feat: add bing search (camel-ai#1865)

Co-authored-by: NeilJohnson0930 <[email protected]>
Co-authored-by: Wendong <[email protected]>
Co-authored-by: Wendong-Fan <[email protected]>

Author: 3 people

camel/toolkits/search_toolkit.py

@@ -835,6 +835,116 @@ def search_baidu(self, query: str, max_results: int = 5) -> Dict[str, Any]:
         except Exception as e:
             return {"error": f"Baidu scraping error: {e!s}"}
 
+    def search_bing(self, query: str, max_results: int = 5) -> Dict[str, Any]:
+        r"""Use Bing search engine to search information for the given query.
+
+        This function queries the Chinese version of Bing search engine (cn.
+        bing.com) using web scraping to retrieve relevant search results. It
+        extracts search results including titles, snippets, and URLs. This
+        function is particularly useful when the query is in Chinese or when
+        Chinese search results are desired.
+
+        Args:
+            query (str): The search query string to submit to Bing. Works best
+                with Chinese queries or when Chinese results are preferred.
+            max_results (int): Maximum number of results to return.
+                (default: :obj:`5`)
+
+        Returns:
+            Dict ([str, Any]): A dictionary containing either:
+                - 'results': A list of dictionaries, each with:
+                    - 'result_id': The index of the result.
+                    - 'snippet': A brief description of the search result.
+                    - 'title': The title of the search result.
+                    - 'link': The URL of the search result.
+                - or 'error': An error message if something went wrong.
+        """
+        from typing import Any, Dict, List, cast
+        from urllib.parse import urlencode
+
+        from bs4 import BeautifulSoup, Tag
+
+        try:
+            query = urlencode({"q": query})
+            url = f'https://cn.bing.com/search?{query}'
+            headers = {
+                "User-Agent": (
+                    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                    "AppleWebKit/537.36 (KHTML, like Gecko) "
+                    "Chrome/120.0.0.0 Safari/537.36"
+                ),
+            }
+            # Add timeout to prevent hanging
+            response = requests.get(url, headers=headers, timeout=10)
+
+            # Check if the request was successful
+            if response.status_code != 200:
+                return {
+                    "error": (
+                        f"Bing returned status code: "
+                        f"{response.status_code}"
+                    )
+                }
+
+            response.encoding = 'utf-8'
+            soup = BeautifulSoup(response.text, 'html.parser')
+
+            b_results_element = soup.find("ol", id="b_results")
+            if b_results_element is None:
+                return {"results": []}
+
+            # Ensure b_results is a Tag and find all li elements
+            b_results_tag = cast(Tag, b_results_element)
+            result_items = b_results_tag.find_all("li")
+
+            results: List[Dict[str, Any]] = []
+            for i in range(min(len(result_items), max_results)):
+                row = result_items[i]
+                if not isinstance(row, Tag):
+                    continue
+
+                h2_element = row.find("h2")
+                if h2_element is None:
+                    continue
+                h2_tag = cast(Tag, h2_element)
+
+                title = h2_tag.get_text().strip()
+
+                link_tag_element = h2_tag.find("a")
+                if link_tag_element is None:
+                    continue
+                link_tag = cast(Tag, link_tag_element)
+
+                link = link_tag.get("href")
+                if link is None:
+                    continue
+
+                content_element = row.find("p", class_="b_algoSlug")
+                content_text = ""
+                if content_element is not None and isinstance(
+                    content_element, Tag
+                ):
+                    content_text = content_element.get_text()
+
+                row_data = {
+                    "result_id": i + 1,
+                    "snippet": content_text,
+                    "title": title,
+                    "link": link,
+                }
+                results.append(row_data)
+
+            if not results:
+                return {
+                    "warning": "No results found. Check if "
+                    "Bing HTML structure has changed."
+                }
+
+            return {"results": results}
+
+        except Exception as e:
+            return {"error": f"Bing scraping error: {e!s}"}
+
     def get_tools(self) -> List[FunctionTool]:
         r"""Returns a list of FunctionTool objects representing the
         functions in the toolkit.
@@ -853,4 +963,5 @@ def get_tools(self) -> List[FunctionTool]:
             FunctionTool(self.search_brave),
             FunctionTool(self.search_bocha),
             FunctionTool(self.search_baidu),
+            FunctionTool(self.search_bing),
         ]

examples/toolkits/search_toolkit.py

@@ -17,39 +17,6 @@
 from camel.agents import ChatAgent
 from camel.toolkits import FunctionTool, SearchToolkit
 
-agent = ChatAgent(
-    system_message="""You are a helpful assistant that can use baidu search 
-        engine to answer questions.""",
-    tools=[FunctionTool(SearchToolkit().search_baidu)],
-)
-
-usr_msg = "今天北京的天气如何"
-
-response = agent.step(input_message=usr_msg, response_format=None)
-
-print(response.msgs[0].content)
-
-"""
-===============================================================================
-今天北京的天气信息可以通过以下链接查看:
-
-1. [中国天气网 - 北京天气预报](http://www.baidu.com/link?
-url=AJhE9PhEO3TmkJ70CUcRsR3NVB3m6wxN5Imdp0ZVsEBK1t8YhtM6YMxrQy3_vRN6dJv4FLHkBCe
-fZURnzHTm9gio-dS4-4MwGVgJe40m7prOoggce2eB0h-3DsllbKMm)
-2. [中国天气网 - 北京天气预报](http://www.baidu.com/link?
-url=1vhNOfl9tV65_104GMQbDnU_fdCZPXDV2BtTJelxdd6isdSZjAHvtoXqOWG3n7D1N-m9zAmOhQG
-c-jEGqiXe9K)
-3. [中国天气网 - 北京天气预报](http://www.baidu.com/link?
-url=Q0URfpodXDpUe1TKBPpToKIyIuCcjSGUR5jorx81g8Pni5XH-Tbc6AXMa7EwCWjBG3jysTZb43S
-6ZCsJOKvPw2EbIlQ_bMu42-5sCraqXlS)
-4. [中国天气网 - 北京天气预报一周](http://www.baidu.com/link?
-url=TtFe8QryJFuwX1kx50YF5WijRcd2TMJRhPudDQvqW7TG4siah68gUZd_frsVWPi1xkYvrxoYL87
-QMH0wSjDYOq)
-
-请点击链接查看详细的天气预报信息。
-===============================================================================
-"""
-
 res_simple = SearchToolkit().query_wolfram_alpha(
     query="solve 3x-7=11", is_detailed=False
 )
@@ -284,3 +251,71 @@ class PersonInfo(BaseModel):
 dly":None},"videos":None}
 ===============================================================================
 """
+
+
+agent = ChatAgent(
+    system_message="""You are a helpful assistant that can use baidu search 
+        engine to answer questions.""",
+    tools=[FunctionTool(SearchToolkit().search_baidu)],
+)
+
+usr_msg = "今天北京的天气如何"
+
+response = agent.step(input_message=usr_msg, response_format=None)
+
+print(response.msgs[0].content)
+
+"""
+===============================================================================
+今天北京的天气信息可以通过以下链接查看:
+
+1. [中国天气网 - 北京天气预报](http://www.baidu.com/link?
+url=AJhE9PhEO3TmkJ70CUcRsR3NVB3m6wxN5Imdp0ZVsEBK1t8YhtM6YMxrQy3_vRN6dJv4FLHkBCe
+fZURnzHTm9gio-dS4-4MwGVgJe40m7prOoggce2eB0h-3DsllbKMm)
+2. [中国天气网 - 北京天气预报](http://www.baidu.com/link?
+url=1vhNOfl9tV65_104GMQbDnU_fdCZPXDV2BtTJelxdd6isdSZjAHvtoXqOWG3n7D1N-m9zAmOhQG
+c-jEGqiXe9K)
+3. [中国天气网 - 北京天气预报](http://www.baidu.com/link?
+url=Q0URfpodXDpUe1TKBPpToKIyIuCcjSGUR5jorx81g8Pni5XH-Tbc6AXMa7EwCWjBG3jysTZb43S
+6ZCsJOKvPw2EbIlQ_bMu42-5sCraqXlS)
+4. [中国天气网 - 北京天气预报一周](http://www.baidu.com/link?
+url=TtFe8QryJFuwX1kx50YF5WijRcd2TMJRhPudDQvqW7TG4siah68gUZd_frsVWPi1xkYvrxoYL87
+QMH0wSjDYOq)
+
+请点击链接查看详细的天气预报信息。
+===============================================================================
+"""
+
+bing_call_agent = ChatAgent(
+    system_message="""You are a helpful assistant that can use baidu search 
+        engine to answer questions.""",
+    tools=[FunctionTool(SearchToolkit().search_bing)],
+)
+
+bing_usr_msg = "帮忙查询巴黎圣母院最新修复进展"
+
+response = bing_call_agent.step(
+    input_message=bing_usr_msg, response_format=None
+)
+
+print(response.msgs[0].content)
+
+"""
+===============================================================================
+以下是关于巴黎圣母院最新修复进展的一些信息:
+
+1. **时隔4年,灾后余生的巴黎圣母院即将重生** -
+[知乎](https://zhuanlan.zhihu.com/p/619405504)
+   
+2. **历时4年,耗资70亿,被烧塌的巴黎圣母院修好了!!** -
+[腾讯网](https://news.qq.com/rain/a/20231018A0329F00)
+
+3. **一票难求!巴黎圣母院重新开放!5年修复离不开来自东方的支持** -
+[新浪财经](https://finance.sina.com.cn/wm/2024-12-08/doc-incyumnp3384392.shtml)
+
+4. **巴黎圣母院浴火重生!建筑学者:勘探报告近3000页,修复工作复杂** -
+[腾讯网](https://news.qq.com/rain/a/20241208A05Q9K00)
+
+这些链接提供了关于巴黎圣母院修复的详细信息和最新进展。
+===============================================================================
+"""

test/toolkits/test_search_functions.py

@@ -248,6 +248,67 @@ def test_search_baidu(mock_get, search_toolkit):
     )
 
 
+@patch('requests.get')
+def test_search_bing(mock_get, search_toolkit):
+    # Mock the response from Bing search
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.encoding = "utf-8"
+    mock_response.text = """
+    <html>
+        <head><title>Bing Search</title></head>
+        <body>
+            <ol id="b_results">
+                <li>
+                    <h2><a href="https://example1.com">Test Title 1</a></h2>
+                    <p class="b_algoSlug">Test Snippet 1</p>
+                </li>
+                <li>
+                    <h2><a href="https://example2.com">Test Title 2</a></h2>
+                    <p class="b_algoSlug">Test Snippet 2</p>
+                </li>
+            </ol>
+        </body>
+    </html>
+    """
+    mock_get.return_value = mock_response
+
+    # Call the function under test
+    result = search_toolkit.search_bing(query="test query", max_results=5)
+
+    # Expected output
+    expected_output = {
+        "results": [
+            {
+                "result_id": 1,
+                "title": "Test Title 1",
+                "snippet": "Test Snippet 1",
+                "link": "https://example1.com",
+            },
+            {
+                "result_id": 2,
+                "title": "Test Title 2",
+                "snippet": "Test Snippet 2",
+                "link": "https://example2.com",
+            },
+        ]
+    }
+
+    # Assertions
+    assert result == expected_output
+    mock_get.assert_called_once_with(
+        "https://cn.bing.com/search?q=test+query",
+        headers={
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/120.0.0.0 Safari/537.36"
+            ),
+        },
+        timeout=10,
+    )
+
+
 @patch('requests.get')
 @patch('wolframalpha.Client')
 @patch('os.environ.get')