Rekayasa prompt untuk pengembangan chatbot

Prompt Engineering dengan OpenAI API

Fouad Trad

Machine Learning Engineer

Kebutuhan rekayasa prompt untuk chatbot

Sulit menebak pertanyaan pengguna
Tantangan memastikan jawaban efektif
Rekayasa prompt mengarahkan perilaku chatbot

Gambar menampilkan chatbot di ponsel.

Rekayasa prompt chatbot dengan OpenAI API

Gambar yang menunjukkan tiga peran sebuah pesan dan komunikasi di antaranya.

Tiap pesan punya peran tertentu

Rekayasa prompt chatbot dengan OpenAI API

Gambar yang menunjukkan tiga peran pesan dan komunikasi di antaranya, menyorot interaksi pengguna–asisten.

Tiap pesan punya peran tertentu
Fokus sebelumnya pada prompt pengguna

Rekayasa prompt chatbot dengan OpenAI API

Gambar yang menunjukkan tiga peran pesan dan komunikasi di antaranya, menyorot interaksi sistem–asisten.

Tiap pesan punya peran tertentu
Fokus sebelumnya pada prompt pengguna
Prompt sistem mengarahkan perilaku chatbot

Endpoint chat completions untuk pengembangan chatbot

Mengirim rangkaian pesan ke model sebagai list

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "system",
             "content": "You are an expert data scientist that explains complex concepts in simple terms"},

            {"role": "user",
             "content": "What is prompt engineering?"}]
)

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

Imagine you're giving instructions to a computer program, like teaching a robot to make a sandwich. 
Prompt engineering is all about crafting those instructions, or "prompts," in a way that helps the 
computer understand and perform the task better.

Mengubah get_response() untuk chatbot

Mengirim satu prompt

def get_response(prompt):
    messages = [
      {"role": "user", "content": prompt}
    ]
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages,
        temperature=0,
    )
    return response.choices[0].message.content


prompt = "<PROMPT>"
print(get_response(prompt))

Mengirim dua prompt

def get_response(system_prompt, user_prompt):

    messages = [
      {"role": "system", "content": system_prompt},
      {"role": "user", "content": user_prompt}]

    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages,
        temperature=0,
    )
    return response.choices[0].message.content


system_prompt = "<SYSTEM_PROMPT>"
user_prompt = "<USER_PROMPT>"
print(get_response(system_prompt, user_prompt))

Pesan sistem: tetapkan tujuan

system_prompt = "You are a chatbot that answers financial questions."


user_prompt = "Who are you?"

print(get_response(system_prompt, user_prompt))

I'm a financial chatbot that answers financial questions. How can I help you?

Memungkinkan chatbot memberi bantuan akurat sesuai domain
Tanpa tujuan yang jelas, jawaban bisa tidak relevan konteks

Pesan sistem: panduan respons

Tentukan audiens, nada, panjang, struktur

system_prompt = """You are a chatbot that answers financial questions. 
Your answers should be precise, formal and objective"""


user_prompt = "What do you think about cryptocurrencies?"

print(get_response(system_prompt, user_prompt))

Pesan sistem: panduan respons

Cryptocurrencies are digital or virtual currencies that use cryptography for security and operate on 
decentralized networks based on blockchain technology. 
[...]


Advantages of cryptocurrencies include:
- Decentralization: [...]
- Security:[...]
- Global Accessibility: [...]


However, there are also notable concerns:
- Volatility: [...]
- Regulatory Uncertainty: [...]
- Lack of Consumer Protection: [...]


In summary, cryptocurrencies have the potential to offer various benefits, but their adoption and impact 
on the financial landscape are still evolving [...]

Pesan sistem: pandu perilaku

Prompt kondisional untuk menjawab pertanyaan

system_prompt = """You are a chatbot that answers financial questions. 
Your answers should be precise, formal and objective.


"""

Pesan sistem: pandu perilaku

Prompt kondisional untuk menjawab pertanyaan

system_prompt = """You are a chatbot that answers financial questions. 
Your answers should be precise, formal and objective.
If the question you receive is within the financial field, answer it to the best of your knowledge.

"""

Pesan sistem: pandu perilaku

Prompt kondisional untuk menjawab pertanyaan

system_prompt = """You are a chatbot that answers financial questions. 
Your answers should be precise, formal and objective.
If the question you receive is within the financial field, answer it to the best of your knowledge.
Otherwise, answer with 'Sorry, I only know about finance.'
"""

user_prompt = "How's the weather today?"

print(get_response(system_prompt, user_prompt))

Sorry, I only know about finance.

Ayo berlatih!

Prompt Engineering dengan OpenAI API