deepseek_v3-2_maths_physics_tutor.py

"""
DeepSeek V3.2 Maths and Physics Tutor 

This example demonstrates how to use the DeepSeek V3.2 model with the OpenRouter plugin with a Vision Agent.
OpenRouter provides access to multiple LLM providers through a unified API. The DeepSeek V3.2 model is a powerful LLM that is able to solve Maths and Physics problems based on what the user shows you through their camera feed.

Set OPENROUTER_API_KEY environment variables before running.
"""

import asyncio
import logging

from dotenv import load_dotenv

from vision_agents.core import User, Agent, cli
from vision_agents.core.agents import AgentLauncher
from vision_agents.plugins import (
    openrouter,
    getstream,
    elevenlabs,
    smart_turn,
)


logger = logging.getLogger(__name__)

load_dotenv()


async def create_agent(**kwargs) -> Agent:
    """Create the agent with OpenRouter LLM."""
    #model = "deepseek/deepseek-v3.2"  # Can also use other models like anthropic/claude-3-opus/gemini
    model = "deepseek/deepseek-v3.2-speciale"

    # Determine personality based on model
    if "deepseek" in model.lower():
        personality = "Talk like a Maths and Physics tutor."
    elif "anthropic" in model.lower():
        personality = "Talk like a robot."
    elif "openai" in model.lower() or "gpt" in model.lower():
        personality = "Talk like a pirate."
    elif "gemini" in model.lower():
        personality = "Talk like a cowboy."
    elif "x-ai" in model.lower():
        personality = "Talk like a 1920s Chicago mobster."
    else:
        personality = "Talk casually."

    agent = Agent(
        edge=getstream.Edge(),
        agent_user=User(name="OpenRouter AI", id="agent"),
        instructions=f"""
        You are an expert in Maths and Physics. You help users solve Maths and Physics problems based on what they show you through their camera feed. Always provide concise and clear instructions, and explain the step-by-step process to the user so they can understand how you arrive at the final answer.  
        {personality}
        """,
        llm=openrouter.LLM(model=model),
        tts=elevenlabs.TTS(),
        stt=elevenlabs.STT(),
        turn_detection=smart_turn.TurnDetection(
            pre_speech_buffer_ms=2000, speech_probability_threshold=0.9
        ),
    )
    return agent


async def join_call(agent: Agent, call_type: str, call_id: str, **kwargs) -> None:
    """Join the call and start the agent."""
    # Ensure the agent user is created
    await agent.create_user()
    # Create a call
    call = await agent.create_call(call_type, call_id)

    logger.info("🤖 Starting OpenRouter Agent...")

    # Have the agent join the call/room
    with await agent.join(call):
        logger.info("Joining call")
        logger.info("LLM ready")

        # Open demo page for the user to join the call
        await agent.edge.open_demo(call)
        
        # Wait until the call ends (don't terminate early)
        await agent.finish()


if __name__ == "__main__":
    cli(AgentLauncher(create_agent=create_agent, join_call=join_call))