Update app.py

app.py

@@ -18,6 +18,11 @@ final_answer = FinalAnswerTool()
 wikipedia_search= WikipediaSearchTool()
 python_code_executor=PythonInterpreterTool()
 
+image_captioner = pipeline(
+    "image-to-text",
+    model="Salesforce/blip-image-captioning-base"
+    )
+
 
 @tool
 def describe_image(path: str) -> str:
@@ -25,10 +30,6 @@ def describe_image(path: str) -> str:
     Args:
         path: Path to the image file to analyze.
     """
-    image_captioner = pipeline(
-    "image-to-text",
-    model="Salesforce/blip-image-captioning-base"
-    )
     return image_captioner(path)[0]["generated_text"]
 
 @tool    
@@ -38,16 +39,16 @@ def audio_to_text_tool(audio_file_path:str) -> str:
         audio_file_path: path of audio data file
     """
     output = SpeechToTextTool()
-    return output 
+    return output(audio_file_path) 
     
 @tool
-def excel_reader(file_path):
-    """ reads an excel file. Requires the file path as input. Return rows and columns of a data frame.
+def excel_reader(file_path:str) -> str:
+    """ reads an excel file. Requires the file path as input. Return information on rows and columns.
     Args:
         file_path: file path as input
     """
     df= pd.read_excel(file_path)
-    return (df.rows, df.columns)
+    return f"Rows: {len(df)}, Columns: {list(df.columns)}"
 
 class BasicAgent:
     def __init__(self):