Integrare contesto esterno

Prompt Engineering con l'API di OpenAI

Fouad Trad

Machine Learning Engineer

Perché serve contesto esterno

I modelli linguistici pre-addestrati riconoscono le info su cui sono stati addestrati
Serve fornire più contesto
Maggiore accuratezza ed efficacia

Icona che rappresenta un chatbot su uno smartphone.

Informazioni mancanti negli LLM

Knowledge cut-off

system_prompt = "Act as a financial expert that knows about the latest trends."

user_prompt = "What are the top financial trends in 2023?"

print(get_response(system_prompt, user_prompt))

I apologize for any inconvenience, but as of my last knowledge update in 
September 2021, I don't have information about financial trends in 2023.

Informazioni mancanti negli LLM

Richiesta di info non pubbliche

system_prompt = "Act as a study buddy that helps me with my studies to succeed 
in exams."


user_prompt = "What is the name of my favorite instructor?"

print(get_response(system_prompt, user_prompt))

I don't have personal information about you, including the name of your 
favorite instructor.

Come fornire info extra?

Conversazioni precedenti di esempio
Prompt di sistema

Icona con due fumetti per indicare una conversazione.

Conversazioni di esempio

Guida il modello a rispondere a domande specifiche

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "system",
             "content": "You are a customer service chatbot that responds to user queries in a gentle way"},

            {"role": "user",
             "content": "What services do you offer?"},

           {"role": "assistant",
             "content": "We provide services for web application development, mobile app development, and 
            custom software solutions."},

           {"role": "user",
             "content": "How many services do you have?"}])

print(response.choices[0].message.content)

We have 3 services including web application development, mobile app development, and custom software solutions.

Svantaggio: può servire un numero elevato di esempi

Prompt di sistema

Include il contesto necessario per le risposte del chatbot

services = "ABC Tech Solutions, a leading IT company, offers a range of services: 
application development, mobile app development, and custom software solutions."

system_prompt = f"""You are a customer service chatbot that responds to user 
queries in a gentle way. Some information about our services are delimited by 
triple backticks.
```{services}```"""

user_prompt = "How many services do you offer?"
print(get_response(system_prompt, user_prompt))

We have 3 services including web application development, mobile app development, 
and custom software solutions.

Nota finale

I metodi visti funzionano per contesti piccoli
Per contesti più ampi servono tecniche più sofisticate

Icona che rappresenta un avviso.

Ayo berlatih!

Prompt Engineering con l'API di OpenAI