Inkorporera extern kontext

Prompt Engineering med OpenAI API

Fouad Trad

Machine Learning Engineer

Behovet av extern kontext

  • Förtränade språkmodeller känner igen information de tränats på
  • Behöver mer kontext
  • Bättre precision och träffsäkerhet

Ikon som föreställer en chatbot på en mobiltelefon.

Prompt Engineering med OpenAI API

Brist på information i LLM:er

  • Kunskapsavstängning
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.
Prompt Engineering med OpenAI API

Brist på information i LLM:er

  • Begärde icke-offentlig information
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.
Prompt Engineering med OpenAI API

Hur ger man extra information?

  • Exempelkonversationer
  • Systemprompt

Ikon med två meddelanderutor som illustrerar ett samtal.

Prompt Engineering med OpenAI API

Exempelkonversationer

  • Styr modellen att svara på specifika frågor
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.
  • Nackdel: kan kräva många exempel
Prompt Engineering med OpenAI API

Systemprompt

  • Inkluderar nödvändig kontext för chatbotens svar
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.
Prompt Engineering med OpenAI API

Avslutande notering

  • De tidigare metoderna fungerar bra för liten kontext
  • Större kontext kräver mer avancerade tekniker

Ikon som föreställer en varning.

Prompt Engineering med OpenAI API

Nu kör vi en övning!

Prompt Engineering med OpenAI API

Preparing Video For Download...