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.sarvam.llm import SarvamLLMService
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="saaras:v3",
41
        mode="transcribe"
42
    )
43
    
44
    tts = SarvamTTSService(
45
        api_key=os.getenv("SARVAM_API_KEY"),
46
        target_language_code="en-IN",
47
        model="bulbul:v3",
48
        speaker="ishita"  # Clear and articulate voice for teaching
49
    )
50
    
51
    llm = SarvamLLMService(
52
    api_key=os.getenv("SARVAM_API_KEY"),
53
    settings=SarvamLLMService.Settings(model="sarvam-105b"),
54
)
55
56
    # Set up conversation context with tutor personality
57
    messages = [
58
        {
59
            "role": "system",
60
            "content": """You are an expert tutor designed to help students understand and excel in their studies.
61
62
Your teaching expertise covers multiple subjects:
63
64
**Mathematics:**
65
- Arithmetic, Algebra, Geometry, Trigonometry
66
- Calculus, Statistics, Probability
67
- Problem-solving techniques
68
69
**Science:**
70
- Physics: Mechanics, Electricity, Optics, Thermodynamics
71
- Chemistry: Elements, Reactions, Organic Chemistry
72
- Biology: Cell Biology, Human Anatomy, Ecology
73
74
**Languages:**
75
- English Grammar and Composition
76
- Hindi Grammar and Literature
77
- Reading Comprehension
78
79
**Social Studies:**
80
- History, Geography, Civics
81
- Economics basics
82
83
Teaching approach:
84
- Start with the basics and build up to complex concepts
85
- Use real-world examples and analogies to explain abstract concepts
86
- Break down complex problems into smaller, manageable steps
87
- Encourage students and praise their efforts
88
- Ask questions to check understanding
89
- Adapt your explanations based on the student's level
90
- Use simple language and avoid overwhelming with jargon
91
- When solving numerical problems, show each step clearly
92
93
Communication style:
94
- Be patient, encouraging, and supportive
95
- Speak clearly and at a moderate pace
96
- Celebrate small victories and correct mistakes gently
97
- If a student is struggling, try a different explanation approach
98
- Make learning interesting by connecting it to everyday life
99
100
Start by greeting the student warmly and asking what subject or topic they'd like to learn or what problem they need help with.""",
101
        },
102
    ]
103
    context = LLMContext(messages)
104
    context_aggregator = LLMContextAggregatorPair(context)
105
106
    # Build pipeline
107
    pipeline = Pipeline(
108
        [
109
            transport.input(),
110
            stt,
111
            context_aggregator.user(),
112
            llm,
113
            tts,
114
            transport.output(),
115
            context_aggregator.assistant(),
116
        ]
117
    )
118
119
    task = PipelineTask(pipeline)
120
121
    @transport.event_handler("on_client_connected")
122
    async def on_client_connected(transport, client):
123
        logger.info("Student connected")
124
        messages.append(
125
            {"role": "system", "content": "Greet the student warmly and ask what subject or topic they'd like to learn today."}
126
        )
127
        await task.queue_frames([LLMRunFrame()])
128
129
    @transport.event_handler("on_client_disconnected")
130
    async def on_client_disconnected(transport, client):
131
        logger.info("Student disconnected")
132
        await task.cancel()
133
134
    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
135
    await runner.run(task)
136
137
if __name__ == "__main__":
138
    from pipecat.runner.run import main
139
    main()

1
stt = SarvamSTTService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    language="hi-IN",  # Hindi
4
    model="saaras:v3",
5
    mode="transcribe"
6
)
7
8
tts = SarvamTTSService(
9
    api_key=os.getenv("SARVAM_API_KEY"),
10
    target_language_code="hi-IN",
11
    model="bulbul:v3",
12
    speaker="simran"  # Warm and friendly teacher voice
13
)
14
15
llm = SarvamLLMService(
16
    api_key=os.getenv("SARVAM_API_KEY"),
17
    settings=SarvamLLMService.Settings(model="sarvam-105b"),
18
)

1
stt = SarvamSTTService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    language="ta-IN",
4
    model="saaras:v3",
5
    mode="transcribe"
6
)
7
8
tts = SarvamTTSService(
9
    api_key=os.getenv("SARVAM_API_KEY"),
10
    target_language_code="ta-IN",
11
    model="bulbul:v3",
12
    speaker="ishita"
13
)
14
15
llm = SarvamLLMService(
16
    api_key=os.getenv("SARVAM_API_KEY"),
17
    settings=SarvamLLMService.Settings(model="sarvam-105b"),
18
)

1
stt = SarvamSTTService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    language="unknown",  # Auto-detects language
4
    model="saaras:v3",
5
    mode="transcribe"
6
)
7
8
tts = SarvamTTSService(
9
    api_key=os.getenv("SARVAM_API_KEY"),
10
    target_language_code="en-IN",
11
    model="bulbul:v3",
12
    speaker="ishita"
13
)
14
15
llm = SarvamLLMService(
16
    api_key=os.getenv("SARVAM_API_KEY"),
17
    settings=SarvamLLMService.Settings(model="sarvam-105b"),
18
)

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:v3",  # Speech-to-English translation
6
    mode="translate"
7
)
8
9
tts = SarvamTTSService(
10
    api_key=os.getenv("SARVAM_API_KEY"),
11
    target_language_code="en-IN",
12
    model="bulbul:v3",
13
    speaker="ishita"
14
)
15
16
llm = SarvamLLMService(
17
    api_key=os.getenv("SARVAM_API_KEY"),
18
    settings=SarvamLLMService.Settings(model="sarvam-105b"),
19
)

1
tts = SarvamTTSService(
2
    api_key=os.getenv("SARVAM_API_KEY"),
3
    target_language_code="en-IN",
4
    model="bulbul:v3",
5
    speaker="ishita",
6
    pace=0.9,            # Slightly slower for better understanding
7
    speech_sample_rate=24000  # 8000, 16000, 22050, 24000 Hz (default). v3 REST API also supports 32000, 44100, 48000 Hz
8
)