llmsim 0.2.0

LLM Traffic Simulator - A lightweight, high-performance LLM API simulator
Documentation 
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "openai>=1.60.0",
# ]
# ///
"""
OpenAI client example for llmsim.

This script demonstrates connecting to a running llmsim server using the
official OpenAI Python library. The server simulates LLM responses with
realistic latency without running actual models.

Server endpoints:
    POST /openai/v1/chat/completions - Chat completions (streaming supported)
    POST /openai/v1/responses        - Responses API
    GET  /openai/v1/models           - List available models
    GET  /openai/v1/models/:id       - Get model details

Prerequisites:
    Start the llmsim server first:
        llmsim serve --port 8080

    Or from source:
        cargo run --release -- serve --port 8080

Usage:
    uv run examples/openai_client.py

Environment variables:
    LLMSIM_URL: Server URL (default: http://localhost:8080/openai/v1)
"""

import os
import sys

from openai import OpenAI


def main() -> None:
    base_url = os.environ.get("LLMSIM_URL", "http://localhost:8080/openai/v1")

    print("=" * 50)
    print("OpenAI SDK + LLMSim Example")
    print("=" * 50)
    print(f"\nConnecting to: {base_url}")
    print()

    # Create OpenAI client pointing to llmsim
    client = OpenAI(
        base_url=base_url,
        api_key="not-needed",  # llmsim doesn't require auth
    )

    # Example 1: Simple completion
    print("1. Simple Completion")
    print("-" * 30)
    try:
        response = client.chat.completions.create(
            model="gpt-5",
            messages=[
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": "What is the capital of France?"},
            ],
            max_tokens=100,
        )
        print(f"Response: {response.choices[0].message.content}")
        print(f"Model: {response.model}")
        print(f"Tokens: {response.usage}")
    except Exception as e:
        print(f"Error: {e}")
        print("\nMake sure the llmsim server is running:")
        print("  llmsim serve --port 8080")
        sys.exit(1)
    print()

    # Example 2: Streaming
    print("2. Streaming Response")
    print("-" * 30)
    print("Response: ", end="", flush=True)

    stream = client.chat.completions.create(
        model="gpt-5",
        messages=[
            {"role": "user", "content": "Tell me a short story."},
        ],
        max_tokens=100,
        stream=True,
    )

    for chunk in stream:
        if chunk.choices[0].delta.content:
            print(chunk.choices[0].delta.content, end="", flush=True)
    print("\n")

    # Example 3: Different models
    print("3. Different Models")
    print("-" * 30)

    models = ["gpt-5-mini", "claude-opus-4.5", "o3-mini"]
    for model in models:
        response = client.chat.completions.create(
            model=model,
            messages=[{"role": "user", "content": "Hello!"}],
            max_tokens=50,
        )
        content = response.choices[0].message.content or ""
        print(f"{model}: {content[:60]}...")
    print()

    # Example 4: List available models
    print("4. Available Models")
    print("-" * 30)
    models_list = client.models.list()
    for model in list(models_list)[:5]:
        print(f"  - {model.id} (owned by: {model.owned_by})")
    print(f"  ... and {len(list(models_list)) - 5} more")
    print()

    # Example 5: Multiple messages (conversation)
    print("5. Multi-turn Conversation")
    print("-" * 30)
    response = client.chat.completions.create(
        model="gpt-5",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "My name is Alice."},
            {"role": "assistant", "content": "Hello Alice! Nice to meet you."},
            {"role": "user", "content": "What's my name?"},
        ],
        max_tokens=50,
    )
    print(f"Response: {response.choices[0].message.content}")
    print()

    print("=" * 50)
    print("Examples complete!")
    print("=" * 50)


if __name__ == "__main__":
    main()