4.2 Lab: Build RAG Pipeline

# Tạo S3 bucket
aws s3 mb s3://workshop-rag-kb-$(aws sts get-caller-identity --query Account --output text) --region us-east-1

# Tạo sample document
echo "Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models from leading AI companies. It provides a single API to access models from Anthropic, Meta, Amazon, Cohere, and Mistral. Bedrock supports features like Knowledge Bases for RAG, Guardrails for content safety, and Agents for autonomous workflows." > bedrock-overview.txt

echo "Retrieval Augmented Generation (RAG) is a technique that enhances LLM responses by retrieving relevant information from external data sources. RAG reduces hallucination by grounding responses in factual data. Amazon Bedrock Knowledge Bases provides a managed RAG solution with automatic chunking, embedding, and vector storage." > rag-overview.txt

# Upload documents
aws s3 cp bedrock-overview.txt s3://workshop-rag-kb-$(aws sts get-caller-identity --query Account --output text)/
aws s3 cp rag-overview.txt s3://workshop-rag-kb-$(aws sts get-caller-identity --query Account --output text)/

import boto3
import json

client = boto3.client('bedrock-agent-runtime', region_name='us-east-1')

response = client.retrieve_and_generate(
    input={'text': 'What is RAG and how does Bedrock support it?'},
    retrieveAndGenerateConfiguration={
        'type': 'KNOWLEDGE_BASE',
        'knowledgeBaseConfiguration': {
            'knowledgeBaseId': '<YOUR_KB_ID>',
            'modelArn': 'arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-5-sonnet-20241022-v2:0'
        }
    }
)

print("Response:", response['output']['text'])
print("\nCitations:")
for citation in response.get('citations', []):
    for ref in citation.get('retrievedReferences', []):
        print(f"  - {ref['location']['s3Location']['uri']}")