Riepilogo e modifica del testo

Lavorare con DeepSeek in Python

James Chapman

AI Curriculum Lead, DataCamp

Ricapitoliamo...

Q&A

response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4.1-Flash",
  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...

Modifica del testo

Esempio: aggiornare nome, pronomi e qualifica

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.
"""

Modifica del testo

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4.1-Flash",

    messages=[{"role": "user", "content": prompt}]

)

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

Here's the updated text with the requested changes:

Maarten is a Senior Content Developer at DataCamp. His favorite programming language
is R, which he uses for his statistical analyses.

Let me know if you'd like any further adjustments!

Sintesi del testo

Esempio: sintesi di trascrizioni di chat con clienti

Team di assistenza clienti

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?  
...
"""

Sintesi del testo

prompt = f"""Summarize the customer support chat 
             in three concise key points: {text}"""


response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4.1-Flash",
  messages=[{"role": "user", "content": prompt}]
)
print(response.choices[0].message.content)

1. **Problema di accesso**: il cliente non riusciva a entrare per un errore di password e mancato link di reset.  
2. **Suggerimento reset password**: il supporto ha reinviato l'email di reset dopo la verifica.  
3. **Assistenza rapida**: il cliente ha risolto usando l'accesso con Google.

Controllare la lunghezza della risposta

max_tokens = 5

response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4.1-Flash",
  messages=[{"role":"user",
      "content":"Write a haiku about AI."}],
  max_tokens=5
)

**Silent circuits hum

max_tokens = 30

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4.1-Flash",
    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.**

Capire i token

Token: unità di testo che aiutano l'AI a comprendere e interpretare il testo

La frase «How can the OpenAI API deliver business value?» con ogni token evidenziato in un colore diverso.

¹ https://lunary.ai/deepseek-tokenizer

Calcolare il costo

I costi API dipendono da piattaforma, modello e numero di token 💰
- I modelli sono prezziati per costo/token
- I token di input e output possono avere costi diversi
Aumentare max_tokens aumenta il costo 📈

Screenshot 2025-03-05 at 11.46.54.png

Calcolare 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-V4.1-Flash",
    messages=[{"role": "user", "content": prompt}], 
    max_tokens=max_tokens
)

Calcolare il costo

# Define price per token
input_token_price = 2.1 / 1_000_000
output_token_price = 4.4 / 1_000_000

# Extract token usage
input_tokens = response.usage.prompt_tokens

output_tokens = max_tokens

# Calculate cost
cost = (input_tokens * input_token_price + output_tokens * output_token_price)
print(f"Estimated cost: ${cost}")

Estimated cost: $0.0153964

Esercitiamoci!

Lavorare con DeepSeek in Python