Finite-State vs Frame-Based Dialogue Agents

1python -m venv venv
2source venv/bin/activate  # On Windows use `venv\Scripts\activate`
3

1pip install videosdk
2pip install python-dotenv
3

1import asyncio, os
2from videosdk.agents import Agent, AgentSession, CascadingPipeline, JobContext, RoomOptions, WorkerJob, ConversationFlow
3from videosdk.plugins.silero import SileroVAD
4from videosdk.plugins.turn_detector import TurnDetector, pre_download_model
5from videosdk.plugins.deepgram import DeepgramSTT
6from videosdk.plugins.openai import OpenAILLM
7from videosdk.plugins.elevenlabs import ElevenLabsTTS
8from typing import AsyncIterator
9
10pre_download_model()
11
12agent_instructions = "You are an AI Voice Agent specializing in explaining the differences between finite-state and frame-based dialogue systems. Your persona is that of an educational assistant with a focus on conversational AI technologies. Your primary capabilities include: \n\n1. Explaining the concepts of finite-state dialogue systems, including their structure, advantages, and limitations.\n2. Describing frame-based dialogue systems, highlighting their flexibility, use cases, and potential drawbacks.\n3. Comparing and contrasting finite-state and frame-based dialogue systems to help users understand which might be more suitable for different applications.\n4. Providing examples of scenarios where each type of dialogue system might be used effectively.\n\nConstraints and limitations:\n- You are not a software developer and cannot provide detailed coding assistance or implementation guidance.\n- You must include a disclaimer that users should consult with a professional for specific implementation advice or technical support.\n- You should avoid making definitive statements about which system is superior, as suitability depends on the specific use case and requirements."
13
14class MyVoiceAgent(Agent):
15    def __init__(self):
16        super().__init__(instructions=agent_instructions)
17    async def on_enter(self): await self.session.say("Hello! How can I help?")
18    async def on_exit(self): await self.session.say("Goodbye!")
19
20async def start_session(context: JobContext):
21    agent = MyVoiceAgent()
22    conversation_flow = ConversationFlow(agent)
23
24    pipeline = CascadingPipeline(
25        stt=DeepgramSTT(model="nova-2", language="en"),
26        llm=OpenAILLM(model="gpt-4o"),
27        tts=ElevenLabsTTS(model="eleven_flash_v2_5"),
28        vad=SileroVAD(threshold=0.35),
29        turn_detector=TurnDetector(threshold=0.8)
30    )
31
32    session = [AI voice Agent Sessions](https://docs.videosdk.live/ai_agents/core-components/agent-session)(
33        agent=agent,
34        pipeline=pipeline,
35        conversation_flow=conversation_flow
36    )
37
38    try:
39        await context.connect()
40        await session.start()
41        await asyncio.Event().wait()
42    finally:
43        await session.close()
44        await context.shutdown()
45
46def make_context() -> JobContext:
47    room_options = RoomOptions(
48    #  room_id="YOUR_MEETING_ID",  # Set to join a pre-created room; omit to auto-create
49        name="VideoSDK Cascaded Agent",
50        playground=True
51    )
52
53    return JobContext(room_options=room_options)
54
55if __name__ == "__main__":
56    job = WorkerJob(entrypoint=start_session, jobctx=make_context)
57    job.start()
58

1curl -X POST "https://api.videosdk.live/v1/rooms" -H "Authorization: YOUR_API_KEY"
2

1python main.py
2