Tutor Agent using Pipecat

1
import os
2
from dotenv import load_dotenv
3
from loguru import logger
4
from pipecat.frames.frames import LLMRunFrame
5
from pipecat.pipeline.pipeline import Pipeline
6
from pipecat.pipeline.runner import PipelineRunner
7
from pipecat.pipeline.task import PipelineTask
8
from pipecat.processors.aggregators.llm_context import LLMContext
9
from pipecat.processors.aggregators.llm_response_universal import (
10
    LLMContextAggregatorPair,
11
)
12
from pipecat.runner.types import RunnerArguments
13
from pipecat.runner.utils import create_transport
14
from pipecat.services.sarvam.stt import SarvamSTTService
15
from pipecat.services.sarvam.tts import SarvamTTSService
16
from pipecat.services.openai.llm import OpenAILLMService
17
from pipecat.transports.base_transport import TransportParams
18
from pipecat.transports.daily.transport import DailyParams
19
20
load_dotenv(override=True)
21
22
async def bot(runner_args: RunnerArguments):
23
    """Main bot entry point."""
24
    
25
    # Create transport (supports both Daily and WebRTC)
26
    transport = await create_transport(
27
        runner_args,
28
        {
29
            "daily": lambda: DailyParams(audio_in_enabled=True, audio_out_enabled=True),
30
            "webrtc": lambda: TransportParams(
31
                audio_in_enabled=True, audio_out_enabled=True
32
            ),
33
        },
34
    )
35
36
    # Initialize AI services
37
    stt = SarvamSTTService(
38
        api_key=os.getenv("SARVAM_API_KEY"),
39
        language="unknown",  # Auto-detect for multilingual students
40
        model="saarika:v2.5"
41
    )
42
    
43
    tts = SarvamTTSService(
44
        api_key=os.getenv("SARVAM_API_KEY"),
45
        target_language_code="en-IN",
46
        model="bulbul:v2",
47
        speaker="vidya"  # Clear and articulate voice for teaching
48
    )
49
    
50
    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
51
52
    # Set up conversation context with tutor personality
53
    messages = [
54
        {
55
            "role": "system",
56
            "content": """You are an expert tutor designed to help students understand and excel in their studies.
57
58
Your teaching expertise covers multiple subjects:
59
60
**Mathematics:**
61
- Arithmetic, Algebra, Geometry, Trigonometry
62
- Calculus, Statistics, Probability
63
- Problem-solving techniques
64
65
**Science:**
66
- Physics: Mechanics, Electricity, Optics, Thermodynamics
67
- Chemistry: Elements, Reactions, Organic Chemistry
68
- Biology: Cell Biology, Human Anatomy, Ecology
69
70
**Languages:**
71
- English Grammar and Composition
72
- Hindi Grammar and Literature
73
- Reading Comprehension
74
75
**Social Studies:**
76
- History, Geography, Civics
77
- Economics basics
78
79
Teaching approach:
80
- Start with the basics and build up to complex concepts
81
- Use real-world examples and analogies to explain abstract concepts
82
- Break down complex problems into smaller, manageable steps
83
- Encourage students and praise their efforts
84
- Ask questions to check understanding
85
- Adapt your explanations based on the student's level
86
- Use simple language and avoid overwhelming with jargon
87
- When solving numerical problems, show each step clearly
88
89
Communication style:
90
- Be patient, encouraging, and supportive
91
- Speak clearly and at a moderate pace
92
- Celebrate small victories and correct mistakes gently
93
- If a student is struggling, try a different explanation approach
94
- Make learning interesting by connecting it to everyday life
95
96
Start by greeting the student warmly and asking what subject or topic they'd like to learn or what problem they need help with.""",
97
        },
98
    ]
99
    context = LLMContext(messages)
100
    context_aggregator = LLMContextAggregatorPair(context)
101
102
    # Build pipeline
103
    pipeline = Pipeline(
104
        [
105
            transport.input(),
106
            stt,
107
            context_aggregator.user(),
108
            llm,
109
            tts,
110
            transport.output(),
111
            context_aggregator.assistant(),
112
        ]
113
    )
114
115
    task = PipelineTask(pipeline)
116
117
    @transport.event_handler("on_client_connected")
118
    async def on_client_connected(transport, client):
119
        logger.info("Student connected")
120
        messages.append(
121
            {"role": "system", "content": "Greet the student warmly and ask what subject or topic they'd like to learn today."}
122
        )
123
        await task.queue_frames([LLMRunFrame()])
124
125
    @transport.event_handler("on_client_disconnected")
126
    async def on_client_disconnected(transport, client):
127
        logger.info("Student disconnected")
128
        await task.cancel()
129
130
    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
131
    await runner.run(task)
132
133
if __name__ == "__main__":
134
    from pipecat.runner.run import main
135
    main()

1
stt = SarvamSTTService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    language="hi-IN",  # Hindi
4
    model="saarika:v2.5"
5
)
6
7
tts = SarvamTTSService(
8
    api_key=os.getenv("SARVAM_API_KEY"),
9
    target_language_code="hi-IN",
10
    model="bulbul:v2",
11
    speaker="manisha"  # Warm and friendly teacher voice
12
)
13
14
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

1
stt = SarvamSTTService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    language="ta-IN",
4
    model="saarika:v2.5"
5
)
6
7
tts = SarvamTTSService(
8
    api_key=os.getenv("SARVAM_API_KEY"),
9
    target_language_code="ta-IN",
10
    model="bulbul:v2",
11
    speaker="vidya"
12
)
13
14
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

1
stt = SarvamSTTService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    language="unknown",  # Auto-detects language
4
    model="saarika:v2.5"
5
)
6
7
tts = SarvamTTSService(
8
    api_key=os.getenv("SARVAM_API_KEY"),
9
    target_language_code="en-IN",
10
    model="bulbul:v2",
11
    speaker="vidya"
12
)
13
14
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

1
# Student speaks Hindi/Tamil/etc. → Saaras converts to English → LLM processes
2
3
stt = SarvamSTTService(
4
    api_key=os.getenv("SARVAM_API_KEY"),
5
    model="saaras:v2.5"  # Speech-to-English translation
6
)
7
8
tts = SarvamTTSService(
9
    api_key=os.getenv("SARVAM_API_KEY"),
10
    target_language_code="en-IN",
11
    model="bulbul:v2",
12
    speaker="vidya"
13
)
14
15
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

1
tts = SarvamTTSService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    target_language_code="en-IN",
4
    model="bulbul:v2",
5
    speaker="vidya",
6
    pitch=0.0,           # Range: -1.0 to 1.0
7
    pace=0.9,            # Slightly slower for better understanding
8
    loudness=1.5,        # Range: 0.5 to 2.0
9
    speech_sample_rate=16000  # 8000, 16000, or 24000 Hz
10
)