Create tools.py

tools.py

@@ -0,0 +1,94 @@
+from smolagents import Tool
+import time
+import random
+from duckduckgo_search import DDGS
+import requests
+import os
+import wikipedia
+from bs4 import BeautifulSoup
+
+
+class DuckDuckGoSearchToolWH(Tool):
+    name = "web_search"
+    description = """Performs a DuckDuckGo web search based on your query (think a Google search) then returns the top search results."""
+    inputs = {"query": {"type": "string", "description": "The search query to perform."}}
+    output_type = "string"
+
+    def __init__(self, max_results=10, **kwargs):
+        super().__init__()
+        self.max_results = max_results
+        self.USER_AGENTS = [
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:122.0) Gecko/20100101 Firefox/122.0",
+            "Mozilla/5.0 (Macintosh; Intel Mac OS X 13_0) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15",
+            "Mozilla/5.0 (Linux; Android 11; Pixel 5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36",
+            "Mozilla/5.0 (iPhone; CPU iPhone OS 16_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.0 Mobile/15E148 Safari/604.1"
+        ]
+        self.kwargs = kwargs
+        self.kwargs.pop('headers', None)
+
+
+    def forward(self, query: str) -> str:
+        headers = {"User-Agent": random.choice(self.USER_AGENTS)}
+        self.ddgs = DDGS(headers=headers, **self.kwargs)
+        time.sleep(2.0)
+        results = self.ddgs.text(query, max_results=self.max_results)
+        if not results:
+            raise Exception("No results found! Try a less restrictive/shorter query.")
+        postprocessed_results = [
+            f"[{result['title']}]({result['href']})\n{result['body']}"
+            for result in results
+        ]
+        return "## Search Results\n\n" + "\n\n".join(postprocessed_results)
+
+class WikipediaSearchTool(Tool):
+    name = "wikipedia_search"
+    description = "Searches Wikipedia and returns a short summary of the most relevant article."
+    inputs = {
+        "query": {"type": "string", "description": "The search term or topic to look up on Wikipedia."}
+    }
+    output_type = "string"
+
+    def __init__(self, summary_sentences=3):
+        super().__init__()
+        self.summary_sentences = summary_sentences
+
+    def forward(self, query: str) -> str:
+        try:
+            page_title = wikipedia.search(query)[0]
+            page = wikipedia.page(page_title)
+            return f"**{page.title}**\n\n{page.content}"
+        except IndexError:
+            return "No Wikipedia results found for that query."
+        except Exception as e:
+            return f"Error during Wikipedia search: {e}"
+
+
+class WebpageReaderTool(Tool):
+    name = "read_webpage"
+    description = "Fetches the text content from a given URL and returns the main body text."
+    inputs = {
+        "url": {"type": "string", "description": "The URL of the webpage to read."}
+    }
+    output_type = "string"
+
+    def forward(self, url: str) -> str:
+        try:
+            headers = {
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
+                              "(KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"
+            }
+            response = requests.get(url, headers=headers, timeout=10)
+            response.raise_for_status()
+
+            soup = BeautifulSoup(response.text, "html.parser")
+
+            # Extract visible text (ignore scripts/styles)
+            for tag in soup(["script", "style", "noscript"]):
+                tag.extract()
+            text = soup.get_text(separator="\n")
+            cleaned = "\n".join(line.strip() for line in text.splitlines() if line.strip())
+
+            return cleaned[:5000]  # Optionally limit to 5,000 chars
+        except Exception as e:
+            return f"Error reading webpage: {e}"