Résumé et édition de texte

Travailler avec l'API OpenAI

James Chapman

Curriculum Manager, DataCamp

Résumé…

Q&A

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "user", "content": "How many days are in October?"}]
)

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

October has 31 days.

Édition de texte

Exemple : mise à jour du nom, des pronoms et du titre du poste

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.
"""

Édition de texte

response = client.chat.completions.create(
    model="gpt-4o-mini",

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

)

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

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

Résumé de texte

Exemple : résumé des transcriptions des conversations avec les clients

Customer support team

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?  
...
"""

Résumé de texte

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


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

1. Customer couldn't log in due to a password issue and missing reset link.  
2. Support resent the reset email after confirming it was sent.  
3. Customer resolved the issue by using Google sign-in.

Contrôle de la longueur des réponses

max_completion_tokens = 5

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "user", 
  "content": "Write a haiku about AI."}],
  max_completion_tokens=5
)

AI so powerful
Computers

max_completion_tokens = 30

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "user", 
  "content": "Write a haiku about AI."}],
  max_completion_tokens=30
)

A machine mind thinks
Logic dictates its choices
Mankind ponders anew

Découverte des jetons

Jetons : unités de texte qui assistent l'IA dans la compréhension et l'interprétation du texte

The sentence, "How can the OpenAI API deliver business value?" with each token highlighted in a different color.

¹ https://platform.openai.com/tokenizer

Calcul de coût

Les coûts d'utilisation dépendent du modèle et du nombre de jetons 💰
- Les modèles sont facturés en fonction du coût/jetons
- Les jetons d'entrée et de sortie peuvent avoir des coûts différents
Une augmentation de max_completion_tokens entraîne une augmentation des coûts 📈

Screenshot 2025-03-05 at 11.46.54.png

Calcul de coût

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

max_completion_tokens = 500

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "user", "content": prompt}], 
  max_completion_tokens=max_completion_tokens
  )

Calcul de coût

# Define price per token
input_token_price = 0.15 / 1_000_000
output_token_price = 0.6 / 1_000_000

# Extract token usage
input_tokens = response.usage.prompt_tokens

output_tokens = max_completion_tokens

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

Estimated cost: $0.00124

¹ https://openai.com/pricing

Passons à la pratique !

Travailler avec l'API OpenAI