Multi-Agent Systems with SUTRA
This notebook demonstrates how to use SUTRA with CrewAI, a framework for orchestrating role-playing, autonomous AI agents. SUTRA-V2, developed by TWO AI, powers multilingual chat and instruction tasks, integrating seamlessly with CrewAI’s collaborative agent workflows.
🔧 Prerequisites
- Obtain your SUTRA API key from https://developer.two.ai.
- Store the API key securely (e.g., in Google Colab secrets or environment variables).
- Install CrewAI and OpenAI SDK.
📦 Step 1: Install Dependencies
# SUTRA models are OpenAI API compatible
!pip install -qU crewai openai🔐 Step 2: Initialize SUTRA-V2 with CrewAI
from crewai import Agent, Task, Crew
from crewai import LLM
import os
client = LLM(
model="openai/sutra-v2",
api_key=os.getenv("SUTRA_API_KEY"),
api_base="https://api.two.ai/v2",
)
# Define a CrewAI agent with SUTRA-V2
agent = Agent(
role="Multilingual Assistant",
goal="Provide concise answers in multiple languages",
backstory="You are an expert AI assistant trained to communicate fluently in over 50 languages.",
llm=client,
model="sutra-v2",
verbose=True
)
# Define a task
task = Task(
description="Explain AI in three sentences in German.",
agent=agent,
expected_output="A concise explanation of AI in German."
)
# Create a crew
crew = Crew(
agents=[agent],
tasks=[task],
verbose=True
)💬 Step 3: Run the agent
# Run the agent
response = agent.kickoff("How Many Languages SUTRA Speak in Hindi.")
print(response)🌟 Why CrewAI?
- Collaboration: Enables multi-agent workflows with role-based tasks.
- Flexibility: Integrates with OpenAI-compatible APIs like SUTRA-V2.
- Performance: Optimized for speed and enterprise-grade automation.
🛠 Troubleshooting
- Invalid API Key: Verify your key at https://developer.two.ai.
- Model Not Found: Use
sutra-v2. SUTRA-V1 was deprecated on March 22, 2025. - CrewAI Errors: Ensure Python < 3.13 for compatibility with CrewAI tools.