AWS Bedrock

import boto3
import json
 
bedrock_runtime = boto3.client('bedrock-runtime')
 
# Invocación unificada — funciona con cualquier modelo
response = bedrock_runtime.converse(
    modelId='us.anthropic.claude-sonnet-4-20250514-v1:0',
    messages=[
        {
            'role': 'user',
            'content': [{'text': '¿Cuáles son las ventajas de arquitecturas event-driven?'}]
        }
    ],
    inferenceConfig={
        'maxTokens': 1000,
        'temperature': 0.7
    }
)
 
# Respuesta estructurada
output = response['output']['message']['content'][0]['text']
usage = response['usage']  # inputTokens, outputTokens
print(f"Tokens: {usage['inputTokens']} in, {usage['outputTokens']} out")

response = bedrock_runtime.converse_stream(
    modelId='us.anthropic.claude-sonnet-4-20250514-v1:0',
    messages=[
        {'role': 'user', 'content': [{'text': 'Explica event sourcing'}]}
    ],
    inferenceConfig={'maxTokens': 500}
)
 
for event in response['stream']:
    if 'contentBlockDelta' in event:
        print(event['contentBlockDelta']['delta']['text'], end='')

bedrock_agent = boto3.client('bedrock-agent')
 
agent_response = bedrock_agent.create_agent(
    agentName='support-agent',
    foundationModel='anthropic.claude-sonnet-4-20250514-v1:0',
    instruction='''Eres un agente de soporte técnico.
    Usa las herramientas disponibles para:
    1. Consultar el estado de pedidos
    2. Buscar documentación técnica
    3. Crear tickets de soporte''',
    actionGroups=[
        {
            'actionGroupName': 'order-tools',
            'actionGroupExecutor': {
                'lambda': 'arn:aws:lambda:us-east-1:<account-id>:function:order-lookup'
            },
            'apiSchema': {
                's3': {
                    's3BucketName': 'agent-schemas',
                    's3ObjectKey': 'order-api-schema.json'
                }
            }
        }
    ]
)

kb_response = bedrock_agent.create_knowledge_base(
    name='technical-docs-kb',
    description='Documentación técnica de la empresa',
    roleArn='arn:aws:iam::<account-id>:role/BedrockKBRole',
    knowledgeBaseConfiguration={
        'type': 'VECTOR',
        'vectorKnowledgeBaseConfiguration': {
            'embeddingModelArn': 'arn:aws:bedrock:us-east-1::foundation-model/amazon.titan-embed-text-v2:0'
        }
    },
    storageConfiguration={
        'type': 'OPENSEARCH_SERVERLESS',
        'opensearchServerlessConfiguration': {
            'collectionArn': 'arn:aws:aoss:us-east-1:<account-id>:collection/kb-collection',
            'vectorIndexName': 'bedrock-kb-index',
            'fieldMapping': {
                'vectorField': 'bedrock-knowledge-base-default-vector',
                'textField': 'AMAZON_BEDROCK_TEXT_CHUNK',
                'metadataField': 'AMAZON_BEDROCK_METADATA'
            }
        }
    }
)
 
# Configurar fuente de datos con chunking
data_source = bedrock_agent.create_data_source(
    knowledgeBaseId=kb_response['knowledgeBase']['knowledgeBaseId'],
    name='s3-docs',
    dataSourceConfiguration={
        'type': 'S3',
        's3Configuration': {
            'bucketArn': 'arn:aws:s3:::my-docs-bucket',
            'inclusionPrefixes': ['technical-docs/']
        }
    },
    vectorIngestionConfiguration={
        'chunkingConfiguration': {
            'chunkingStrategy': 'FIXED_SIZE',
            'fixedSizeChunkingConfiguration': {
                'maxTokens': 512,
                'overlapPercentage': 20
            }
        }
    }
)

bedrock = boto3.client('bedrock')
 
guardrail = bedrock.create_guardrail(
    name='enterprise-guardrail',
    description='Filtros para contenido empresarial',
    topicPolicyConfig={
        'topicsConfig': [
            {
                'name': 'Financial Advice',
                'definition': 'Evitar consejos financieros específicos',
                'examples': ['¿Debo invertir en acciones?'],
                'type': 'DENY'
            }
        ]
    },
    contentPolicyConfig={
        'filtersConfig': [
            {'type': 'SEXUAL', 'inputStrength': 'HIGH', 'outputStrength': 'HIGH'},
            {'type': 'VIOLENCE', 'inputStrength': 'MEDIUM', 'outputStrength': 'MEDIUM'}
        ]
    },
    sensitiveInformationPolicyConfig={
        'piiEntitiesConfig': [
            {'type': 'EMAIL', 'action': 'BLOCK'},
            {'type': 'PHONE', 'action': 'ANONYMIZE'}
        ]
    }
)
 
# Aplicar guardrails con Converse API
response = bedrock_runtime.converse(
    modelId='us.anthropic.claude-sonnet-4-20250514-v1:0',
    messages=[{'role': 'user', 'content': [{'text': 'Pregunta del usuario'}]}],
    guardrailConfig={
        'guardrailIdentifier': guardrail['guardrailId'],
        'guardrailVersion': '1'
    },
    inferenceConfig={'maxTokens': 1000}
)