File size: 11,633 Bytes
ca7a2c2 0140f42 ca7a2c2 0140f42 ca7a2c2 0140f42 ca7a2c2 |
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 |
"""
LocalMate Agent Test Script - Single vs ReAct Mode Comparison
Tests 10 queries in both modes:
- Single mode: configurable delay between queries
- ReAct mode: configurable delay between queries
- Configurable delay between modes
Generates detailed report with all step inputs/outputs.
"""
import asyncio
import json
import time
from datetime import datetime
import httpx
# =============================================================================
# CONFIGURATION - Adjust these values as needed
# =============================================================================
# API Settings
API_BASE = "https://cuong2004-localmate.hf.space/api/v1"
USER_ID = "test_comparison"
# Delay Settings (in seconds)
SINGLE_MODE_DELAY = 10 # Delay between queries in single mode
REACT_MODE_DELAY = 60 # Delay between queries in ReAct mode
MODE_SWITCH_DELAY = 60 # Delay between switching modes
REQUEST_TIMEOUT = 120 # Timeout for each API request
# =============================================================================
# Test Cases - 10 queries covering different scenarios
TEST_CASES = [
# {
# "id": 1,
# "query": "Quán cafe view đẹp",
# "description": "Simple text search - no location",
# "expected_tools": ["retrieve_context_text"],
# },
{
"id": 2,
"query": "Nhà hàng gần bãi biển Mỹ Khê",
"description": "Location-based search",
"expected_tools": ["find_nearby_places"],
},
# {
# "id": 3,
# "query": "Quán cafe có không gian xanh mát gần Cầu Rồng",
# "description": "Complex: location + feature (should use multiple tools in ReAct)",
# "expected_tools": ["find_nearby_places", "retrieve_context_text"],
# },
# {
# "id": 4,
# "query": "Phở ngon giá rẻ",
# "description": "Food-specific text search",
# "expected_tools": ["retrieve_context_text"],
# },
# {
# "id": 5,
# "query": "Địa điểm checkin đẹp gần Bà Nà",
# "description": "Location + activity type",
# "expected_tools": ["find_nearby_places"],
# },
# {
# "id": 6,
# "query": "Quán ăn hải sản có view sông gần trung tâm",
# "description": "Complex: location + category + feature",
# "expected_tools": ["find_nearby_places", "retrieve_context_text"],
# },
# {
# "id": 7,
# "query": "Khách sạn 5 sao gần biển",
# "description": "Hotel + location search",
# "expected_tools": ["find_nearby_places"],
# },
# {
# "id": 8,
# "query": "Quán bar có view đẹp về đêm",
# "description": "Nightlife text search",
# "expected_tools": ["retrieve_context_text"],
# },
# {
# "id": 9,
# "query": "Cafe rooftop gần Sơn Trà có coffee ngon",
# "description": "Complex: location + feature + quality",
# "expected_tools": ["find_nearby_places", "retrieve_context_text"],
# },
# {
# "id": 10,
# "query": "Nhà hàng Việt Nam authentic gần Rex Hotel",
# "description": "Specific location + category + style",
# "expected_tools": ["find_nearby_places", "retrieve_context_text"],
# },
]
async def run_test(client: httpx.AsyncClient, test_case: dict, react_mode: bool) -> dict:
"""Run a single test case and return results."""
start_time = time.time()
try:
response = await client.post(
f"{API_BASE}/chat",
json={
"message": test_case["query"],
"user_id": USER_ID,
"provider": "MegaLLM",
"react_mode": react_mode,
"max_steps": 5,
},
timeout=float(REQUEST_TIMEOUT),
)
duration = (time.time() - start_time) * 1000
if response.status_code == 200:
data = response.json()
return {
"success": True,
"test_id": test_case["id"],
"query": test_case["query"],
"description": test_case["description"],
"react_mode": react_mode,
"response": data.get("response", "")[:300],
"workflow": data.get("workflow", {}),
"tools_used": data.get("tools_used", []),
"api_duration_ms": data.get("duration_ms", 0),
"total_duration_ms": duration,
}
else:
return {
"success": False,
"test_id": test_case["id"],
"query": test_case["query"],
"react_mode": react_mode,
"error": f"HTTP {response.status_code}: {response.text[:200]}",
"total_duration_ms": duration,
}
except Exception as e:
return {
"success": False,
"test_id": test_case["id"],
"query": test_case["query"],
"react_mode": react_mode,
"error": str(e),
"total_duration_ms": (time.time() - start_time) * 1000,
}
def format_workflow_steps(workflow: dict) -> str:
"""Format workflow steps for report."""
steps = workflow.get("steps", [])
if not steps:
return "No steps recorded"
lines = []
for step in steps:
tool = step.get("tool", "N/A")
purpose = step.get("purpose", "")
results = step.get("results", 0)
lines.append(f" - {step.get('step', 'Unknown')}")
lines.append(f" Tool: `{tool}` | Results: {results}")
return "\n".join(lines)
def generate_report(single_results: list, react_results: list) -> str:
"""Generate detailed markdown report."""
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
report = f"""# LocalMate Agent Test Report
**Generated:** {timestamp}
## Summary
| Metric | Single Mode | ReAct Mode |
|--------|-------------|------------|
| Total Tests | {len(single_results)} | {len(react_results)} |
| Success | {sum(1 for r in single_results if r.get('success'))} | {sum(1 for r in react_results if r.get('success'))} |
| Avg Duration | {sum(r.get('api_duration_ms', 0) for r in single_results if r.get('success')) / max(1, sum(1 for r in single_results if r.get('success'))):.0f}ms | {sum(r.get('api_duration_ms', 0) for r in react_results if r.get('success')) / max(1, sum(1 for r in react_results if r.get('success'))):.0f}ms |
---
## Detailed Results
"""
for i, (single, react) in enumerate(zip(single_results, react_results)):
test_id = single.get("test_id", i + 1)
query = single.get("query", "N/A")
description = single.get("description", "")
report += f"""### Test Case {test_id}: {description}
**Query:** `{query}`
#### Single Mode
"""
if single.get("success"):
report += f"""- **Status:** ✅ Success
- **Duration:** {single.get('api_duration_ms', 0):.0f}ms
- **Tools Used:** {', '.join(single.get('tools_used', [])) or 'None'}
**Workflow:**
{format_workflow_steps(single.get('workflow', {}))}
**Response Preview:**
> {single.get('response', 'N/A')[:200]}...
"""
else:
report += f"""- **Status:** ❌ Failed
- **Error:** {single.get('error', 'Unknown')}
"""
report += """#### ReAct Mode
"""
if react.get("success"):
workflow = react.get("workflow", {})
report += f"""- **Status:** ✅ Success
- **Duration:** {react.get('api_duration_ms', 0):.0f}ms
- **Tools Used:** {', '.join(react.get('tools_used', [])) or 'None'}
- **Steps:** {len(workflow.get('steps', []))}
- **Intent Detected:** {workflow.get('intent_detected', 'N/A')}
**Workflow Steps:**
{format_workflow_steps(workflow)}
**Response Preview:**
> {react.get('response', 'N/A')[:200]}...
"""
else:
report += f"""- **Status:** ❌ Failed
- **Error:** {react.get('error', 'Unknown')}
"""
report += "---\n\n"
# Comparison analysis
report += """## Analysis
### Tool Usage Comparison
| Test | Single Mode Tools | ReAct Mode Tools | ReAct Steps |
|------|-------------------|------------------|-------------|
"""
for single, react in zip(single_results, react_results):
test_id = single.get("test_id", "?")
single_tools = ", ".join(single.get("tools_used", [])) if single.get("success") else "❌"
react_tools = ", ".join(react.get("tools_used", [])) if react.get("success") else "❌"
react_steps = len(react.get("workflow", {}).get("steps", [])) if react.get("success") else 0
report += f"| {test_id} | {single_tools} | {react_tools} | {react_steps} |\n"
report += """
### Key Observations
1. **Multi-tool queries**: ReAct mode can chain multiple tools for complex queries
2. **Single-tool queries**: Both modes perform similarly for simple queries
3. **Reasoning steps**: ReAct mode shows explicit reasoning before each tool call
"""
return report
async def main():
"""Main test runner."""
print("=" * 60)
print("LocalMate Agent Mode Comparison Test")
print("=" * 60)
print()
single_results = []
react_results = []
async with httpx.AsyncClient() as client:
# Test Single Mode
print(f"📌 Running Single Mode Tests ({SINGLE_MODE_DELAY}s delay)...")
print("-" * 40)
for test in TEST_CASES:
print(f" Test {test['id']}: {test['query'][:40]}...")
result = await run_test(client, test, react_mode=False)
single_results.append(result)
status = "✅" if result.get("success") else "❌"
tools = ", ".join(result.get("tools_used", [])) or "None"
print(f" {status} Tools: {tools} | {result.get('api_duration_ms', 0):.0f}ms")
if test["id"] < len(TEST_CASES):
await asyncio.sleep(SINGLE_MODE_DELAY)
print()
print(f"⏸️ Waiting {MODE_SWITCH_DELAY}s before ReAct mode...")
await asyncio.sleep(MODE_SWITCH_DELAY)
# Test ReAct Mode
print()
print(f"🧠 Running ReAct Mode Tests ({REACT_MODE_DELAY}s delay)...")
print("-" * 40)
for test in TEST_CASES:
print(f" Test {test['id']}: {test['query'][:40]}...")
result = await run_test(client, test, react_mode=True)
react_results.append(result)
status = "✅" if result.get("success") else "❌"
tools = ", ".join(result.get("tools_used", [])) or "None"
steps = len(result.get("workflow", {}).get("steps", []))
print(f" {status} Tools: {tools} | Steps: {steps} | {result.get('api_duration_ms', 0):.0f}ms")
if test["id"] < len(TEST_CASES):
await asyncio.sleep(REACT_MODE_DELAY)
# Generate report
print()
print("📝 Generating report...")
report = generate_report(single_results, react_results)
# Use absolute path based on script location
import os
script_dir = os.path.dirname(os.path.abspath(__file__))
report_path = os.path.join(script_dir, "react_comparison_report.md")
with open(report_path, "w", encoding="utf-8") as f:
f.write(report)
print(f"✅ Report saved to: {report_path}")
print()
print("=" * 60)
print("Test Complete!")
print("=" * 60)
if __name__ == "__main__":
asyncio.run(main())
|