Few-shot prompting

Prompt Engineering dengan OpenAI API

Fouad Trad

Machine Learning Engineer

Few-shot prompting

Model diberi contoh (pasangan tanya–jawab)

Representasi visual few-shot prompt yang menunjukkan strukturnya dengan contoh pertanyaan dan jawaban, lalu pertanyaan yang ingin kita jawabkan model.

Few-shot prompting

Model diberi contoh (pasangan tanya–jawab)

Diagram visual yang menunjukkan cara kita mengirim few-shot prompt ke LLM.

Few-shot prompting

Model diberi contoh (pasangan tanya–jawab)

Diagram visual yang menunjukkan cara kita mengirim few-shot prompt ke LLM dan mendapat jawaban.

Few-shot prompting

Model diberi contoh (pasangan tanya–jawab)

Diagram visual yang menunjukkan cara kita mengirim few-shot prompt ke LLM dan mendapat jawaban.

Jumlah contoh:
- Nol -> zero-shot prompting
- Satu -> one-shot prompting
- Lebih dari satu -> few-shot prompting

Zero-shot prompting

Memberi prompt tanpa contoh
Model menjawab berdasarkan pengetahuannya
Cocok untuk tugas cepat dan sederhana

prompt = "What is prompt engineering?"
print(get_response(prompt))

Prompt engineering refers to designing and refining prompts or instructions given 
to a language model like ChatGPT to elicit desired responses or behaviors. It 
involves formulating specific guidelines or hints to guide the model's output 
towards a desired outcome.

One-shot prompting

Beri model satu contoh
Berguna untuk format atau gaya yang konsisten

prompt =  """ 
Q: Sum the numbers 3, 5, and 6. A: 3+5+6=14
Q: Sum the numbers 2, 4, and 7. A: 
"""
print(get_response(prompt))

2+4+7=13

One-shot prompting

prompt = """
Q: Sum the numbers 3, 5, and 6. A: The sum of 3, 5, and 6 is 14
Q: Sum the numbers 2, 4, and 7. A: 
"""
print(get_response(prompt))

The sum of 2, 4, and 7 is 13

Few-shot prompting

Beri lebih dari satu contoh
Kuat untuk tugas kontekstual

prompt = """
Text: Today the weather is fantastic -> Classification: positive
Text: The furniture is small -> Classification: neutral
Text: I don't like your attitude -> Classification: negative

"""

Few-shot prompting

Beri lebih dari satu contoh
Kuat untuk tugas kontekstual

prompt = """
Text: Today the weather is fantastic -> Classification: positive
Text: The furniture is small -> Classification: neutral
Text: I don't like your attitude -> Classification: negative
Text: That shot selection was awful -> Classification: 
"""
print(get_response(prompt))

negative

Few-shot prompting dengan model chat

response = client.chat.completions.create(
  model = "gpt-3.5-turbo",

  messages = [{"role": "user",
             "content": "Today the weather is fantastic"},

             {"role": "assistant",
             "content": "positive"},

              {"role": "user",
             "content": "I don't like your attitude"},
              {"role": "assistant",
             "content": "negative"},

              {"role": "user",
             "content": "That shot selection was awful"}
             ],
  temperature = 0
)

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

negative

Pertimbangan

Pilih jumlah shot sesuai kompleksitas tugas
- Sedikit shot -> tugas dasar
- Beragam shot -> tugas kompleks

Gambar orang yang sedang mempertanyakan dirinya.

Ayo berlatih!

Prompt Engineering dengan OpenAI API