How to list your chat messages

The messages parameter defines your entire conversation so far — this is how you “teach” the model what has happened in the chat.

Each message is an object with two fields:

Key	Value
`role`	`"system"`, `"user"`, or `"assistant"`
`content`	The message text (string)

Why is this important?

The model uses the conversation history to generate context-aware replies.
The order of the messages matters — the model reads them top to bottom.
Including previous assistant responses helps the model maintain coherence and memory.

Roles explained:

system (Optional, but Recommended)
Sets initial behavior, tone, or instructions for the assistant.
Example: "You are a helpful assistant."
user (Required)
Represents questions, requests, or inputs from the user.
Example: "Tell me about Indian classical music."
assistant (Optional, only for context in multi-turn)
Contains previous replies from the model, which help it stay consistent in tone and content.
Example: "Indian classical music is one of the oldest musical traditions..."

Example: Listing messages in a conversation

1 # Install SarvamAI
2 !pip install -Uqq sarvamai
3 from sarvamai import SarvamAI

1 # Initialize the SarvamAI client with your API key
2 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

1 # Example1: Default example - single "user" message which is required (no prior context)
2 response = client.chat.completions(
3     messages=[
4     {"role": "user", "content": "Hey, what is the capital of India?"}
5     ]
6 )

1 # Example2: Multi-turn example — maintaining conversation context
2 response = client.chat.completions(
3     messages=[
4         {"role": "system", "content": "You are a helpful assistant."},
5         {"role": "user", "content": "Tell me about Indian classical music."},
6         {"role": "assistant", "content": "Indian classical music is one of the oldest musical traditions in the world, with roots in ancient texts like the Natya Shastra."},
7         {"role": "user", "content": "What are the two main styles?"}
8     ]
9 )

1 # Receive assistant's reply as output.
2 print(response.choices[0].message.content)