Sarvam AI

Configure Sarvam AI as an LLM provider in Mem0, specializing in Indian language support with the Sarvam-M model.

Sarvam AI is an Indian AI company developing language models with a focus on Indian languages and cultural context. Their latest model Sarvam-M is designed to understand and generate content in multiple Indian languages while maintaining high performance in English.

To use Sarvam AI’s models, please set the SARVAM_API_KEY which you can get from their platform.

Usage

Python

import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
os.environ["SARVAM_API_KEY"] = "your-api-key"

config = {
    "llm": {
        "provider": "sarvam",
        "config": {
            "model": "sarvam-m",
            "temperature": 0.7,
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="alex")

import { Memory } from 'mem0ai/oss';

const config = {
  llm: {
    provider: 'sarvam',
    config: {
      apiKey: process.env.SARVAM_API_KEY || '',
      model: 'sarvam-m',
      temperature: 0.7,
    },
  },
};

const memory = new Memory(config);
const messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
];
await memory.add(messages, { userId: 'alex' });

Advanced Usage with Sarvam-Specific Features

import os
from mem0 import Memory

config = {
    "llm": {
        "provider": "sarvam",
        "config": {
            "model": {
                "name": "sarvam-m",
                "reasoning_effort": "high",  # Enable advanced reasoning
                "frequency_penalty": 0.1,    # Reduce repetition
                "seed": 42                   # For deterministic outputs
            },
            "temperature": 0.3,
            "max_tokens": 2000,
            "api_key": "your-sarvam-api-key"
        }
    }
}

m = Memory.from_config(config)

# Example with Hindi conversation
messages = [
    {"role": "user", "content": "मैं SBI में joint account खोलना चाहता हूँ।"},
    {"role": "assistant", "content": "SBI में joint account खोलने के लिए आपको कुछ documents की जरूरत होगी। क्या आप जानना चाहते हैं कि कौन से documents चाहिए?"}
]
m.add(messages, user_id="rajesh", metadata={"language": "hindi", "topic": "banking"})

Config

All available parameters for the sarvam config are present in Master List of All Params in Config.