Einbeziehen von externem Kontext

Prompt-Engineering mit der OpenAI-API

Fouad Trad

Machine Learning Engineer

Der Bedarf an externem Kontext

Vortrainierte Sprachmodelle erkennen Informationen, auf denen sie trainiert wurden
Mehr Kontext bereitstellen
Mehr Genauigkeit und Effektivität

Symbol für einen Chatbot auf einem Mobiltelefon.

Informationsmangel in LLMs

Wissensstand

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.

Informationsmangel in LLMs

Angeforderte nicht öffentliche Informationen

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.

Wie gibt man zusätzliche Informationen?

Beispielhafte vorherige Gespräche
System-Prompt

Symbol mit zwei Nachrichtendialogfeldern zur Darstellung eines Gesprächsaspekts.

Beispielgespräche

Modell anleiten, spezifische Fragen zu beantworten

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.

Nachteil: könnte viele Stichproben benötigen

System-Prompt

Enthält den erforderlichen Kontext für Chatbot-Antworten

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.

Abschließender Hinweis

Frühere Methoden funktionieren gut für kleine Kontexte
Größere Kontexte erfordern ausgefeiltere Techniken

Symbol für eine Warnung.

Lass uns üben!

Prompt-Engineering mit der OpenAI-API