add tools

requirements.txt

@@ -11,4 +11,4 @@ pandas
 Pillow
 pydub
 tavily-python
-wikipedia
+wikipedia

tools.py

@@ -1,8 +1,13 @@
 import os
 import random
+import requests
+import tempfile
+import re
 
 from typing import Dict
 from pathlib import Path
+from markitdown import MarkItDown
+from urllib.parse import urlparse
 
 from langchain_core.tools import tool
 
@@ -138,14 +143,53 @@ def convert_units(value: float, from_unit: str, to_unit: str) -> float:
 
     return conversions[key](value)
 
+
+def convert_query_to_pandas_syntax(natural_query: str, column_names: list) -> str:
+    """
+    Converts a natural language query to pandas query syntax using basic heuristics.
+    
+    Args:
+        natural_query: A string with a question or filter expression in plain English.
+        column_names: List of column names from the DataFrame.
+
+    Returns:
+        A best-effort string in pandas query() format.
+    """
+    # Preprocess query
+    query = natural_query.lower().strip()
+
+    # Heuristic rules
+    rules = [
+        (r"(\w+) greater than (\d+)", r"\1 > \2"),
+        (r"(\w+) less than (\d+)", r"\1 < \2"),
+        (r"(\w+) equal to ['\"]?([\w\s]+)['\"]?", r"\1 == '\2'"),
+        (r"(\w+) not equal to ['\"]?([\w\s]+)['\"]?", r"\1 != '\2'"),
+        (r"(\w+) more than (\d+)", r"\1 > \2"),
+        (r"(\w+) less than or equal to (\d+)", r"\1 <= \2"),
+        (r"(\w+) greater than or equal to (\d+)", r"\1 >= \2"),
+        (r"(\w+) is ['\"]?([\w\s]+)['\"]?", r"\1 == '\2'"),
+    ]
+
+    for pattern, replacement in rules:
+        if re.search(pattern, query):
+            query = re.sub(pattern, replacement, query)
+            break
+
+    # Handle AND/OR logic
+    query = query.replace(" and ", " and ")
+    query = query.replace(" or ", " or ")
+
+    return query
+
+
 @tool
-def query_table_data(file_path: str, query: str, sheet_name: str = None) -> str:
+def query_table_data(file_path: str, query_pandas_syntax: str, sheet_name: str = None) -> str:
     """
     Loads a table from CSV or Excel and filters it using a pandas query.
 
     Args:
         file_path: Path to the table file (.xlsx, .xls).
-        query: A pandas-compatible query string, e.g., "Age > 30 and Country == 'USA'".
+        query_pandas_syntax: A pandas-compatible query string, e.g., "Age > 30 and Country == 'USA'".
         sheet_name: Optional sheet name if the file is Excel.
 
     Returns:
@@ -164,10 +208,10 @@ def query_table_data(file_path: str, query: str, sheet_name: str = None) -> str:
         else:
            raise ValueError(f"Unsupported file extension: {ext}")
         try:
-           filtered_df = df.query(query)
+           filtered_df = df.query(query_pandas_syntax)
            return filtered_df.head(10).to_markdown(index=False)
         except Exception as e:
-           raise ValueError(f"Invalid query: {query}. Error: {e}")
+           raise ValueError(f"Invalid query: {query_pandas_syntax}. Error: {e}")
     except ImportError:
         return "Error: pandas and openpyxl are not installed. Please install them with 'pip install pandas openpyxl'."
     
@@ -189,6 +233,98 @@ def arvix_search(query: str) -> str:
     return {"arvix_results": formatted_search_docs}
 
 
+@tool
+def read_python_file(file_path: str) -> str:
+    """
+    Reads and parses an Python file to markdown.
+    Args:
+        file_path: Path to the Python file
+    Returns:
+       Python file content.
+    """
+
+    try:
+        # Just with markitdown
+        path = Path(file_path)
+        if not path.exists():
+           raise FileNotFoundError(f"File not found: {file_path}")
+        ext = path.suffix.lower()
+        if ext == ".py":
+           md = MarkItDown(enable_plugins=True)
+           result = md.convert(file_path)
+           return result.text_content
+        else:
+           raise ValueError(f"Unsupported file extension: {ext}")
+    except Exception as err:
+        raise type(err)(f"Could not parse python file > {err}")
+
+
+@tool
+def save_and_read_file(content: str, filename: str = None) -> str:
+    """
+    Save content to a temporary file and return the path.
+    Useful for processing files from the GAIA API.
+    
+    Args:
+        content: The content to save to the file
+        filename: Optional filename, will generate a random name if not provided
+        
+    Returns:
+        Path to the saved file
+    """
+    temp_dir = tempfile.gettempdir()
+    if filename is None:
+        temp_file = tempfile.NamedTemporaryFile(delete=False)
+        filepath = temp_file.name
+    else:
+        filepath = os.path.join(temp_dir, filename)
+    
+    # Write content to the file
+    with open(filepath, 'w') as f:
+        f.write(content)
+    
+    return f"File saved to {filepath}. You can read this file to process its contents."
+
+
+
+def download_file_from_url(url: str, filename: str) -> str:
+    """
+    Download a file from a URL and save it to a temporary location.
+    Args:
+        url: The URL to download from
+        filename: filename
+    Returns:
+        Path to the downloaded file
+    """
+    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
+
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+
+        # Download the file
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+
+        # Save the file
+        with open(filepath, "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."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"
+
+
 level1_tools = [
     multiply,
     add,
@@ -199,5 +335,9 @@ level1_tools = [
     web_search,
     arvix_search,
     convert_units,
-    query_table_data
+    convert_query_to_pandas_syntax,
+    query_table_data,
+    download_file_from_url,
+    save_and_read_file,
+    read_python_file
 ]