File size: 1,981 Bytes
2571d1a
256f1a5
2571d1a
 
256f1a5
2571d1a
 
256f1a5
2571d1a
256f1a5
 
 
2571d1a
 
 
922b8c2
2571d1a
 
 
256f1a5
 
2571d1a
256f1a5
2571d1a
 
 
256f1a5
 
2571d1a
256f1a5
2571d1a
 
 
 
256f1a5
2571d1a
 
 
 
256f1a5
922b8c2
2571d1a
256f1a5
 
2571d1a
256f1a5
 
2571d1a
 
 
922b8c2
 
2571d1a
 
256f1a5
 
2571d1a
256f1a5
 
922b8c2
 
256f1a5
 
922b8c2
256f1a5
2571d1a
 
 
 
256f1a5
2571d1a
922b8c2
 
 
256f1a5
922b8c2
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import time
from app import respond, cancel_inference  # assuming respond and cancel_inference are defined in app.py

def test_api():
    # Set up input parameters for API model
    message = "What is the meaning of life?"
    history = []
    system_message = "You are a helpful, concise chatbot."
    max_tokens = 256
    temperature = 0.7
    top_p = 0.95
    use_local_model = False  # Use API model

    start_time = time.time()

    # Call the respond function (generator)
    result_generator = respond(
        message=message,
        history=history,
        system_message=system_message,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        use_local_model=use_local_model
    )

    # Collect results
    final_history = None
    for result in result_generator:
        final_history = result

    end_time = time.time()
    runtime = end_time - start_time

    print("API Runtime:", runtime)
    print("API Final conversation history:", final_history)


def test_local():
    # Set up input parameters for local model
    message = "What is the meaning of life?"
    history = []
    system_message = "You are a helpful, concise chatbot."
    max_tokens = 256
    temperature = 0.7
    top_p = 0.95
    use_local_model = True  # Use local model

    start_time = time.time()

    # Call the respond function (generator)
    result_generator = respond(
        message=message,
        history=history,
        system_message=system_message,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        use_local_model=use_local_model
    )

    # Collect results
    final_history = None
    for result in result_generator:
        final_history = result

    end_time = time.time()
    runtime = end_time - start_time

    print("Local Runtime:", runtime)
    print("Local Final conversation history:", final_history)

# Run the tests
if __name__ == "__main__":
    test_api()
    test_local()