minor code restructuration

custom_tools.py

@@ -1,4 +1,4 @@
-from utils import download_file, read_file, download_yt_video, extract_frames, encode_image, analyze_frame, generate_prompt_for_video_frame_analysis, get_response_from_frames_analysis, transcript_audio_file
+from utils import download_file, read_file, sum_pandas_df_cols, download_yt_video, extract_frames, encode_image, analyze_frame, generate_prompt_for_video_frame_analysis, get_response_from_frames_analysis, transcript_audio_file
 
 import os
 import requests
@@ -125,7 +125,7 @@ def add_numbers(numbers_list: List[float]) -> Union[float, str]:
 
 
 @tool
-def sum_pandas_df(task_id: str, file_name: str, column_names: List[str]) -> float:
+def sum_excel_cols(task_id: str, file_name: str, column_names: List[str]) -> float:
     """
     Sum the values of specified columns in a pandas DataFrame read from an Excel file.
 
@@ -138,53 +138,25 @@ def sum_pandas_df(task_id: str, file_name: str, column_names: List[str]) -> floa
         float: The sum of the specified columns.
 
     Example:
-        sum_pandas_df("task123", "data.xlsx", ["Column1", "Column2"]) -> 100.0
+        sum_excel_cols("task123", "data.xlsx", ["Column1", "Column2"]) -> 100.0
     """
-    try:
-        download_file(task_id, file_name)
-    except Exception as e:
-        return f"Error downloading file: {e}"
+    file_status = download_file(task_id, file_name)
 
     if not os.path.exists(file_name):
         return f"File {file_name} does not exist."
 
-    try:
-        extension = os.path.splitext(file_name)[1].lower()
-    except Exception as e:
-        return f"Error parsing file extension: {e}"
+    extension = os.path.splitext(file_name)[1].lower()
 
     if extension not in ['.csv', '.xlsx']:
         return "Unsupported file format. Please provide a CSV or XLSX file."
 
-    try:
-        if extension == '.csv':
-            df = pd.read_csv(file_name)
-        elif extension == '.xlsx':
-            df = pd.read_excel(file_name)
-        else:
-            return "Unsupported file format. Please provide a CSV or XLSX file."
-    except FileNotFoundError:
-        return f"File {file_name} not found."
-    except pd.errors.EmptyDataError:
-        return "The file is empty."
-    except Exception as e:
-        return f"Error reading file: {e}"
-
-    if df.empty:
-        return "The DataFrame is empty."
-
-    if not isinstance(column_names, list):
-        return "column_names should be a list of column names."
-
-    if not column_names:
-        return "No columns specified to sum."
-
-    missing_columns = [col for col in column_names if col not in df.columns]
-    if missing_columns:
-        return f"The following columns do not exist in the DataFrame: {missing_columns}"
+    if extension == '.csv':
+        df = pd.read_csv(file_name)
+    elif extension == '.xlsx':
+        df = pd.read_excel(file_name)
 
     try:
-        total_sum = df[column_names].sum().sum()
+        total_sum = sum_pandas_df_cols(df, column_names)
         return total_sum
     except Exception as e:
         return f"Error summing columns: {e}"
@@ -353,7 +325,7 @@ custom_tools = [
     wiki_search,
     DuckDuckGoSearchResults(),
     # add_numbers,
-    sum_pandas_df,
+    sum_excel_cols,
     youtube_transcript,
     analyse_youtube_video,
     analyze_image,

utils.py

@@ -99,6 +99,9 @@ def read_file(file_name: str) -> str:
         return f"Permission denied: Unable to access the file at {file_name}."
     except Exception as e:
         return f"An unexpected error occurred: {e}"
+    
+def sum_pandas_df_cols(df: pd.DataFrame, cols: list):
+    return df[cols].sum().sum()
         
 def download_yt_video(url: str) -> str:
     """