Implementare il prompting con chain of thought

StellarStack sta per lanciare la sua piattaforma cloud di punta. Il team Marketing vuole un'email che spieghi perché gli sviluppatori dovrebbero migrare. Per guidare il ragionamento di Claude, aggiungerai una checklist di “think-step” al prompt.

La libreria json è già stata importata.

Questo esercizio fa parte del corso

Introduzione ad Amazon Bedrock

Visualizza il corso

Istruzioni dell'esercizio

Definisci tre passaggi che il modello dovrebbe seguire per preparare la risposta, usando un elenco numerato (1., 2., 3.).
Usando la lista steps per la chain of thought, compila il campo "text" di text_data aggiungendoli dopo "\nSteps: ".

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

def generate_message_content(text_data):
    steps = [
        # Outline the steps
        "____",
        "____",
        "____"
    ]
    # Append the steps to the prompt text
    text_data["text"] += "\nSteps: " + ____
    return text_data

text_data = {"text": "Create a promotional email for the StellarStack cloud platform."}
  
print(generate_message_content(text_data))

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Introduzione ad Amazon Bedrock

IntermediárioNível de habilidade

4.8+

Inizia il corso 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: Generating text with language models Exercise 2: Enhancing prompts with role assignment Exercise 3: Processing model responses and error handling Exercise 4: Foundation model report categorization Exercise 5: Applying prompt engineering techniques Exercise 6: Implement few-shot learning for geometry Exercise 7: Creating structured output prompts Exercise 8: Working with different model parameters Exercise 9: Adjusting creativity with temperature control Exercise 10: Controlling output with top_p and max_tokens Exercise 11: Parameters for product descriptions

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: Considerazioni etiche e guardrail Exercise 2: Moderazione delle recensioni di prodotto Exercise 3: Creare filtri per contenuti adatti all’età Exercise 4: Gestire le conversazioni con l'AI Exercise 5: Creare una classe per gestire le conversazioni Exercise 6: Rendere la conversazione consapevole della memoria Exercise 7: Strategie avanzate di prompting Exercise 8: Implementare il prompting con chain of thought

Esercizio in corso

Exercise 9: Generazione di contenuti con stile con Bedrock Exercise 10: Gestire le risposte e gli errori dell'API Exercise 11: Implementare la gestione dei rate limit Exercise 12: Implementare i fallback di modello Exercise 13: Congratulazioni!