File size: 8,729 Bytes
78f67d6 |
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 |
#!/usr/bin/env python3
"""
Advanced finance tests including streaming and complex scenarios.
"""
import httpx
import json
import time
BASE_URL = "https://jeanbaptdzd-open-finance-llm-8b.hf.space"
def test_streaming_response():
"""Test streaming chat completion."""
print("\n" + "="*80)
print("TESTING STREAMING RESPONSE")
print("="*80)
payload = {
"model": "DragonLLM/qwen3-8b-fin-v1.0",
"messages": [
{
"role": "user",
"content": "Explain the Black-Scholes option pricing model in simple terms."
}
],
"stream": True,
"max_tokens": 150,
"temperature": 0.4
}
print(f"\nQuestion: {payload['messages'][0]['content']}")
print(f"\nStreaming response:")
print("─" * 80)
start_time = time.time()
chunks_received = 0
full_response = ""
try:
with httpx.stream(
"POST",
f"{BASE_URL}/v1/chat/completions",
json=payload,
timeout=60.0
) as response:
for line in response.iter_lines():
if line.startswith("data: "):
data_str = line[6:] # Remove "data: " prefix
if data_str == "[DONE]":
break
try:
chunk_data = json.loads(data_str)
delta = chunk_data.get("choices", [{}])[0].get("delta", {})
content = delta.get("content", "")
if content:
print(content, end="", flush=True)
full_response += content
chunks_received += 1
except json.JSONDecodeError:
pass
elapsed = time.time() - start_time
print("\n" + "─" * 80)
print(f"\n✅ Streaming test successful!")
print(f" ⏱️ Time: {elapsed:.2f}s")
print(f" 📦 Chunks received: {chunks_received}")
print(f" 📝 Total characters: {len(full_response)}")
return True
except Exception as e:
print(f"\n❌ Error: {e}")
return False
def test_complex_finance_scenario():
"""Test complex multi-step finance reasoning."""
print("\n" + "="*80)
print("TESTING COMPLEX FINANCE SCENARIO")
print("="*80)
question = """A company has the following financials:
- Revenue: $10 million
- Cost of Goods Sold: $4 million
- Operating Expenses: $3 million
- Interest Expense: $500,000
- Tax Rate: 25%
Calculate the company's:
1. Gross Profit Margin
2. Operating Income
3. Net Income
4. EBITDA (assuming $200k depreciation)"""
payload = {
"model": "DragonLLM/qwen3-8b-fin-v1.0",
"messages": [
{"role": "user", "content": question}
],
"temperature": 0.1,
"max_tokens": 300
}
print(f"\nQuestion:\n{question}")
print("\n" + "─" * 80)
start_time = time.time()
try:
response = httpx.post(
f"{BASE_URL}/v1/chat/completions",
json=payload,
timeout=60.0
)
elapsed = time.time() - start_time
if response.status_code == 200:
data = response.json()
answer = data['choices'][0]['message']['content']
usage = data.get('usage', {})
print(f"\n💬 Answer:\n{answer}")
print("\n" + "─" * 80)
print(f"\n✅ Complex scenario test successful!")
print(f" ⏱️ Time: {elapsed:.2f}s")
print(f" 📝 Tokens: {usage.get('total_tokens', 'N/A')}")
# Check for key calculations in response
calculations = ["gross profit", "operating income", "net income", "ebitda"]
found = [calc for calc in calculations if calc in answer.lower()]
print(f" 🎯 Calculations mentioned: {len(found)}/{len(calculations)}")
return True
else:
print(f"❌ Error: HTTP {response.status_code}")
return False
except Exception as e:
print(f"❌ Error: {e}")
return False
def test_financial_advice():
"""Test investment advice generation."""
print("\n" + "="*80)
print("TESTING FINANCIAL ADVICE")
print("="*80)
question = """I'm 30 years old with $50,000 to invest. My risk tolerance is moderate,
and I'm investing for retirement in 35 years. What asset allocation would you recommend?"""
payload = {
"model": "DragonLLM/qwen3-8b-fin-v1.0",
"messages": [
{"role": "user", "content": question}
],
"temperature": 0.5,
"max_tokens": 250
}
print(f"\nQuestion: {question}")
print("\n" + "─" * 80)
try:
response = httpx.post(
f"{BASE_URL}/v1/chat/completions",
json=payload,
timeout=60.0
)
if response.status_code == 200:
data = response.json()
answer = data['choices'][0]['message']['content']
print(f"\n💬 Answer:\n{answer}")
print("\n" + "─" * 80)
print(f"\n✅ Financial advice test successful!")
# Check for relevant concepts
concepts = ["stocks", "bonds", "diversification", "allocation", "risk"]
found = [c for c in concepts if c in answer.lower()]
print(f" 🎯 Relevant concepts: {', '.join(found)}")
return True
else:
print(f"❌ Error: HTTP {response.status_code}")
return False
except Exception as e:
print(f"❌ Error: {e}")
return False
def test_market_interpretation():
"""Test market data interpretation."""
print("\n" + "="*80)
print("TESTING MARKET DATA INTERPRETATION")
print("="*80)
question = """A stock has the following characteristics:
- Current Price: $100
- 52-week High: $120
- 52-week Low: $75
- P/E Ratio: 25
- Beta: 1.5
- Dividend Yield: 2%
What does this data tell you about the stock's risk and valuation?"""
payload = {
"model": "DragonLLM/qwen3-8b-fin-v1.0",
"messages": [
{"role": "user", "content": question}
],
"temperature": 0.3,
"max_tokens": 250
}
print(f"\nQuestion:\n{question}")
print("\n" + "─" * 80)
try:
response = httpx.post(
f"{BASE_URL}/v1/chat/completions",
json=payload,
timeout=60.0
)
if response.status_code == 200:
data = response.json()
answer = data['choices'][0]['message']['content']
print(f"\n💬 Answer:\n{answer}")
print("\n" + "─" * 80)
print(f"\n✅ Market interpretation test successful!")
# Check for key concepts
concepts = ["beta", "p/e", "volatility", "risk", "valuation"]
found = [c for c in concepts if c in answer.lower()]
print(f" 🎯 Key concepts addressed: {', '.join(found)}")
return True
else:
print(f"❌ Error: HTTP {response.status_code}")
return False
except Exception as e:
print(f"❌ Error: {e}")
return False
def main():
"""Run all advanced tests."""
print("="*80)
print("ADVANCED FINANCE LLM TESTING")
print("="*80)
print(f"Target: {BASE_URL}")
results = []
# Test 1: Streaming
results.append(("Streaming Response", test_streaming_response()))
time.sleep(2)
# Test 2: Complex scenario
results.append(("Complex Finance Calculations", test_complex_finance_scenario()))
time.sleep(2)
# Test 3: Financial advice
results.append(("Investment Advice", test_financial_advice()))
time.sleep(2)
# Test 4: Market interpretation
results.append(("Market Data Interpretation", test_market_interpretation()))
# Summary
print("\n" + "="*80)
print("ADVANCED TESTS SUMMARY")
print("="*80)
passed = sum(1 for _, success in results if success)
total = len(results)
print(f"\n✅ Passed: {passed}/{total}")
for test_name, success in results:
status = "✅" if success else "❌"
print(f" {status} {test_name}")
print("\n" + "="*80)
if __name__ == "__main__":
main()
|