通过Lambda调用SageMaker触发ModelError错误的排查求助

错误信息 #

调用Lambda请求SageMaker端点时返回400客户端错误，具体错误响应如下：

{
  "errorMessage": "An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary and could not load the entire response body. See CloudWatch日志组/aws/sagemaker/Endpoints/jira-endpoint获取详细信息.",
  "errorType": "ModelError",
  "stackTrace": [
    "  File \"/var/task/lambda_function.py\", line 19, in lambda_handler\n    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,\n",
    "  File \"/var/runtime/botocore/client.py\", line 565, in _api_call\n    return self._make_api_call(operation_name, kwargs)\n",
    "  File \"/var/runtime/botocore/client.py\", line 1021, in _make_api_call\n    raise error_class(parsed_response, operation_name)\n"
  ]
}

当前Lambda代码 #

import os, io, boto3, json, csv, base64

ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    project = event['project']
    # project = base64.b64decode(event['project'])
    # timeline = base64.b64decode(event['timeline'])
    
    # payload = """{}.
    #     Given the project description above, sugges a project tasklist to achieve the project goals.
    #     The project timeline is {} weeks.
    # """.format(project, timeline)

        
    payload = project
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,
                                       Body=project, ContentType="text/csv")

    result = json.loads(response["Body"].read().decode())
    print(result)
    return {
        "statusCode": 200,
        "headers": { "content-type": "application/json"},
        "body":  result
    }

问题分析与解决方案 #

核心问题 #

错误400表明请求格式不符合SageMaker端点的预期，当前代码存在两个明显问题：

• 请求ContentType设置为text/csv，但预构建模型通常期望JSON格式输入
• 请求Body直接传入原始字符串，未按模型要求的结构封装

解决步骤 #

1. 查看CloudWatch日志：进入指定的SageMaker端点日志组，获取模型返回的具体错误详情，明确输入格式要求
2. 匹配模型输入规范：
   大多数SageMaker预构建LLM模型（如JumpStart模型）期望JSON格式输入，示例结构：

   {"inputs": "你的提示文本内容"}
   

   此时ContentType需设置为application/json
3. 调整Lambda代码：
   修改请求格式，确保Body符合模型要求，示例代码如下：

   import os, boto3, json
   
   ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
   runtime= boto3.client('runtime.sagemaker')
   
   def lambda_handler(event, context):
       project = event['project']
       # 构建符合模型要求的JSON payload，可根据需求补充提示词
       payload = json.dumps({
           "inputs": f"{project}. Given the project description above, suggest a project tasklist to achieve the project goals."
       })
       response = runtime.invoke_endpoint(
           EndpointName=ENDPOINT_NAME,
           Body=payload,
           ContentType="application/json"
       )
       result = json.loads(response["Body"].read().decode())
       print(result)
       return {
           "statusCode": 200,
           "headers": {"content-type": "application/json"},
           "body": json.dumps(result)  # Lambda返回的body需为字符串类型
       }
   

4. 验证输入内容：确保event中的project字段为有效文本，若前端传入的是base64编码内容，需取消注释解码代码

内容的提问来源于stack exchange，提问作者Dru