Modelreacties verwerken en foutafhandeling

SkyCast Assistant verzorgt ook gepersonaliseerde weeralerts. Als onderdeel hiervan is gevraagd om een antwoord te genereren voor een gebruiker die de frequentie van zijn nieuwsbrief wil aanpassen. Gebruik Claude om het antwoord te genereren en parse het vervolgens zodat het eindbericht past in de compacte meldingsweergave van de app.

De json-bibliotheek, de bedrock-client en request_body zijn al geïmporteerd.

Deze oefening maakt deel uit van de cursus

Introductie tot Amazon Bedrock

Cursus bekijken

Oefeninstructies

Controleer of de sleutel 'output' bestaat in de data-dictionary.
Haal 'text' op uit de content in de berichtoutput.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

response = bedrock.invoke_model(modelId='amazon.nova-lite-v1:0', body=request_body)
data = json.loads(response['body'].read().decode())

# Check for the output key
if '____' in ____:
    response = data['output']['message']['content'][0]['____'][:100]
    print(response)
else:
    print('Key not found')

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Introductie tot Amazon Bedrock

SkillTag.level.intermediateSkillTag.label

4.8+

Begin de cursus gratis

Learn the fundamentals of Amazon Bedrock, AWS's fully managed foundation model service. Start with basic setup and authentication, explore available foundation models like Claude and Titan, and master essential API interactions. This chapter covers setting up a development environment, choosing appropriate models for a use case, and implementing proper API request handling, including streaming responses and error management.

Exercise 1: Accessing Amazon Bedrock Exercise 2: Initializing the Bedrock client Exercise 3: Retrieving Bedrock model details Exercise 4: Selecting a foundation model Exercise 5: Using the correct model in Bedrock Exercise 6: Generating text in Bedrock

In this chapter, you'll progress through three key lessons. Starting with the basics of text generation and response handling, you'll then advance to sophisticated prompt engineering techniques like few-shot learning and structured outputs. The final lesson covers model parameter optimization, teaching learners to fine-tune settings like temperature and token limits for optimal results. Each lesson builds upon the previous, moving from fundamental API interactions to advanced parameter control for specific use cases.

Exercise 1: Tekst genereren met taalmodellen Exercise 2: Prompts verbeteren met roltoewijzing Exercise 3: Modelreacties verwerken en foutafhandeling

Huidige oefening

Exercise 4: Categorisatie van foundation model-rapport Exercise 5: Prompt engineering-technieken toepassen Exercise 6: Implementeer few-shot learning voor meetkunde Exercise 7: Gestructureerde output-prompts maken Exercise 8: Werken met verschillende modelparameters Exercise 9: Creativiteit aanpassen met temperatuurregeling Exercise 10: Uitvoer sturen met top_p en max_tokens Exercise 11: Parameters voor productbeschrijvingen

In this chapter, you’ll build robust and responsible applications with Amazon Bedrock, moving beyond basic API interactions. Starting with conversational AI, you’ll master state management and context handling to create coherent chat experiences. You’ll then explore advanced prompting techniques, learning how to generate diverse content types while maintaining consistent style and tone. The chapter covers critical production aspects like error handling, rate limiting, and efficient response processing. Finally, you will implement ethical guardrails and safety measures, ensuring your AI applications are both powerful and responsible.

Exercise 1: Ethical considerations and guardrails Exercise 2: Product review moderation Exercise 3: Creating age-appropriate content filters Exercise 4: Managing AI conversations Exercise 5: Building a conversation-manager class Exercise 6: Making a conversation memory-aware Exercise 7: Advanced prompting strategies Exercise 8: Implementing chain of thought prompting Exercise 9: Styled content generation with Bedrock Exercise 10: Handling API responses and errors Exercise 11: Implementing rate limit handling Exercise 12: Implementing model fallbacks Exercise 13: Congratulations!