How to Evaluate You.com Search API

1
from youdotcom import You
2
3
with You("your_api_key") as you:
4
    result = you.search.unified(
5
        query=query,
6
        count=10
7
    )
8
9
# That's it. No date filters. No domain whitelists. Just search.

1
# Good: Comparing within the same latency class
2
compare_systems([
3
    "You.com (350ms p50)",
4
    "Competitor A (380ms p50)",
5
    "Competitor B (290ms p50)"
6
])
7
8
# Bad: Comparing across latency classes
9
compare_systems([
10
    "You.com (350ms p50)",
11
    "Deep Research API (2800ms p50)"  # Meaningless comparison
12
])

1
from youdotcom import You
2
3
with You("your_api_key") as you:
4
    result = you.search.unified(
5
        query=query,
6
        count=10
7
    )

1
result = you.search.unified(
2
    query=query,
3
    count=10,
4
    livecrawl="web",
5
    livecrawl_formats="markdown"
6
)
7
8
# Access full content via result.results.web[0].contents.markdown

1
result = you.search.unified(
2
    query="latest AI news",
3
    count=10,
4
    freshness="day"  # or "week", "month", "year", "2024-01-01to2024-12-31"
5
)

1
from youdotcom import You
2
import time
3
4
def run_eval(dataset_path, config):
5
    results = []
6
7
    with You("your_api_key") as you:
8
        for item in load_dataset(dataset_path):
9
            query = item['question']
10
            expected = item['answer']
11
12
            # Step 1: Retrieve
13
            start = time.time()
14
            search_results = you.search.unified(
15
                query=query,
16
                count=config.get('count', 10),
17
                livecrawl=config.get('livecrawl'),
18
                freshness=config.get('freshness')
19
            )
20
            latency = (time.time() - start) * 1000
21
22
            # Step 2: Synthesize answer using your LLM
23
            snippets = [r.snippets[0] for r in search_results.results.web if r.snippets]
24
            context = "\n".join(snippets)
25
            answer = llm.generate(
26
                f"Answer using only this context:\n{context}\n\n"
27
                f"Question: {query}\nAnswer:"
28
            )
29
30
            # Step 3: Grade
31
            grade = evaluate_answer(expected, answer)
32
33
            results.append({
34
                'correct': grade == 'correct',
35
                'latency_ms': latency
36
            })
37
38
    # Calculate metrics
39
    accuracy = sum(r['correct'] for r in results) / len(results)
40
    p50_latency = sorted([r['latency_ms'] for r in results])[len(results)//2]
41
42
    return {
43
        'accuracy': f"{accuracy:.1%}",
44
        'p50_latency': f"{p50_latency:.0f}ms"
45
    }

1
search_tool = {
2
    "type": "function",
3
    "function": {
4
        "name": "web_search",
5
        "description": "Search the web using You.com. Returns relevant snippets and URLs.",
6
        "parameters": {
7
            "type": "object",
8
            "properties": {
9
                "query": {
10
                    "type": "string",
11
                    "description": "The search query"
12
                }
13
            },
14
            "required": ["query"]
15
        }
16
    }
17
}

1
def handle_tool_call(tool_call):
2
    query = tool_call.arguments["query"]
3
4
    with You("your_api_key") as you:
5
        results = you.search.unified(query=query, count=10)
6
7
    # Format for agent consumption
8
    formatted = []
9
    for r in results.results.web[:5]:
10
        formatted.append({
11
            "title": r.title,
12
            "snippet": r.snippets[0] if r.snippets else r.description,
13
            "url": r.url
14
        })
15
16
    return json.dumps(formatted)

1
result = you.search.unified(
2
    query=query,
3
    freshness="week",
4
    country="US",
5
    language="EN",
6
    safesearch="strict"
7
)

1
result = you.search.unified(query=query, count=10)  # Start simple

1
results = you.search.unified(
2
    query=query,
3
    count=15,
4
    livecrawl="web",
5
    livecrawl_formats="markdown"
6
)

1
# Force fresh results
2
results = you.search.unified(
3
    query=query,
4
    count=10,
5
    freshness="day"  # or "week", "month"
6
)

1
configs = [
2
    {'count': 5},
3
    {'count': 10},
4
    {'count': 10, 'livecrawl': 'web', 'livecrawl_formats': 'markdown'}
5
]
6
7
for config in configs:
8
    results = run_eval('your_dataset.json', config)
9
    print(f"{config}: {results}")

1
# What to log
2
{
3
    'query': query,
4
    'latency_ms': latency,
5
    'num_results_returned': len(results.results.web),
6
    'used_livecrawl': bool(livecrawl),
7
    'freshness_filter': freshness,
8
    'timestamp': now()
9
}