Redesign UI for cleaner academic interface and remove pandasai dependency

Major UI improvements:
- Set DeepSeek-R1 as default model
- Remove all decorative emojis for academic look
- Redesign header with logo, subtitle, and model selector
- Clean sidebar with dataset info and quick queries
- Improve message styling with better alignment and spacing
- Add collapsible code containers with clean styling

Technical improvements:
- Remove unused pandasai dependency and functions
- Clean up imports and unused code
- Add CLAUDE.md documentation for future development

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

CLAUDE.md

@@ -0,0 +1,87 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+VayuChat is a Streamlit-based conversational AI application for air quality data analysis. It provides an interactive chat interface where users can ask questions about PM2.5 and PM10 pollution data through natural language, and receive responses including visualizations and data insights.
+
+## Architecture
+
+The application follows a two-file architecture:
+
+- **app.py**: Main Streamlit application with UI components, chat interface, and user interaction handling
+- **src.py**: Core data processing logic, LLM integration, and code generation/execution engine
+
+Key architectural patterns:
+- **Code Generation Pipeline**: User questions are converted to executable Python code via LLM prompting, then executed dynamically
+- **Multi-LLM Support**: Supports both Groq (LLaMA models) and Google Gemini models through LangChain
+- **Session Management**: Uses Streamlit session state for chat history and user interactions
+- **Feedback Loop**: Comprehensive logging and feedback collection to HuggingFace datasets
+
+## Development Commands
+
+### Run the Application
+```bash
+streamlit run app.py
+```
+
+### Install Dependencies
+```bash
+pip install -r requirements.txt
+```
+
+### Environment Setup
+Create a `.env` file with the following variables:
+```bash
+GROQ_API_KEY=your_groq_api_key_here
+GEMINI_TOKEN=your_google_gemini_api_key_here
+HF_TOKEN=your_huggingface_token_here  # Optional, for logging
+```
+
+## Data Requirements
+
+- **Data.csv**: Must contain columns: `Timestamp`, `station`, `PM2.5`, `PM10`, `address`, `city`, `latitude`, `longitude`, `state`
+- **IITGN_Logo.png**: Logo image for the sidebar
+- **questions.txt**: Pre-defined quick prompt questions (optional)
+- **system_prompt.txt**: Contains specific instructions for the LLM code generation
+
+## Code Generation System
+
+The application uses a unique code generation approach in `src.py`:
+
+1. **Template-based Code Generation**: User questions are embedded into a Python code template that includes data loading and analysis patterns
+2. **Dynamic Execution**: Generated code is executed in a controlled environment with pandas, matplotlib, and other libraries available
+3. **Result Handling**: Results are stored in an `answer` variable and can be either text/numbers or plot file paths
+4. **Error Recovery**: Comprehensive error handling with logging to HuggingFace datasets
+
+## Key Functions (src.py)
+
+- `ask_question()`: Main entry point for processing user queries
+- `preprocess_and_load_df()`: Data loading and preprocessing
+- `load_agent()` / `load_smart_df()`: LLM agent initialization
+- `log_interaction()`: Interaction logging to HuggingFace
+- `upload_feedback()`: User feedback collection (in app.py)
+
+## Model Configuration
+
+Available models are defined in both files:
+- Groq models: LLaMA 3.1, LLaMA 3.3, LLaMA 4 variants, DeepSeek-R1, GPT-OSS
+- Google models: Gemini 1.5 Pro
+
+## Plotting Guidelines
+
+When generating visualization code, the system follows specific guidelines from `system_prompt.txt`:
+- Include India (60 µg/m³) and WHO (15 µg/m³) guidelines for PM2.5
+- Include India (100 µg/m³) and WHO (50 µg/m³) guidelines for PM10
+- Use tight layout and 45-degree rotated x-axis labels
+- Save plots with unique filenames using UUID
+- Use 'Reds' colormap for air quality visualizations
+- Round floating point numbers to 2 decimal places
+- Always report units (µg/m³) and include standard deviation/error for aggregations
+
+## Logging and Feedback
+
+- All interactions are logged to `SustainabilityLabIITGN/VayuChat_logs` HuggingFace dataset
+- User feedback is collected and stored in `SustainabilityLabIITGN/VayuChat_Feedback` dataset
+- Session tracking via UUID for analytics

app.py

@@ -7,12 +7,7 @@ from os.path import join
 from datetime import datetime
 from src import (
     preprocess_and_load_df,
-    load_agent,
-    ask_agent,
-    decorate_with_code,
-    show_response,
     get_from_user,
-    load_smart_df,
     ask_question,
 )
 from dotenv import load_dotenv
@@ -28,7 +23,7 @@ import uuid
 # Page config with beautiful theme
 st.set_page_config(
     page_title="VayuChat - AI Air Quality Assistant",
-    page_icon="🌬️",
+    page_icon="V",
     layout="wide",
     initial_sidebar_state="expanded"
 )
@@ -109,42 +104,41 @@ st.markdown("""
 
 /* User message styling */
 .user-message {
-    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+    background: #3b82f6;
     color: white;
-    padding: 15px 20px;
-    border-radius: 20px 20px 5px 20px;
-    margin: 10px 0;
+    padding: 1rem 1.5rem;
+    border-radius: 12px;
+    margin: 2rem 0;
     margin-left: auto;
     margin-right: 0;
-    max-width: 80%;
-    position: relative;
-    box-shadow: 0 2px 10px rgba(0,0,0,0.1);
+    max-width: 70%;
+    display: flex;
+    justify-content: flex-end;
 }
 
 .user-info {
-    font-size: 0.8rem;
-    opacity: 0.8;
+    font-size: 0.875rem;
+    opacity: 0.9;
     margin-bottom: 5px;
-    text-align: right;
 }
 
 /* Assistant message styling */
 .assistant-message {
-    background: linear-gradient(135deg, #f093fb 0%, #f5576c 100%);
-    color: white;
-    padding: 15px 20px;
-    border-radius: 20px 20px 20px 5px;
-    margin: 10px 0;
+    background: #f1f5f9;
+    color: #334155;
+    padding: 1rem 1.5rem;
+    border-radius: 12px;
+    margin: 2rem 0;
     margin-left: 0;
     margin-right: auto;
-    max-width: 80%;
-    position: relative;
-    box-shadow: 0 2px 10px rgba(0,0,0,0.1);
+    max-width: 70%;
+    display: flex;
+    justify-content: flex-start;
 }
 
 .assistant-info {
-    font-size: 0.8rem;
-    opacity: 0.8;
+    font-size: 0.875rem;
+    color: #6b7280;
     margin-bottom: 5px;
 }
 
@@ -217,13 +211,80 @@ st.markdown("""
     background-color: #0b5ed7;
 }
 
-/* Code details styling */
-.code-details {
-    background-color: #f8f9fa;
-    border: 1px solid #dee2e6;
+/* Code container styling */
+.code-container {
+    margin: 1rem 0;
+    border: 1px solid #e2e8f0;
     border-radius: 8px;
-    padding: 10px;
-    margin-top: 10px;
+    background: #f8fafc;
+}
+
+.code-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    padding: 0.75rem 1rem;
+    background: #f1f5f9;
+    border-bottom: 1px solid #e2e8f0;
+    cursor: pointer;
+    transition: background-color 0.2s;
+}
+
+.code-header:hover {
+    background: #e2e8f0;
+}
+
+.code-title {
+    font-size: 0.875rem;
+    font-weight: 500;
+    color: #374151;
+}
+
+.toggle-text {
+    font-size: 0.75rem;
+    color: #6b7280;
+}
+
+.code-block {
+    background: #1e293b;
+    color: #e2e8f0;
+    padding: 1rem;
+    font-family: 'Monaco', 'Menlo', monospace;
+    font-size: 0.875rem;
+    overflow-x: auto;
+    line-height: 1.5;
+}
+
+.answer-container {
+    background: #f8fafc;
+    border: 1px solid #e2e8f0;
+    border-radius: 8px;
+    padding: 1.5rem;
+    margin: 1rem 0;
+}
+
+.answer-text {
+    font-size: 1.125rem;
+    color: #1e293b;
+    line-height: 1.6;
+    margin-bottom: 1rem;
+}
+
+.answer-highlight {
+    background: #fef3c7;
+    padding: 0.125rem 0.375rem;
+    border-radius: 4px;
+    font-weight: 600;
+    color: #92400e;
+}
+
+.context-info {
+    background: #f1f5f9;
+    border-left: 4px solid #3b82f6;
+    padding: 0.75rem 1rem;
+    margin: 1rem 0;
+    font-size: 0.875rem;
+    color: #475569;
 }
 
 /* Hide default menu and footer */
@@ -239,7 +300,7 @@ header {visibility: hidden;}
 </style>
 """, unsafe_allow_html=True)
 
-# Auto-scroll JavaScript
+# JavaScript for interactions
 st.markdown("""
 <script>
 function scrollToBottom() {
@@ -251,6 +312,19 @@ function scrollToBottom() {
         window.scrollTo(0, document.body.scrollHeight);
     }, 100);
 }
+
+function toggleCode(header) {
+    const codeBlock = header.nextElementSibling;
+    const toggleText = header.querySelector('.toggle-text');
+    
+    if (codeBlock.style.display === 'none') {
+        codeBlock.style.display = 'block';
+        toggleText.textContent = 'Click to collapse';
+    } else {
+        codeBlock.style.display = 'none';
+        toggleText.textContent = 'Click to expand';
+    }
+}
 </script>
 """, unsafe_allow_html=True)
 
@@ -283,7 +357,7 @@ def upload_feedback(feedback, error, output, last_prompt, code, status):
     """Enhanced feedback upload function with better logging and error handling"""
     try:
         if not hf_token or hf_token.strip() == "":
-            st.warning("⚠️ Cannot upload feedback - HF_TOKEN not available")
+            st.warning("Cannot upload feedback - HF_TOKEN not available")
             return False
 
         # Create comprehensive feedback data
@@ -368,187 +442,160 @@ def upload_feedback(feedback, error, output, last_prompt, code, status):
         if os.path.exists(markdown_local_path):
             os.remove(markdown_local_path)
         
-        st.success("🎉 Feedback uploaded successfully!")
+        st.success("Feedback uploaded successfully!")
         return True
         
     except Exception as e:
-        st.error(f"❌ Error uploading feedback: {e}")
+        st.error(f"Error uploading feedback: {e}")
         print(f"Feedback upload error: {e}")
         return False
 
-# Beautiful header
-st.markdown("<h1 class='main-title'>🌬️ VayuChat</h1>", unsafe_allow_html=True)
+# Filter available models
+available_models = []
+model_names = list(models.keys())
+groq_models = []
+gemini_models = []
+for model_name in model_names:
+    if "gemini" not in model_name:
+        groq_models.append(model_name)
+    else:
+        gemini_models.append(model_name)
+if Groq_Token and Groq_Token.strip():
+    available_models.extend(groq_models)
+if gemini_token and gemini_token.strip():
+    available_models.extend(gemini_models)
+
+if not available_models:
+    st.error("No API keys available! Please set up your API keys in the .env file")
+    st.stop()
 
-st.markdown("""
-<div class='subtitle'>
-    <strong>AI-Powered Air Quality Insights</strong><br>
-    Simplifying pollution analysis using conversational AI.
-</div>
-""", unsafe_allow_html=True)
+# Set DeepSeek-R1 as default if available
+default_index = 0
+if "deepseek-R1" in available_models:
+    default_index = available_models.index("deepseek-R1")
+
+# Header with logo, title and model selector
+header_col1, header_col2 = st.columns([2, 1])
+
+with header_col1:
+    st.markdown("""
+    <div style='display: flex; align-items: center; gap: 0.75rem; margin-bottom: 1rem;'>
+        <div style='width: 32px; height: 32px; background: #3b82f6; border-radius: 8px; display: flex; align-items: center; justify-content: center; color: white; font-weight: bold;'>V</div>
+        <div>
+            <h1 style='margin: 0; font-size: 1.25rem; font-weight: 600; color: #1e293b;'>VayuChat</h1>
+            <p style='margin: 0; font-size: 0.875rem; color: #64748b;'>Environmental Data Analysis</p>
+        </div>
+    </div>
+    """, unsafe_allow_html=True)
 
-st.markdown("""
-<div class='instructions'>
-    <strong>How to Use:</strong><br>
-    Select a model from the sidebar and ask questions directly in the chat. Use quick prompts below for common queries.
-</div>
-""", unsafe_allow_html=True)
+with header_col2:
+    model_name = st.selectbox(
+        "Model:",
+        available_models,
+        index=default_index,
+        help="Choose your AI model",
+        label_visibility="collapsed"
+    )
+
+st.markdown("<hr style='margin: 1rem 0; border: none; border-top: 1px solid #e2e8f0;'>", unsafe_allow_html=True)
 
-os.environ["PANDASAI_API_KEY"] = "$2a$10$gbmqKotzJOnqa7iYOun8eO50TxMD/6Zw1pLI2JEoqncwsNx4XeBS2"
 
 # Load data with error handling
 try:
     df = preprocess_and_load_df(join(self_path, "Data.csv"))
-    st.success("✅ Data loaded successfully!")
+    st.success("Data loaded successfully!")
 except Exception as e:
-    st.error(f"❌ Error loading data: {e}")
+    st.error(f"Error loading data: {e}")
     st.stop()
 
 inference_server = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2"
 image_path = "IITGN_Logo.png"
 
-# Beautiful sidebar
+# Clean sidebar
 with st.sidebar:
-    # Logo and title
-    col1, col2, col3 = st.columns([1, 2, 1])
-    with col2:
-        if os.path.exists(image_path):
-            st.image(image_path, use_column_width=True)
-    
-    # Session info
-    st.markdown(f"**Session ID**: `{st.session_state.session_id[:8]}...`")
-    
-    # Model selection
-    st.markdown("### 🤖 AI Model Selection")
-    
-    # Filter available models
-    available_models = []
-    model_names = list(models.keys())
-    groq_models = []
-    gemini_models = []
-    for model_name in model_names:
-        if "gemini" not in model_name:
-            groq_models.append(model_name)
-        else:
-            gemini_models.append(model_name)
-    if Groq_Token and Groq_Token.strip():
-        available_models.extend(groq_models)
-    if gemini_token and gemini_token.strip():
-        available_models.extend(gemini_models)
+    # Dataset Info Section
+    st.markdown("### Dataset Info")
+    st.markdown("""
+    <div style='background-color: #f1f5f9; padding: 1rem; border-radius: 8px; margin-bottom: 1.5rem;'>
+        <h4 style='margin: 0 0 0.5rem 0; color: #1e293b; font-size: 1rem;'>PM2.5 Air Quality Data</h4>
+        <p style='margin: 0.25rem 0; font-size: 0.875rem;'><strong>Time Range:</strong> Daily measurements</p>
+        <p style='margin: 0.25rem 0; font-size: 0.875rem;'><strong>Locations:</strong> Multiple cities in Gujarat</p>
+        <p style='margin: 0.25rem 0; font-size: 0.875rem;'><strong>Records:</strong> Air quality monitoring data</p>
+        <p style='margin: 0.25rem 0; font-size: 0.875rem;'><strong>Parameters:</strong> PM2.5, PM10, Location data</p>
+    </div>
+    """, unsafe_allow_html=True)
     
-    if not available_models:
-        st.error("❌ No API keys available! Please set up your API keys in the .env file")
-        st.stop()
-
-    model_name = st.selectbox(
-        "Choose your AI assistant:",
-        available_models,
-        help="Different models have different strengths. Try them all!"
-    )
+    # Current Model Info
+    st.markdown("### Current Model")
+    st.markdown(f"**{model_name}**")
     
-    # Model descriptions
     model_descriptions = {
-        "llama3.1": "🦙 Fast and efficient for general queries",
-        "llama3.3": "🦙 Most advanced LLaMA model for complex reasoning",
-        "mistral": "⚡ Balanced performance and speed",
-        "gemma": "💎 Google's lightweight model",
-        "gemini-pro": "🧠 Google's most powerful model",
-        "gpt-oss-20b": "📘 OpenAI's compact open-weight GPT for everyday tasks",
-        "gpt-oss-120b": "📚 OpenAI's massive open-weight GPT for nuanced responses",
-        "deepseek-R1": "🔍 DeepSeek's distilled LLaMA model for efficient reasoning",
-        "llama4 maverik": "🚀 Meta's LLaMA 4 Maverick — high-performance instruction model",
-        "llama4 scout": "🛰️ Meta's LLaMA 4 Scout — optimized for adaptive reasoning"
+        "llama3.1": "Fast and efficient for general queries",
+        "llama3.3": "Most advanced LLaMA model for complex reasoning",
+        "mistral": "Balanced performance and speed",
+        "gemma": "Google's lightweight model",
+        "gemini-pro": "Google's most powerful model",
+        "gpt-oss-20b": "OpenAI's compact open-weight GPT for everyday tasks",
+        "gpt-oss-120b": "OpenAI's massive open-weight GPT for nuanced responses",
+        "deepseek-R1": "DeepSeek's distilled LLaMA model for efficient reasoning",
+        "llama4 maverik": "Meta's LLaMA 4 Maverick — high-performance instruction model",
+        "llama4 scout": "Meta's LLaMA 4 Scout — optimized for adaptive reasoning"
     }
-
     
     if model_name in model_descriptions:
-        st.info(model_descriptions[model_name])
+        st.caption(model_descriptions[model_name])
     
     st.markdown("---")
     
-    # Logging status
-    st.markdown("### 📊 Logging Status")
-    if hf_token and hf_token.strip():
-        st.success("✅ Logging enabled")
-        st.caption("Interactions are being logged to HuggingFace")
-    else:
-        st.warning("⚠️ Logging disabled")
-        st.caption("HF_TOKEN not available")
+    # Quick Queries Section
+    st.markdown("### Quick Queries")
+    
+    # Load quick prompts
+    questions = []
+    questions_file = join(self_path, "questions.txt")
+    if os.path.exists(questions_file):
+        try:
+            with open(questions_file, 'r', encoding='utf-8') as f:
+                content = f.read()
+                questions = [q.strip() for q in content.split("\n") if q.strip()]
+        except Exception as e:
+            questions = []
+    
+    # Add default prompts if file doesn't exist or is empty
+    if not questions:
+        questions = [
+            "Which month had highest pollution?",
+            "Which city has worst air quality?", 
+            "Show annual PM2.5 average",
+            "Compare winter vs summer pollution",
+            "List all cities by pollution level",
+            "Plot monthly average PM2.5 for 2023"
+        ]
+    
+    # Quick query buttons in sidebar
+    selected_prompt = None
+    for i, question in enumerate(questions[:6]):  # Show only first 6
+        if st.button(
+            question, 
+            key=f"sidebar_prompt_{i}",
+            help=question,
+            use_container_width=True
+        ):
+            selected_prompt = question
     
     st.markdown("---")
     
     # Clear Chat Button
-    if st.button("🧹 Clear Chat"):
+    if st.button("Clear Chat", use_container_width=True):
         st.session_state.responses = []
         st.session_state.processing = False
-        # Generate new session ID for new chat
         st.session_state.session_id = str(uuid.uuid4())
         try:
             st.rerun()
         except AttributeError:
             st.experimental_rerun()
-    
-    st.markdown("---")
-    
-    # Chat History in Sidebar
-    with st.expander("📜 Chat History"):
-        for i, response in enumerate(st.session_state.get("responses", [])):
-            if response.get("role") == "user":
-                st.markdown(f"**You:** {response.get('content', '')[:50]}...")
-            elif response.get("role") == "assistant":
-                content = response.get('content', '')
-                if isinstance(content, str) and len(content) > 50:
-                    st.markdown(f"**VayuChat:** {content[:50]}...")
-                else:
-                    st.markdown(f"**VayuChat:** {str(content)[:50]}...")
-            st.markdown("---")
-
-# Load quick prompts
-questions = []
-questions_file = join(self_path, "questions.txt")
-if os.path.exists(questions_file):
-    try:
-        with open(questions_file, 'r', encoding='utf-8') as f:
-            content = f.read()
-            questions = [q.strip() for q in content.split("\n") if q.strip()]
-        print(f"Loaded {len(questions)} quick prompts")  # Debug
-    except Exception as e:
-        st.error(f"Error loading questions: {e}")
-        questions = []
-
-# Add some default prompts if file doesn't exist or is empty
-if not questions:
-    questions = [
-        "What is the average PM2.5 level in the dataset?",
-        "Show me the air quality trend over time",
-        "Which pollutant has the highest concentration?",
-        "Create a correlation plot between different pollutants",
-        "What are the peak pollution hours?",
-        "Compare weekday vs weekend pollution levels"
-    ]
-
-# Quick prompts section (horizontal)
-st.markdown("### 💭 Quick Prompts")
-
-# Create columns for horizontal layout
-cols_per_row = 2  # Reduced to 2 for better fit
-rows = [questions[i:i + cols_per_row] for i in range(0, len(questions), cols_per_row)]
-
-selected_prompt = None
-for row_idx, row in enumerate(rows):
-    cols = st.columns(len(row))
-    for col_idx, question in enumerate(row):
-        with cols[col_idx]:
-            # Create unique key using row and column indices
-            unique_key = f"prompt_btn_{row_idx}_{col_idx}"
-            button_text = f"📝 {question[:35]}{'...' if len(question) > 35 else ''}"
-            
-            if st.button(button_text, 
-                        key=unique_key,
-                        help=question,
-                        use_container_width=True):
-                selected_prompt = question
 
-st.markdown("---")
+# Main content area - removed quick prompts section from here as it's now in sidebar
 
 # Initialize chat history and processing state
 if "responses" not in st.session_state:
@@ -557,35 +604,55 @@ if "processing" not in st.session_state:
     st.session_state.processing = False
 
 def show_custom_response(response):
-    """Custom response display function"""
+    """Custom response display function with improved styling"""
     role = response.get("role", "assistant")
     content = response.get("content", "")
     
     if role == "user":
+        # User message with right alignment
         st.markdown(f"""
-        <div class='user-message'>
-            <div class='user-info'>You</div>
-            {content}
+        <div style='display: flex; justify-content: flex-end; margin: 2rem 0;'>
+            <div class='user-message'>
+                {content}
+            </div>
         </div>
         """, unsafe_allow_html=True)
     elif role == "assistant":
+        # Assistant message with left alignment
         st.markdown(f"""
-        <div class='assistant-message'>
-            <div class='assistant-info'>🤖 VayuChat</div>
-            {content if isinstance(content, str) else str(content)}
+        <div style='display: flex; justify-content: flex-start; margin: 2rem 0;'>
+            <div class='assistant-message'>
+                <div class='assistant-info'>VayuChat</div>
+                {content if isinstance(content, str) else str(content)}
+            </div>
         </div>
         """, unsafe_allow_html=True)
         
-        # Show generated code if available
+        # Show generated code with collapsible container
         if response.get("gen_code"):
-            with st.expander("📋 View Generated Code"):
-                st.code(response["gen_code"], language="python")
+            st.markdown("""
+            <div class='code-container'>
+                <div class='code-header' onclick='toggleCode(this)'>
+                    <div class='code-title'>Generated Python Code</div>
+                    <div class='toggle-text'>Click to expand</div>
+                </div>
+                <div class='code-block' style='display: none;'>
+            """, unsafe_allow_html=True)
+            
+            st.code(response["gen_code"], language="python")
+            
+            st.markdown("</div></div>", unsafe_allow_html=True)
         
         # Try to display image if content is a file path
         try:
             if isinstance(content, str) and (content.endswith('.png') or content.endswith('.jpg')):
                 if os.path.exists(content):
+                    # Chart container styling
+                    st.markdown("""
+                    <div style='background: white; border: 1px solid #e2e8f0; border-radius: 8px; padding: 1.5rem; margin: 1rem 0;'>
+                    """, unsafe_allow_html=True)
                     st.image(content)
+                    st.markdown("</div>", unsafe_allow_html=True)
                     return {"is_image": True}
         except:
             pass
@@ -596,9 +663,9 @@ def show_processing_indicator(model_name, question):
     """Show processing indicator"""
     st.markdown(f"""
     <div class='processing-indicator'>
-        <div class='assistant-info'>🤖 VayuChat • Processing with {model_name}</div>
+        <div class='assistant-info'>VayuChat • Processing with {model_name}</div>
         <strong>Question:</strong> {question}<br>
-        <em>🔄 Generating response...</em>
+        <em>Generating response...</em>
     </div>
     """, unsafe_allow_html=True)
 
@@ -622,7 +689,7 @@ with chat_container:
                 feedback_data = st.session_state.responses[response_id]["feedback"]
                 st.markdown(f"""
                 <div class='feedback-section'>
-                    <strong>📝 Your Feedback:</strong> {feedback_data.get('score', '')} 
+                    <strong>Your Feedback:</strong> {feedback_data.get('score', '')} 
                     {f"- {feedback_data.get('text', '')}" if feedback_data.get('text') else ""}
                 </div>
                 """, unsafe_allow_html=True)
@@ -640,13 +707,13 @@ with chat_container:
                 if thumbs_up or thumbs_down:
                     thumbs = "👍 Helpful" if thumbs_up else "👎 Not Helpful"
                     comments = st.text_area(
-                        "💬 Tell us more (optional):", 
+                        "Tell us more (optional):", 
                         key=f"{feedback_key}_comments",
                         placeholder="What could be improved? Any suggestions?",
                         max_chars=500
                     )
                     
-                    if st.button("🚀 Submit Feedback", key=f"{feedback_key}_submit"):
+                    if st.button("Submit Feedback", key=f"{feedback_key}_submit"):
                         feedback = {"score": thumbs, "text": comments}
                         
                         # Upload feedback with enhanced error handling
@@ -665,7 +732,7 @@ with chat_container:
         )
 
 # Chat input (always visible at bottom)
-prompt = st.chat_input("💬 Ask me anything about air quality!", key="main_chat")
+prompt = st.chat_input("Ask me anything about air quality!", key="main_chat")
 
 # Handle selected prompt from quick prompts
 if selected_prompt:
@@ -704,7 +771,7 @@ if st.session_state.get("processing"):
         if not isinstance(response, dict):
             response = {
                 "role": "assistant",
-                "content": "❌ Error: Invalid response format",
+                "content": "Error: Invalid response format",
                 "gen_code": "",
                 "ex_code": "",
                 "last_prompt": prompt,
@@ -767,7 +834,7 @@ if st.session_state.responses:
 # Footer
 st.markdown("""
 <div style='text-align: center; margin-top: 3rem; padding: 2rem; background: rgba(255,255,255,0.1); border-radius: 15px;'>
-    <h3>🌍 Together for Cleaner Air</h3>
+    <h3>Together for Cleaner Air</h3>
     <p>VayuChat - Empowering environmental awareness through AI</p>
     <small>© 2024 IIT Gandhinagar Sustainability Lab</small>
 </div>

requirements.txt

@@ -3,7 +3,6 @@ streamlit==1.32.2
 pandas==1.5.3
 langchain==0.1.15
 python-dotenv==1.0.0
-pandasai==2.0.30
 geopandas
 plotly
 streamlit_feedback

src.py

@@ -1,9 +1,7 @@
 import os
 import pandas as pd
-from pandasai import Agent, SmartDataframe
 from typing import Tuple
 from PIL import Image
-from pandasai.llm import HuggingFaceTextGen
 from dotenv import load_dotenv
 from langchain_groq import ChatGroq
 from langchain_google_genai import ChatGoogleGenerativeAI
@@ -97,161 +95,14 @@ def preprocess_and_load_df(path: str) -> pd.DataFrame:
     except Exception as e:
         raise Exception(f"Error loading dataframe: {e}")
 
-def load_agent(df: pd.DataFrame, context: str, inference_server: str, name="mistral") -> Agent:
-    """Load pandas AI agent with error handling"""
-    try:
-        if name == "gemini-pro":
-            if not gemini_token or gemini_token.strip() == "":
-                raise ValueError("Gemini API token not available or empty")
-            llm = ChatGoogleGenerativeAI(
-                model=models[name], 
-                google_api_key=gemini_token, 
-                temperature=0.1
-            )
-        else:
-            if not Groq_Token or Groq_Token.strip() == "":
-                raise ValueError("Groq API token not available or empty")
-            llm = ChatGroq(
-                model=models[name], 
-                api_key=Groq_Token,
-                temperature=0.1
-            )
-        
-        agent = Agent(df, config={"llm": llm, "enable_cache": False, "options": {"wait_for_model": True}})
-        if context:
-            agent.add_message(context)
-        return agent
-    except Exception as e:
-        raise Exception(f"Error loading agent: {e}")
 
-def load_smart_df(df: pd.DataFrame, inference_server: str, name="mistral") -> SmartDataframe:
-    """Load smart dataframe with error handling"""
-    try:
-        if name == "gemini-pro":
-            if not gemini_token or gemini_token.strip() == "":
-                raise ValueError("Gemini API token not available or empty")
-            llm = ChatGoogleGenerativeAI(
-                model=models[name], 
-                google_api_key=gemini_token, 
-                temperature=0.1
-            )
-        else:
-            if not Groq_Token or Groq_Token.strip() == "":
-                raise ValueError("Groq API token not available or empty")
-            llm = ChatGroq(
-                model=models[name], 
-                api_key=Groq_Token,
-                temperature=0.1
-            )
-        
-        df = SmartDataframe(df, config={"llm": llm, "max_retries": 5, "enable_cache": False})
-        return df
-    except Exception as e:
-        raise Exception(f"Error loading smart dataframe: {e}")
 
 def get_from_user(prompt):
     """Format user prompt"""
     return {"role": "user", "content": prompt}
 
-def ask_agent(agent: Agent, prompt: str) -> dict:
-    """Ask agent with comprehensive error handling"""
-    start_time = datetime.now()
-    try:
-        response = agent.chat(prompt)
-        execution_time = (datetime.now() - start_time).total_seconds()
-        
-        gen_code = getattr(agent, 'last_code_generated', '')
-        ex_code = getattr(agent, 'last_code_executed', '')
-        last_prompt = getattr(agent, 'last_prompt', prompt)
-        
-        # Log the interaction
-        log_interaction(
-            user_query=prompt,
-            model_name="pandas_ai_agent",
-            response_content=response,
-            generated_code=gen_code,
-            execution_time=execution_time,
-            error_message=None,
-            is_image=isinstance(response, str) and any(response.endswith(ext) for ext in ['.png', '.jpg', '.jpeg'])
-        )
-        
-        return {
-            "role": "assistant", 
-            "content": response, 
-            "gen_code": gen_code, 
-            "ex_code": ex_code, 
-            "last_prompt": last_prompt,
-            "error": None
-        }
-    except Exception as e:
-        execution_time = (datetime.now() - start_time).total_seconds()
-        error_msg = str(e)
-        
-        # Log the failed interaction
-        log_interaction(
-            user_query=prompt,
-            model_name="pandas_ai_agent",
-            response_content=f"Error: {error_msg}",
-            generated_code="",
-            execution_time=execution_time,
-            error_message=error_msg,
-            is_image=False
-        )
-        
-        return {
-            "role": "assistant", 
-            "content": f"Error: {error_msg}", 
-            "gen_code": "", 
-            "ex_code": "", 
-            "last_prompt": prompt,
-            "error": error_msg
-        }
-
-def decorate_with_code(response: dict) -> str:
-    """Decorate response with code details"""
-    gen_code = response.get("gen_code", "No code generated")
-    last_prompt = response.get("last_prompt", "No prompt")
-    
-    return f"""<details>
-<summary>Generated Code</summary>
-    
-```python
-{gen_code}
-```
-</details>
-
-<details>
-<summary>Prompt</summary>
 
-{last_prompt}
-"""
 
-def show_response(st, response):
-    """Display response with error handling"""
-    try:
-        with st.chat_message(response["role"]):
-            content = response.get("content", "No content")
-            
-            try:
-                # Try to open as image
-                image = Image.open(content)
-                if response.get("gen_code"):
-                    st.markdown(decorate_with_code(response), unsafe_allow_html=True)
-                st.image(image)
-                return {"is_image": True}
-            except:
-                # Not an image, display as text
-                if response.get("gen_code"):
-                    display_content = decorate_with_code(response) + f"""</details>
-
-{content}"""
-                else:
-                    display_content = content
-                st.markdown(display_content, unsafe_allow_html=True)
-                return {"is_image": False}
-    except Exception as e:
-        st.error(f"Error displaying response: {e}")
-        return {"is_image": False}
 
 def ask_question(model_name, question):
     """Ask question with comprehensive error handling and logging"""
@@ -274,7 +125,7 @@ def ask_question(model_name, question):
                 log_interaction(
                     user_query=question,
                     model_name=model_name,
-                    response_content="❌ Gemini API token not available or empty",
+                    response_content="Gemini API token not available or empty",
                     generated_code="",
                     execution_time=execution_time,
                     error_message=error_msg,
@@ -283,7 +134,7 @@ def ask_question(model_name, question):
                 
                 return {
                     "role": "assistant", 
-                    "content": "❌ Gemini API token not available or empty. Please set GEMINI_TOKEN in your environment variables.", 
+                    "content": "Gemini API token not available or empty. Please set GEMINI_TOKEN in your environment variables.", 
                     "gen_code": "", 
                     "ex_code": "", 
                     "last_prompt": question,
@@ -303,7 +154,7 @@ def ask_question(model_name, question):
                 log_interaction(
                     user_query=question,
                     model_name=model_name,
-                    response_content="❌ Groq API token not available or empty",
+                    response_content="Groq API token not available or empty",
                     generated_code="",
                     execution_time=execution_time,
                     error_message=error_msg,
@@ -312,7 +163,7 @@ def ask_question(model_name, question):
                 
                 return {
                     "role": "assistant", 
-                    "content": "❌ Groq API token not available or empty. Please set GROQ_API_KEY in your environment variables and restart the application.", 
+                    "content": "Groq API token not available or empty. Please set GROQ_API_KEY in your environment variables and restart the application.", 
                     "gen_code": "", 
                     "ex_code": "", 
                     "last_prompt": question,
@@ -334,10 +185,10 @@ def ask_question(model_name, question):
                 error_msg = str(api_error)
                 
                 if "organization_restricted" in error_msg.lower() or "unauthorized" in error_msg.lower():
-                    response_content = "❌ API Key Error: Your Groq API key appears to be invalid, expired, or restricted. Please check your API key in the .env file."
+                    response_content = "API Key Error: Your Groq API key appears to be invalid, expired, or restricted. Please check your API key in the .env file."
                     log_error_msg = f"API key validation failed: {error_msg}"
                 else:
-                    response_content = f"❌ API Connection Error: {error_msg}"
+                    response_content = f"API Connection Error: {error_msg}"
                     log_error_msg = error_msg
                 
                 # Log the failed interaction
@@ -369,7 +220,7 @@ def ask_question(model_name, question):
             log_interaction(
                 user_query=question,
                 model_name=model_name,
-                response_content="❌ Data.csv file not found",
+                response_content="Data.csv file not found",
                 generated_code="",
                 execution_time=execution_time,
                 error_message=error_msg,
@@ -378,7 +229,7 @@ def ask_question(model_name, question):
             
             return {
                 "role": "assistant", 
-                "content": "❌ Data.csv file not found. Please ensure the data file is in the correct location.", 
+                "content": "Data.csv file not found. Please ensure the data file is in the correct location.", 
                 "gen_code": "", 
                 "ex_code": "", 
                 "last_prompt": question,
@@ -499,7 +350,7 @@ Complete the following code to answer the user's question:
             log_interaction(
                 user_query=question,
                 model_name=model_name,
-                response_content=f"❌ Error executing generated code: {error_msg}",
+                response_content=f"Error executing generated code: {error_msg}",
                 generated_code=full_code if 'full_code' in locals() else "",
                 execution_time=execution_time,
                 error_message=error_msg,
@@ -508,7 +359,7 @@ Complete the following code to answer the user's question:
             
             return {
                 "role": "assistant", 
-                "content": f"❌ Error executing generated code: {error_msg}", 
+                "content": f"Error executing generated code: {error_msg}", 
                 "gen_code": full_code if 'full_code' in locals() else "", 
                 "ex_code": full_code if 'full_code' in locals() else "", 
                 "last_prompt": question,
@@ -521,13 +372,13 @@ Complete the following code to answer the user's question:
         
         # Handle specific API errors
         if "organization_restricted" in error_msg:
-            response_content = "❌ API Organization Restricted: Your API key access has been restricted. Please check your Groq API key or try generating a new one."
+            response_content = "API Organization Restricted: Your API key access has been restricted. Please check your Groq API key or try generating a new one."
             log_error_msg = "API access restricted"
         elif "rate_limit" in error_msg.lower():
-            response_content = "❌ Rate limit exceeded. Please wait a moment and try again."
+            response_content = "Rate limit exceeded. Please wait a moment and try again."
             log_error_msg = "Rate limit exceeded"
         else:
-            response_content = f"❌ Error: {error_msg}"
+            response_content = f"Error: {error_msg}"
             log_error_msg = error_msg
         
         # Log the failed interaction