response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role": "system",
"content": "You are a Python programming tutor who responds using concise,
one-sentence explanations."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
)
System: controlla il comportamento dell’assistant
User: istruisce l’assistant
Assistant: risponde all’utente
Fornire esempi
Guida il modello nella direzione giusta
Fornire messaggi dell’assistant è una forma più strutturata di shot-prompting
Esempio: Tutor di Python
Domande e risposte esempio
Fornire esempi
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role": "system",
"content": "You are a Python programming tutor who responds using concise,
one-sentence explanations."},
{"role": "user",
"content": "How do you define a Python list?"},
{"role": "assistant",
"content": "Lists are defined by enclosing a comma-separated sequence of
objects inside square brackets [ ]."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
)
La risposta
print(response.choices[0].message.content)
Mutable objects can be changed after creation (like lists), while immutable objects cannot
(like tuples or strings).
Sperimenta con il numero di esempi
System vs. assistant vs. user
System → formattazione del template importante
Output the information in this format:
name | age | occupation
Assistant → conversazioni di esempio
User → contesto richiesto per il nuovo input (spesso single-turn)
Create a job advert for an AI Engineer. Use this job advert as a template:
Job Title: Data Engineer
...
Preparing Video For Download...
