File size: 1,950 Bytes
499170b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32e3b61
499170b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32e3b61
 
 
499170b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Web search tool using DuckDuckGo."""

import asyncio
from typing import Any

from duckduckgo_search import DDGS

from src.utils.exceptions import SearchError
from src.utils.models import Citation, Evidence


class WebTool:
    """Search tool for general web search via DuckDuckGo."""

    def __init__(self) -> None:
        pass

    @property
    def name(self) -> str:
        return "web"

    async def search(self, query: str, max_results: int = 10) -> list[Evidence]:
        """
        Search DuckDuckGo and return evidence.

        Note: duckduckgo-search is synchronous, so we run it in executor.
        """
        loop = asyncio.get_running_loop()
        try:
            results = await loop.run_in_executor(
                None,
                lambda: self._sync_search(query, max_results),
            )
            return results
        except Exception as e:
            raise SearchError(f"Web search failed: {e}") from e

    def _sync_search(self, query: str, max_results: int) -> list[Evidence]:
        """Synchronous search implementation."""
        evidence_list = []

        with DDGS() as ddgs:
            results: list[dict[str, Any]] = list(ddgs.text(query, max_results=max_results))

        # Truncation rationale: LLM context limits + cost optimization
        # - Content: 1000 chars (~250 tokens) - web snippets are shorter than abstracts
        # - Title: 500 chars covers most web page titles
        for result in results:
            evidence_list.append(
                Evidence(
                    content=result.get("body", "")[:1000],
                    citation=Citation(
                        source="web",
                        title=result.get("title", "Unknown")[:500],
                        url=result.get("href", ""),
                        date="Unknown",
                        authors=[],
                    ),
                )
            )

        return evidence_list