Lavorare con DeepSeek in Python
James Chapman
Curriculum Manager, DataCamp
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role": "user", "content": "How many days are in October?"}]
)
print(response.choices[0].message.content)
October has **31 days**.
It's one of the seven months in the Gregorian calendar with 31 days...
$$
prompt = """
Update name to Maarten, pronouns to he/him, and job title to Senior Content Developer
in the following text:
Joanne is a Content Developer at DataCamp. Her favorite programming language is R,
which she uses for her statistical analyses.
"""
response = client.chat.completions.create( model="deepseek-ai/DeepSeek-V3",messages=[{"role": "user", "content": prompt}]) print(response.choices[0].message.content)
Ecco il testo aggiornato con le modifiche richieste:
Maarten è Senior Content Developer in DataCamp. Il suo linguaggio di programmazione preferito
è R, che usa per le sue analisi statistiche.
Fammi sapere se vuoi altre modifiche!

text = """
Customer: Hi, I'm trying to log into
my account, but it keeps saying
my password is incorrect. I'm sure
I'm entering the right one.
Support: I'm sorry to hear that!
Have you tried resetting your password?
...
"""
prompt = f"""Summarize the customer support chat in three concise key points: {text}"""response = client.chat.completions.create( model="deepseek-ai/DeepSeek-V3", messages=[{"role": "user", "content": prompt}] ) print(response.choices[0].message.content)
1. **Problema di accesso**: l'utente non riesce a entrare per password errata e link di reset mancante.
2. **Suggerimento reset**: il supporto reinvia l'email di reset dopo averne verificato l'invio.
3. **Assistenza rapida**: l'utente risolve accedendo con Google.
max_tokens = 5response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role":"user",
"content":"Write a haiku about AI."}],
max_tokens=5
)
**Silent circuits hum
max_tokens = 30response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role":"user",
"content":"Write a haiku about AI."}],
max_tokens=30
)
**Silent circuits hum,**
**thoughts of light and logic bloom—**
**minds beyond our own.**
$$
$$

I costi API dipendono da piattaforma, modello e numero di token 💰
Aumentare max_tokens aumenta il costo 📈

prompt = f"""Summarize the customer support chat
in three concise key points: {text}"""
max_tokens = 500
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role": "user", "content": prompt}],
max_tokens=max_tokens
)
# Define price per token input_token_price = 1.25 / 1_000_000 output_token_price = 1.25 / 1_000_000# Extract token usage input_tokens = response.usage.prompt_tokensoutput_tokens = max_tokens# Calculate cost cost = (input_tokens * input_token_price + output_tokens * output_token_price) print(f"Estimated cost: ${cost}")
Estimated cost: $0.00848
Lavorare con DeepSeek in Python