Update app.py

app.py

@@ -8,6 +8,22 @@ import tempfile
 from smolagents import CodeAgent, OpenAIServerModel, tool
 from dotenv import load_dotenv
 from openai import OpenAI
+from markdownify import markdownify
+from requests.exceptions import RequestException
+
+from typing import Optional, List
+from langchain_core.tools import BaseTool, tool
+from langchain_community.tools import DuckDuckGoSearchResults
+from langchain_experimental.tools import PythonREPLTool
+import requests
+from bs4 import BeautifulSoup
+import markdownify
+import pandas as pd
+from io import BytesIO
+#import pytesseract
+from PIL import Image
+from youtube_transcript_api import YouTubeTranscriptApi
+import re
 
 # Load environment variables
 load_dotenv()
@@ -26,62 +42,18 @@ model = OpenAIServerModel(
 openAiClient = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
 @tool
-def VisitWebpageTool(Tool):
-    name = "visit_webpage"
-    description = (
-        "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages."
-    )
-    inputs = {
-        "url": {
-            "type": "string",
-            "description": "The url of the webpage to visit.",
-        }
-    }
-    output_type = "string"
-
-    def __init__(self, max_output_length: int = 40000):
-        super().__init__()
-        self.max_output_length = max_output_length
-
-    def _truncate_content(self, content: str, max_length: int) -> str:
-        if len(content) <= max_length:
-            return content
-        return (
-            content[: max_length // 2]
-            + f"\n..._This content has been truncated to stay below {max_length} characters_...\n"
-            + content[-max_length // 2 :]
-        )
-
-    def forward(self, url: str) -> str:
-        try:
-            import re
-
-            import requests
-            from markdownify import markdownify
-            from requests.exceptions import RequestException
-        except ImportError as e:
-            raise ImportError(
-                "You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
-            ) from e
-        try:
-            # Send a GET request to the URL with a 20-second timeout
-            response = requests.get(url, timeout=20)
-            response.raise_for_status()  # Raise an exception for bad status codes
-
-            # Convert the HTML content to Markdown
-            markdown_content = markdownify(response.text).strip()
-
-            # Remove multiple line breaks
-            markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
-
-            return self._truncate_content(markdown_content, self.max_output_length)
-
-        except requests.exceptions.Timeout:
-            return "The request timed out. Please try again later or check the URL."
-        except RequestException as e:
-            return f"Error fetching the webpage: {str(e)}"
-        except Exception as e:
-            return f"An unexpected error occurred: {str(e)}"
+def arvix_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"arvix_results": formatted_search_docs}
             
 
 @tool
@@ -370,7 +342,13 @@ class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
         # Reuse a single CodeAgent instance for all queries
-        self.agent = CodeAgent(tools=[tavily_search, analyze_image, analyze_sound, analyze_excel, analyze_text, transcribe_youtube, process_file], model=model)
+        self.agent = CodeAgent(tools=[arvix_search,
+                                      analyze_image, 
+                                      analyze_sound, 
+                                      analyze_excel, 
+                                      analyze_text, 
+                                      transcribe_youtube, 
+                                      process_file], model=model)
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")