_HIGH"
                },
                {
                    "category": "HARM_CATEGORY_HATE_SPEECH",
                    "method": "SEVERITY",
                    "threshold": "BLOCK_ONLY_HIGH"
                },
                {
                    "category": "HARM_CATEGORY_HARASSMENT",
                    "method": "SEVERITY",
                    "threshold": "BLOCK_ONLY_HIGH"
                },
                {
                    "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
                    "method": "SEVERITY",
                    "threshold": "BLOCK_ONLY_HIGH"
                }
            ]
        }
    )

Answer 1

基于这些代码示例，在创建批量预测作业时，创建了单独的变量：

model_parameters_dict = {} model_parameters = json_format.ParseDict(model_parameters_dict, Value())

尝试使用此格式设置安全过滤器：

safety_settings = [
   SafetySetting(
       category=SafetySetting.HarmCategory.HARM_CATEGORY_HATE_SPEECH,
       threshold=SafetySetting.HarmBlockThreshold.BLOCK_ONLY_HIGH
   ),
   SafetySetting(
       category=SafetySetting.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
       threshold=SafetySetting.HarmBlockThreshold.BLOCK_ONLY_HIGH
   ),
   SafetySetting(
       category=SafetySetting.HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT,
       threshold=SafetySetting.HarmBlockThreshold.BLOCK_ONLY_HIGH
   ),
   SafetySetting(
       category=SafetySetting.HarmCategory.HARM_CATEGORY_HARASSMENT,
       threshold=SafetySetting.HarmBlockThreshold.BLOCK_ONLY_HIGH
   ),
]