Update app.py

app.py

@@ -1,103 +1,130 @@
 import streamlit as st
+import pandas as pd
+import io
+from utils import query_agent, detect_delimiter
 from dotenv import load_dotenv
 import os
-from utils import query_agent
-import io
 
-# Load environment variables (like HUGGINGFACEHUB_API_TOKEN) from .env
+# Set Streamlit page configuration
+st.set_page_config(
+    page_title="HF Data Analyst Agent",
+    page_icon="📊",
+    layout="centered"
+)
+
+# Load environment variables
 load_dotenv()
+# Retrieve API Token from .env or environment variables
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 
-def display_data_preview(uploaded_file_bytes):
-    """Utility function to display a preview of the uploaded data."""
-    try:
-        # Use utils' logic to detect delimiter
-        from utils import detect_csv_delimiter
-        delimiter = detect_csv_delimiter(uploaded_file_bytes)
-        
-        # Reset stream and load for preview
-        uploaded_file_bytes.seek(0)
-        df_preview = pd.read_csv(uploaded_file_bytes, sep=delimiter, nrows=5)
-        
-        st.subheader("Data Preview (First 5 Rows)")
-        st.dataframe(df_preview, use_container_width=True)
-        st.caption(f"File loaded using detected delimiter: `{delimiter}`")
+# --- Custom Styling (Tailwind-like aesthetic using Streamlit's style) ---
+st.markdown("""
+<style>
+.main-header {
+    font-size: 2.5em;
+    font-weight: 700;
+    color: #4B0082; /* Deep Purple */
+    text-align: center;
+    margin-bottom: 0.5em;
+}
+.stButton>button {
+    background-color: #6A5ACD; /* Slate Blue */
+    color: white;
+    border-radius: 12px;
+    border: 2px solid #483D8B;
+    padding: 10px 20px;
+    font-size: 16px;
+    transition: all 0.3s ease;
+}
+.stButton>button:hover {
+    background-color: #483D8B; /* Darker Blue */
+    color: #E0FFFF;
+    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.2);
+}
+.uploaded-file-details {
+    margin-top: 15px;
+    padding: 15px;
+    border: 1px solid #DDA0DD; /* Plum */
+    border-radius: 10px;
+    background-color: #F8F8FF; /* Ghost White */
+}
+.analysis-input-box {
+    margin-top: 20px;
+    padding: 20px;
+    border: 2px solid #7B68EE; /* Medium Slate Blue */
+    border-radius: 15px;
+    background-color: #E6E6FA; /* Lavender */
+}
+</style>
+""", unsafe_allow_html=True)
 
-        # Reset stream position again for the main agent function
-        uploaded_file_bytes.seek(0)
-        return True
-    except Exception as e:
-        st.error(f"Failed to read or preview the CSV file. Please ensure it is a valid CSV format. Error: {e}")
-        return False
 
-# --- Main Streamlit Application ---
-def main():
-    """Main function to run the Streamlit application."""
-    st.set_page_config(
-        page_title="NL Data Analyst (LLM Powered)",
-        layout="wide",
-        initial_sidebar_state="expanded"
-    )
+# --- Application Title and Setup ---
 
-    st.title("📊 Natural Language Data Analyst")
-    st.markdown("Upload a CSV file and ask questions about your data using plain English.")
-    
-    # Check for API key presence
-    if not os.getenv("HUGGINGFACEHUB_API_TOKEN"):
-        st.error("🚨 HUGGINGFACEHUB_API_TOKEN not found. Please ensure your `.env` file is set up correctly.")
-        return
+st.markdown('<div class="main-header">📊 AI Data Analyst powered by Mistral (HF)</div>', unsafe_allow_html=True)
+st.markdown(
+    """
+    Upload a CSV file and ask natural language questions about your data. 
+    This application uses the **Mistral-7B-Instruct-v0.2** model via the Hugging Face Inference Endpoint for fast, accurate analysis.
+    """,
+    unsafe_allow_html=True
+)
+
+if not HUGGINGFACEHUB_API_TOKEN or HUGGINGFACEHUB_API_TOKEN == "YOUR_HUGGINGFACE_TOKEN_HERE":
+    st.error("⚠️ **API Token Missing!** Please set your `HUGGINGFACEHUB_API_TOKEN` in the `.env` file or as a secret in your Hugging Face Space.")
+else:
+    # --- File Uploader ---
+    uploaded_file = st.file_uploader(
+        "Upload your CSV file", 
+        type=["csv"],
+        accept_multiple_files=False,
+        help="Upload a CSV file. The app automatically detects delimiters (like comma, semicolon, etc.)."
+    )
 
-    # --- Sidebar for File Upload ---
-    with st.sidebar:
-        st.header("1. Upload CSV File")
-        uploaded_file = st.file_uploader(
-            "Choose a CSV file",
-            type=["csv"],
-            help="The app automatically detects the delimiter (comma, semicolon, etc.)."
-        )
-        
-        st.markdown("---")
-        st.subheader("2. Example Queries")
-        st.info(
-            """
-            - What is the average value of the 'Sales' column?
-            - Show me the top 5 highest 'Profit' rows.
-            - How many unique values are there in 'Customer Name'?
-            - Plot a histogram of the 'Age' column.
-            """
-        )
-    
-    # --- Main Content Area ---
     if uploaded_file is not None:
-        # Convert uploaded file to BytesIO object for multiple reads
-        uploaded_file_bytes = io.BytesIO(uploaded_file.getvalue())
+        # Read the file content into bytes
+        file_content_bytes = uploaded_file.getvalue()
 
-        # Display file preview
-        if not display_data_preview(uploaded_file_bytes):
-            return # Stop execution if preview fails
+        st.markdown('<div class="uploaded-file-details">', unsafe_allow_html=True)
+        st.subheader("Data Preview (First 5 Rows)")
+        
+        try:
+            delimiter = detect_delimiter(file_content_bytes)
+            
+            # Read the DataFrame just for display
+            data_io = io.StringIO(file_content_bytes.decode('utf-8'))
+            df_preview = pd.read_csv(data_io, sep=delimiter)
+            
+            st.dataframe(df_preview.head())
+            st.write(f"Detected Delimiter: `{delimiter}`")
+            st.write(f"Shape: {df_preview.shape[0]} rows, {df_preview.shape[1]} columns")
 
-        st.subheader("3. Ask Your Data Question")
-        user_query = st.text_input(
-            "Enter your query here (e.g., 'What is the sum of the Price column?'):",
-            key="user_input_query",
-            placeholder="E.g., What is the average customer age?"
-        )
+            # --- Analysis Input Box ---
+            st.markdown('</div>', unsafe_allow_html=True)
+            st.markdown('<div class="analysis-input-box">', unsafe_allow_html=True)
+            
+            st.subheader("Ask a question about the data")
+            query = st.text_input(
+                "Enter your question here:",
+                placeholder="e.g., What is the average value of the 'Age' column?",
+                key="user_query"
+            )
 
-        if user_query:
-            with st.spinner("🤖 Analyzing data with LangChain Agent..."):
-                try:
-                    # Call the core analysis function
-                    result = query_agent(uploaded_file_bytes, user_query)
+            # --- Analysis Execution ---
+            if st.button("Run Analysis", key="run_analysis_button") and query:
+                with st.spinner("Analyzing data... The Mistral Agent is working hard!"):
+                    # Pass the Hugging Face API token to the agent function
+                    response = query_agent(file_content_bytes, query, HUGGINGFACEHUB_API_TOKEN)
                     
                     st.success("Analysis Complete!")
-                    st.markdown("### Answer")
-                    st.write(result)
-                    
-                except Exception as e:
-                    st.error(f"An unexpected error occurred: {e}")
+                    st.markdown("---")
+                    st.subheader("Agent Response")
+                    st.markdown(f"**{response}**")
+            
+            elif st.button("Run Analysis", key="run_analysis_button_disabled") and not query:
+                st.warning("Please enter a question to analyze the data.")
 
-    else:
-        st.info("Please upload a CSV file in the sidebar to begin the data analysis.")
+            st.markdown('</div>', unsafe_allow_html=True)
 
-if __name__ == "__main__":
-    import pandas as pd
-    main()
+        except Exception as e:
+            st.error(f"Could not process the uploaded file or generate preview. Error: {e}")