View a markdown version of this page

程式碼解譯器 API 參考範例 - Amazon Bedrock AgentCore
程式碼執行終端機命令檔案管理

程式碼解譯器 API 參考範例

本節提供使用不同方法的常見程式碼解譯器操作參考範例。每個範例都會示範如何使用 AWS CLI、Boto3 SDK 和直接 API 呼叫執行相同的操作。

程式碼執行

這些範例示範如何在 Code Interpreter 工作階段中執行程式碼。

範例
Boto3

  1. params = {
      "language": "python",
      "code": "print(\"Hello, world!\")"
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "executeCode",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "executeCode",
    "arguments": {
      "language": "python",
      "code": "print(\"Hello, world!\")"
    }
  }'

終端機命令

這些範例示範如何在 Code Interpreter 工作階段中執行終端機命令。

執行命令

範例
Boto3

  1. params = {
      "command": "ls -l"
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "executeCommand",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "executeCommand",
    "arguments": {
      "command": "ls -l"
    }
  }'

啟動命令執行

範例
Boto3

  1. params = {
      "command": "sleep 15 && echo Task completed successfully"
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "startCommandExecution",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "startCommandExecution",
    "arguments": {
      "command": "sleep 15 && echo Task completed successfully"
    }
  }'

取得任務

範例
Boto3

  1. params = {
      "taskId": "<your-task-id>"
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "getTask",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "getTask",
    "arguments": {
      "taskId": "<your-task-id>"
    }
  }'

停止命令執行任務

範例
Boto3

  1. params = {
      "taskId": "<your-task-id>"
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "stopTask",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "stopTask",
    "arguments": {
      "taskId": "<your-task-id>"
    }
  }'

檔案管理

這些範例示範如何在 Code Interpreter 工作階段中管理檔案。

寫入檔案

範例
Boto3

  1. params = {
        "content": [{"path": "dir1/samename.txt", "text": "File in dir1"}]
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "writeFiles",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "writeFiles",
    "arguments": {
      "content": [{"path": "dir1/samename.txt", "text": "File in dir1"}]
    }
  }'

讀取檔案

範例
Boto3

  1. params = {
      "paths": ["tmp.txt"]
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "readFiles",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "readFiles",
    "arguments": {
      "paths": ["tmp.txt"]
    }
  }'

移除檔案

範例
Boto3

  1. params = {
      "paths": ["tmp.txt"]
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "removeFiles",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "removeFiles",
    "arguments": {
      "paths": ["tmp.txt"]
    }
  }'

列出檔案

範例
Boto3

  1. params = {
      "directoryPath": ""
    }

client.invoke_code_interpreter(
    **{
        "codeInterpreterIdentifier": "aws.codeinterpreter.v1",
        "sessionId": "<your-session-id>",
        "name": "listFiles",
        "arguments": params
    })
API

  1. # Using awscurl
awscurl -X POST \
  "https://bedrock-agentcore.<Region>.amazonaws.com/code-interpreters/aws.codeinterpreter.v1/tools/invoke" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "x-amzn-code-interpreter-session-id: your-session-id" \
  --service bedrock-agentcore \
  --region <Region> \
  -d '{
    "name": "listFiles",
    "arguments": {
      "directoryPath": ""
    }
  }'