Update tools

tools_audio.py

@@ -1,4 +1,6 @@
 # Audio Transcription Tool
+import os
+
 from google import genai
 from google.genai import types
 from langchain_core.tools import tool

tools_doc.py

@@ -1,11 +1,13 @@
 import os
+import re
 import requests
 import tempfile
+import uuid
 
 from langchain_core.tools import tool
 
 # from smolagents import tool
-from typing import Optional
+from typing import Optional, Dict, Union
 from urllib.parse import urlparse
 
 
@@ -36,45 +38,79 @@ def save_and_read_file(content: str, filename: Optional[str] = None) -> str:
     return f"File saved to {filepath}. You can read this file to process its contents."
 
 
+# File Download Tool
 @tool
-def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
-    """
-    Download a file from a URL and save it to a temporary location.
-
+def download_file_from_url(
+    url: str, directory: str
+) -> Dict[str, Union[str, None]]:
+    """Downloads a file from a URL and saves it to a directory.
     Args:
-        url: The URL to download from
-        filename: Optional filename, will generate one based on URL if not provided
-
+        url (str): the URL to download the file from.
+        directory (str): the directory to save the file to.
     Returns:
-        Path to the downloaded file
+        Dict[str, Union[str, None]]: A dictionary containing the file type and path.
     """
+
     try:
-        # Parse URL to get filename if not provided
-        if not filename:
-            path = urlparse(url).path
-            filename = os.path.basename(path)
-            if not filename:
-                # Generate a random name if we couldn't extract one
-                import uuid
+        response = requests.get(url, stream=True, timeout=10)
+        response.raise_for_status()
 
-                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+        content_type = response.headers.get("content-type", "").lower()
 
-        # Create temporary file
-        temp_dir = tempfile.gettempdir()
-        filepath = os.path.join(temp_dir, filename)
+        # Try to get filename from headers
+        filename = None
+        cd = response.headers.get("content-disposition", "")
+        match = re.search(r"filename\*=UTF-8\'\'(.+)", cd) or re.search(
+            r'filename="?([^"]+)"?', cd
+        )
+        if match:
+            filename = match.group(1)
 
-        # Download the file
-        response = requests.get(url, stream=True)
-        response.raise_for_status()
+        # If not in headers, try URL
+        if not filename:
+            filename = os.path.basename(url.split("?")[0])
 
-        # Save the file
-        with open(filepath, "wb") as f:
+        # Fallback to generated filename
+        if not filename:
+            extension = {
+                "image/jpeg": ".jpg",
+                "image/png": ".png",
+                "image/gif": ".gif",
+                "audio/wav": ".wav",
+                "audio/mpeg": ".mp3",
+                "video/mp4": ".mp4",
+                "text/plain": ".txt",
+                "text/csv": ".csv",
+                "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+                "application/vnd.ms-excel": ".xls",
+                "application/octet-stream": ".bin",
+            }.get(content_type, ".bin")
+            filename = f"downloaded_{uuid.uuid4().hex[:8]}{extension}"
+
+        os.makedirs(directory, exist_ok=True)
+        file_path = os.path.join(directory, filename)
+
+        with open(file_path, "wb") as f:
             for chunk in response.iter_content(chunk_size=8192):
                 f.write(chunk)
 
-        return f"File downloaded to {filepath}. You can now process this file."
+        # shutil.copy(file_path, os.getcwd())
+
+        if os.path.exists(file_path) and os.path.getsize(file_path) > 0:
+            return {"type": content_type, "path": file_path}
+        else:
+            return {
+                "type": "error",
+                "path": None,
+                "error": "Failed to save file",
+            }
+
     except Exception as e:
-        return f"Error downloading file: {str(e)}"
+        return {
+            "type": "error",
+            "path": None,
+            "error": f"Error downloading file: {str(e)}",
+        }
 
 
 @tool

tools_video.py

@@ -1,6 +1,7 @@
 import imageio
 import os
 import re
+import tempfile
 import yt_dlp
 
 from datetime import timedelta