Update app.py

app.py

@@ -1,5 +1,5 @@
 import os
-from typing import List, Optional, Union
+from typing import Optional
 
 import gradio as gr
 import pandas as pd
@@ -7,20 +7,9 @@ from smolagents import CodeAgent, LiteLLMModel, tool
 
 
 # Tool definitions to showcase smolagents capabilities
-@tool
-def search_web(query: str) -> str:
-    """Simulate web search (for demo purposes)"""
-    return f"Simulated web search results for: {query}"
-
 @tool
 def analyze_dataframe(df: pd.DataFrame, analysis_type: str) -> str:
-    """
-    Analyze a pandas DataFrame based on specified analysis type.
-    
-    Args:
-        df: DataFrame to analyze
-        analysis_type: Type of analysis to perform
-    """
+    """Analyze a pandas DataFrame"""
     if analysis_type == "summary":
         return str(df.describe())
     elif analysis_type == "info":
@@ -29,13 +18,7 @@ def analyze_dataframe(df: pd.DataFrame, analysis_type: str) -> str:
 
 @tool
 def plot_data(df: pd.DataFrame, plot_type: str) -> None:
-    """
-    Create plots from DataFrame.
-    
-    Args:
-        df: DataFrame to plot
-        plot_type: Type of plot to create
-    """
+    """Create plots from DataFrame"""
     import matplotlib.pyplot as plt
     import seaborn as sns
     
@@ -47,45 +30,39 @@ def plot_data(df: pd.DataFrame, plot_type: str) -> None:
         df.hist(figsize=(15, 10))
         plt.tight_layout()
 
-def process_files(files: List[gr.File]) -> Optional[pd.DataFrame]:
-    """Process uploaded files into a DataFrame."""
-    if not files:
+def process_file(file: gr.File) -> Optional[pd.DataFrame]:
+    """Process uploaded file into a DataFrame"""
+    if not file:
         return None
         
-    dfs = []
-    for file in files:
-        try:
-            if file.name.endswith('.csv'):
-                df = pd.read_csv(file.name)
-            elif file.name.endswith(('.xlsx', '.xls')):
-                df = pd.read_excel(file.name)
-            else:
-                continue
-            dfs.append(df)
-        except Exception as e:
-            print(f"Error reading {file.name}: {str(e)}")
-            
-    if not dfs:
+    try:
+        if file.name.endswith('.csv'):
+            df = pd.read_csv(file.name)
+        elif file.name.endswith(('.xlsx', '.xls')):
+            df = pd.read_excel(file.name)
+        else:
+            return None
+        return df
+    except Exception as e:
+        print(f"Error reading {file.name}: {str(e)}")
         return None
-        
-    return pd.concat(dfs) if len(dfs) > 1 else dfs[0]
 
 def analyze_data(
-    files: List[gr.File],
+    file: gr.File,
     query: str,
     api_key: str,
     temperature: float = 0.7,
 ) -> str:
-    """Process user request and generate analysis using smolagents."""
+    """Process user request and generate analysis using smolagents"""
     
     if not api_key:
         return "Error: Please provide an API key."
         
-    if not files:
-        return "Error: Please upload at least one file."
+    if not file:
+        return "Error: Please upload a file."
         
     try:
-        # Set up the environment
+        # Set up environment
         os.environ["OPENAI_API_KEY"] = api_key
         
         # Create model and agent
@@ -94,9 +71,9 @@ def analyze_data(
             temperature=temperature
         )
         
-        # Create agent with various tools to showcase capabilities
+        # Create agent with various tools
         agent = CodeAgent(
-            tools=[search_web, analyze_dataframe, plot_data],
+            tools=[analyze_dataframe, plot_data],
             model=model,
             additional_authorized_imports=[
                 "pandas",
@@ -111,20 +88,19 @@ def analyze_data(
             verbosity_level=1
         )
         
-        # Process uploaded files
-        df = process_files(files)
+        # Process uploaded file
+        df = process_file(file)
         if df is None:
-            return "Error: Could not process uploaded files."
+            return "Error: Could not process uploaded file."
         
         # Build context
-        file_info = "\n".join([
-            "Uploaded files:",
-            *[f"- {f.name}" for f in files],
-            f"\nDataFrame Shape: {df.shape}",
-            f"Columns: {', '.join(df.columns)}",
-            "\nColumn Types:",
-            *[f"- {col}: {dtype}" for col, dtype in df.dtypes.items()]
-        ])
+        file_info = f"""
+        Uploaded file: {file.name}
+        DataFrame Shape: {df.shape}
+        Columns: {', '.join(df.columns)}
+        Column Types:
+        {chr(10).join([f'- {col}: {dtype}' for col, dtype in df.dtypes.items()])}
+        """
         
         # Build prompt
         prompt = f"""
@@ -132,7 +108,6 @@ def analyze_data(
 
         The data has been loaded into a pandas DataFrame called 'df'.
         Available tools:
-        - search_web: Search for relevant information
         - analyze_dataframe: Perform basic DataFrame analysis
         - plot_data: Create various plots
         
@@ -148,8 +123,6 @@ def analyze_data(
         2. Code for the analysis
         3. Visualizations where relevant
         4. Key insights and findings
-        
-        Make use of the available tools and libraries to provide comprehensive analysis.
         """
         
         # Run analysis
@@ -160,7 +133,7 @@ def analyze_data(
         return f"Error occurred: {str(e)}"
 
 def create_interface():
-    """Create Gradio interface."""
+    """Create Gradio interface"""
     
     with gr.Blocks(title="AI Agent Testing Interface") as interface:
         gr.Markdown("""
@@ -171,7 +144,6 @@ def create_interface():
         **Features:**
         - Data analysis and visualization
         - Machine learning capabilities
-        - Web search simulation
         - Statistical analysis
         - Custom tool integration
         
@@ -181,7 +153,7 @@ def create_interface():
         with gr.Row():
             with gr.Column():
                 file = gr.File(
-                    label="Upload Data Files (CSV/Excel)",
+                    label="Upload Data File (CSV/Excel)",
                     file_types=[".csv", ".xlsx", ".xls"]
                 )
                 query = gr.Textbox(
@@ -221,7 +193,6 @@ def create_interface():
                 [None, "Identify and analyze outliers in the dataset"],
                 [None, "Perform clustering analysis and visualize the results"],
                 [None, "Calculate summary statistics and create box plots for numeric columns"],
-                [None, "Analyze trends and patterns in the data over time"],
             ],
             inputs=[file, query]
         )