How to encourage new topics with presence_penalty

The presence_penalty parameter helps you steer the model toward introducing new concepts or topics, instead of sticking to the same words.

• Positive values → penalize tokens that have already appeared → model becomes more likely to explore new ideas.
• Negative values → encourage staying on the same topic (rarely used).

How it works:

• As the model generates text, it tracks which tokens have already been used.
• Higher presence_penalty nudges the model to shift away from familiar tokens, helping it bring in new topics or angles.

Parameter details:

When to use presence_penalty:

First, install the SDK:

$
pip install -Uqq sarvamai

Then use the following Python code:

1
from sarvamai import SarvamAI
2
3
# Initialize the SarvamAI client with your API key
4
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5
6
# Example: Encourage model to introduce new ideas
7
response = client.chat.completions(
8
    model="sarvam-105b",
9
    messages=[
10
        {"role": "system", "content": "You are a creative brainstorming assistant."},
11
        {"role": "user", "content": "Suggest some ideas for eco-friendly products."}
12
    ],
13
    presence_penalty=1.0  # Encourage exploration of new ideas
14
)
15
16
# Receive assistant's reply as output
17
print(response.choices[0].message.content)