View a markdown version of this page

Exemplos de referência da API Code Interpreter - Amazon Bedrock AgentCore
Execução de códigoComandos do terminalGerenciamento de arquivos

Exemplos de referência da API Code Interpreter

Esta seção fornece exemplos de referência para operações comuns do Code Interpreter usando diferentes abordagens. Cada exemplo mostra como realizar a mesma operação usando AWS CLI, Boto3 SDK e chamadas diretas de API.

Execução de código

Esses exemplos demonstram como executar código em uma sessão do Code Interpreter.

exemplo
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!\")"
    }
  }'

Comandos do terminal

Esses exemplos demonstram como executar comandos de terminal em uma sessão do Code Interpreter.

Executar comando

exemplo
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"
    }
  }'

Iniciar execução do comando

exemplo
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"
    }
  }'

Obter tarefa

exemplo
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>"
    }
  }'

Pare a tarefa de execução do comando

exemplo
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>"
    }
  }'

Gerenciamento de arquivos

Esses exemplos demonstram como gerenciar arquivos em uma sessão do Code Interpreter.

Gravar arquivos

exemplo
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"}]
    }
  }'

Ler arquivos

exemplo
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"]
    }
  }'

Remover arquivos

exemplo
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"]
    }
  }'

Listar arquivos

exemplo
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": ""
    }
  }'