Spaces:
Sleeping
Sleeping
File size: 12,625 Bytes
40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 a68dd7c 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 a68dd7c 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 a68dd7c 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 a68dd7c 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 a68dd7c 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 4d5ce47 40367a2 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 | #!/usr/bin/env python3
"""
Test script for the Multi-Model Chat Backend API with strict typing
"""
import requests
import time
from typing import Dict, Any, List, Optional, Callable
from dataclasses import dataclass
from enum import Enum
from custom_types import (
create_model_id, create_conversation_id, create_user_message,
create_assistant_response
)
# Configuration
API_BASE_URL = "http://localhost:7860"
TEST_MODELS = [
"thoughtcast/outlandish-spiked-lassie-experiment",
"thoughtcast/marketing-spiked-lassie-experiment",
"TinyLlama/TinyLlama-1.1B-Chat-v1.0"
]
class TestStatus(Enum):
"""Test status enumeration."""
PASSED = "passed"
FAILED = "failed"
ERROR = "error"
@dataclass(frozen=True)
class TestResult:
"""Test result with strict typing."""
name: str
status: TestStatus
message: str
details: Optional[Dict[str, Any]] = None
@dataclass(frozen=True)
class ChatTestRequest:
"""Chat test request with validation."""
model_id: str
message: str
conversation_id: str = "test"
max_new_tokens: int = 50
temperature: float = 0.7
top_p: float = 0.9
repetition_penalty: float = 1.1
no_repeat_ngram_size: int = 3
do_sample: bool = True
def to_payload(self) -> Dict[str, Any]:
"""Convert to API payload with validation."""
# Validate inputs using our type system
model_id_wrapper = create_model_id(self.model_id)
conv_id_wrapper = create_conversation_id(self.conversation_id)
message_wrapper = create_user_message(self.message)
return {
"message": message_wrapper.unwrap(),
"conversation_id": conv_id_wrapper.unwrap(),
"model_id": model_id_wrapper.unwrap(),
"max_new_tokens": self.max_new_tokens,
"temperature": self.temperature,
"top_p": self.top_p,
"repetition_penalty": self.repetition_penalty,
"no_repeat_ngram_size": self.no_repeat_ngram_size,
"do_sample": self.do_sample
}
def test_health_check() -> TestResult:
"""Test the health check endpoint."""
print("Testing health check...")
try:
response = requests.get(f"{API_BASE_URL}/health")
if response.status_code == 200:
data = response.json()
print(f"β Health check passed: {data['status']}")
print(f" Models loaded: {data['models_loaded']}")
print(f" GPU memory used: {data['gpu_memory_used']:.2%}")
print(f" Active conversations: {data['active_conversations']}")
return TestResult(
name="health_check",
status=TestStatus.PASSED,
message="Health check successful",
details=data
)
else:
print(f"β Health check failed: {response.status_code}")
return TestResult(
name="health_check",
status=TestStatus.FAILED,
message=f"HTTP {response.status_code}: {response.text}"
)
except Exception as e:
print(f"β Health check error: {e}")
return TestResult(
name="health_check",
status=TestStatus.ERROR,
message=str(e)
)
def test_list_models() -> TestResult:
"""Test the list models endpoint."""
print("\nTesting list models...")
try:
response = requests.get(f"{API_BASE_URL}/models")
if response.status_code == 200:
data = response.json()
print(f"β Models endpoint working")
print(f" Available models: {data['available_models']}")
print(f" Loaded models: {data['loaded_models']}")
# Validate model IDs
for model_id in data['available_models']:
try:
_ = create_model_id(model_id)
except ValueError as e:
return TestResult(
name="list_models",
status=TestStatus.FAILED,
message=f"Invalid model ID format: {model_id} - {e}"
)
return TestResult(
name="list_models",
status=TestStatus.PASSED,
message="Models endpoint working",
details=data
)
else:
print(f"β Models endpoint failed: {response.status_code}")
return TestResult(
name="list_models",
status=TestStatus.FAILED,
message=f"HTTP {response.status_code}: {response.text}"
)
except Exception as e:
print(f"β Models endpoint error: {e}")
return TestResult(
name="list_models",
status=TestStatus.ERROR,
message=str(e)
)
def test_chat(model_id: str, message: str, conversation_id: str = "test") -> TestResult:
"""Test the chat endpoint with a specific model."""
print(f"\nTesting chat with {model_id}...")
try:
# Create and validate chat request
chat_request = ChatTestRequest(
model_id=model_id,
message=message,
conversation_id=conversation_id
)
payload = chat_request.to_payload()
response = requests.post(f"{API_BASE_URL}/chat", json=payload)
if response.status_code == 200:
data = response.json()
# Validate response
try:
_ = create_model_id(data['model_id'])
_ = create_conversation_id(data['conversation_id'])
_ = create_assistant_response(data['response'])
except ValueError as e:
return TestResult(
name=f"chat_{model_id.replace('/', '_')}",
status=TestStatus.FAILED,
message=f"Invalid response format: {e}"
)
print(f"β Chat successful with {model_id}")
print(f" Response: {data['response'][:100]}...")
print(f" Tokens used: {data['tokens_used']}")
return TestResult(
name=f"chat_{model_id.replace('/', '_')}",
status=TestStatus.PASSED,
message=f"Chat successful with {model_id}",
details=data
)
else:
print(f"β Chat failed with {model_id}: {response.status_code}")
print(f" Error: {response.text}")
return TestResult(
name=f"chat_{model_id.replace('/', '_')}",
status=TestStatus.FAILED,
message=f"HTTP {response.status_code}: {response.text}"
)
except ValueError as e:
print(f"β Chat validation error with {model_id}: {e}")
return TestResult(
name=f"chat_{model_id.replace('/', '_')}",
status=TestStatus.ERROR,
message=f"Validation error: {e}"
)
except Exception as e:
print(f"β Chat error with {model_id}: {e}")
return TestResult(
name=f"chat_{model_id.replace('/', '_')}",
status=TestStatus.ERROR,
message=str(e)
)
def test_conversation_management() -> TestResult:
"""Test conversation management endpoints."""
print("\nTesting conversation management...")
try:
# List conversations
response = requests.get(f"{API_BASE_URL}/conversations")
if response.status_code == 200:
data = response.json()
print(f"β List conversations working")
print(f" Active conversations: {len(data['conversations'])}")
# Get specific conversation
test_conv_id = "test"
try:
_ = create_conversation_id(test_conv_id)
except ValueError as e:
return TestResult(
name="conversation_management",
status=TestStatus.ERROR,
message=f"Invalid test conversation ID: {e}"
)
response = requests.get(f"{API_BASE_URL}/conversations/{test_conv_id}")
if response.status_code == 200:
data = response.json()
print(f"β Get conversation working")
print(f" Messages in conversation: {data['message_count']}")
# Export conversation
response = requests.post(f"{API_BASE_URL}/conversations/{test_conv_id}/export")
if response.status_code == 200:
data = response.json()
print(f"β Export conversation working")
print(f" Exported {len(data['messages'])} messages")
return TestResult(
name="conversation_management",
status=TestStatus.PASSED,
message="Conversation management working"
)
except Exception as e:
print(f"β Conversation management error: {e}")
return TestResult(
name="conversation_management",
status=TestStatus.ERROR,
message=str(e)
)
def test_model_loading() -> TestResult:
"""Test model loading and unloading."""
print("\nTesting model loading/unloading...")
try:
# Try to load a model
model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
# Validate model ID
try:
_ = create_model_id(model_id)
except ValueError as e:
return TestResult(
name="model_loading",
status=TestStatus.ERROR,
message=f"Invalid model ID: {e}"
)
response = requests.post(f"{API_BASE_URL}/models/{model_id}/load")
if response.status_code == 200:
print(f"β Model loading working for {model_id}")
return TestResult(
name="model_loading",
status=TestStatus.PASSED,
message=f"Model loading successful for {model_id}"
)
else:
print(f"β Model loading failed for {model_id}: {response.status_code}")
return TestResult(
name="model_loading",
status=TestStatus.FAILED,
message=f"HTTP {response.status_code}: {response.text}"
)
except Exception as e:
print(f"β Model loading error: {e}")
return TestResult(
name="model_loading",
status=TestStatus.ERROR,
message=str(e)
)
def run_comprehensive_test() -> bool:
"""Run all tests with strict typing."""
print("π Starting comprehensive API tests...")
print("=" * 60)
# Wait for service to be ready
print("Waiting for service to be ready...")
for _ in range(30): # Wait up to 30 seconds
health_result = test_health_check()
if health_result.status == TestStatus.PASSED:
break
time.sleep(1)
else:
print("β Service not ready after 30 seconds")
return False
# Define test functions
test_functions: List[Callable[[], TestResult]] = [
test_list_models,
lambda: test_chat("thoughtcast/outlandish-spiked-lassie-experiment", "Hello, how are you?"),
lambda: test_chat("thoughtcast/marketing-spiked-lassie-experiment", "Tell me about your marketing strategy"),
lambda: test_chat("TinyLlama/TinyLlama-1.1B-Chat-v1.0", "What is machine learning?"),
test_conversation_management,
test_model_loading,
]
# Run tests and collect results
results: List[TestResult] = []
for test_func in test_functions:
result = test_func()
results.append(result)
# Analyze results
passed = sum(1 for r in results if r.status == TestStatus.PASSED)
failed = sum(1 for r in results if r.status == TestStatus.FAILED)
errors = sum(1 for r in results if r.status == TestStatus.ERROR)
print("\n" + "=" * 60)
print(f"π― Test Results: {passed}/{len(results)} tests passed")
print(f" Passed: {passed}")
print(f" Failed: {failed}")
print(f" Errors: {errors}")
# Print failed/error tests
if failed > 0 or errors > 0:
print("\nβ Failed/Error Tests:")
for result in results:
if result.status != TestStatus.PASSED:
print(f" {result.name}: {result.status.value} - {result.message}")
if passed == len(results):
print("π All tests passed! The API is working correctly.")
return True
else:
print("β Some tests failed. Please check the logs.")
return False
if __name__ == "__main__":
success = run_comprehensive_test()
exit(0 if success else 1) |