Spaces:
Sleeping
Sleeping
File size: 3,629 Bytes
bb0c63f | 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 | """
Basic usage examples for the Enterprise AI Gateway
"""
import requests
import json
import time
# Configuration
BASE_URL = "http://localhost:8000"
API_KEY = "your-api-key-here" # Replace with your actual API key
def example_health_check():
"""Example of health check endpoint usage"""
print("=== Health Check Example ===")
response = requests.get(f"{BASE_URL}/health")
if response.status_code == 200:
data = response.json()
print(f"Status: {data['status']}")
print(f"Provider: {data['provider']}")
print(f"Timestamp: {data['timestamp']}")
else:
print(f"Health check failed with status code: {response.status_code}")
def example_single_query():
"""Example of single query to the LLM"""
print("\n=== Single Query Example ===")
headers = {
"Content-Type": "application/json",
"X-API-Key": API_KEY
}
payload = {
"prompt": "Explain the benefits of using a secure LLM gateway in enterprise applications.",
"max_tokens": 256,
"temperature": 0.7
}
response = requests.post(f"{BASE_URL}/query", headers=headers, json=payload)
if response.status_code == 200:
data = response.json()
print(f"Response: {data['response']}")
print(f"Provider: {data['provider']}")
print(f"Latency: {data['latency_ms']} ms")
print(f"Status: {data['status']}")
else:
print(f"Query failed with status code: {response.status_code}")
print(f"Response: {response.text}")
def example_batch_queries():
"""Example of batch queries to the LLM"""
print("\n=== Batch Queries Example ===")
queries = [
"What is artificial intelligence?",
"Explain machine learning in simple terms",
"What are the benefits of cloud computing?",
"How does blockchain technology work?",
"What is the difference between HTTP and HTTPS?"
]
headers = {
"Content-Type": "application/json",
"X-API-Key": API_KEY
}
results = []
for i, query in enumerate(queries, 1):
print(f"\nProcessing query {i}/{len(queries)}: {query[:50]}...")
payload = {
"prompt": query,
"max_tokens": 128,
"temperature": 0.7
}
response = requests.post(f"{BASE_URL}/query", headers=headers, json=payload)
if response.status_code == 200:
data = response.json()
results.append({
"query": query,
"response": data["response"],
"provider": data["provider"],
"latency_ms": data["latency_ms"]
})
print(f" ✓ Success - {data['provider']} ({data['latency_ms']} ms)")
else:
print(f" ✗ Failed - Status {response.status_code}")
# Small delay to avoid rate limiting
time.sleep(0.5)
# Print summary
print(f"\n=== Batch Results Summary ===")
total_latency = sum(result["latency_ms"] for result in results if "latency_ms" in result)
avg_latency = total_latency / len(results) if results else 0
print(f"Successful queries: {len(results)}/{len(queries)}")
print(f"Average latency: {avg_latency:.2f} ms")
print(f"Providers used: {set(result['provider'] for result in results if 'provider' in result)}")
if __name__ == "__main__":
# Note: Make sure the Enterprise AI Gateway is running before executing these examples
example_health_check()
example_single_query()
example_batch_queries() |