Add Gradio and Streamlit chat interfaces for Sales Assistant

- Created `run_ui.sh` script to launch the UI applications.
- Added README documentation for the Sales Assistant Chat UI, detailing available interfaces, quick start instructions, example queries, features, technical details, prerequisites, troubleshooting, and development tips.
- Implemented Gradio chat interface in `gradio_app.py` with features for product search, quote generation, and data analysis.
- Developed Streamlit chat interface in `streamlit_app.py` with similar functionalities and enhanced user interaction features.

.gitignore

@@ -91,4 +91,7 @@ Thumbs.db
 
 # Temporary files
 *.tmp
-*.temp
+*.temp
+
+# Quotes
+src/sales_assistant/created_quotes/*

pyproject.toml

@@ -17,11 +17,12 @@ dependencies = [
     "langchain>=0.3.27",
     "langgraph>=0.6.5",
     "langchain-openai>=0.3.30",
-    "langchain-nvidia-ai-endpoints>=0.3.0",
     "langsmith>=0.2.13",
     "pydantic>=2.11.7",
     "huggingface-hub>=0.34.4",
     "langchain-huggingface>=0.3.1",
+    "gradio>=5.43.1",
+    "streamlit>=1.48.1",
 ]
 
 [build-system]

src/sales_assistant/agent_main/agent_node.py

@@ -9,6 +9,7 @@ from langgraph.graph import MessagesState
 from langchain_openai import ChatOpenAI
 from dotenv import load_dotenv
 from ..prompts.system_prompt import SYSTEM_PROMPT
+from .tools_node import get_all_tools
 
 # Load environment variables
 load_dotenv()
@@ -51,8 +52,6 @@ def agent_node(state: MessagesState) -> Dict[str, Any]:
             api_key=os.getenv("OPENAI_API_KEY"),
         )
     
-    # Bind tools to the model
-    from .tools_node import get_all_tools
     tools = get_all_tools()
     model_with_tools = model.bind_tools(tools)
     

src/sales_assistant/ui_dashboard/README.md

@@ -0,0 +1,130 @@
+# Sales Assistant Chat UI
+
+This directory contains two different chat interfaces for the Sales Assistant:
+
+## 🎨 Available Interfaces
+
+### 1. Gradio Chat Interface (`gradio_app.py`)
+- **URL**: http://localhost:7860
+- **Features**: 
+  - Simple, clean chat interface
+  - Example queries sidebar
+  - Real-time responses
+  - Mobile-friendly design
+- **Best for**: Quick testing and development
+
+### 2. Streamlit Chat Interface (`streamlit_app.py`)
+- **URL**: http://localhost:8501
+- **Features**:
+  - Rich sidebar with capabilities overview
+  - Chat statistics
+  - Agent status monitoring
+  - Professional dashboard layout
+- **Best for**: Demos and production use
+
+## 🚀 Quick Start
+
+### Option 1: Use the Launcher Script
+```bash
+# From the project root
+./run_ui.sh
+```
+
+### Option 2: Run Individual Apps
+
+**Gradio:**
+```bash
+uv run python src/sales_assistant/ui_dashboard/gradio_app.py
+```
+
+**Streamlit:**
+```bash
+uv run streamlit run src/sales_assistant/ui_dashboard/streamlit_app.py --server.port 8501
+```
+
+### Option 3: Run Both Simultaneously
+```bash
+# Terminal 1 - Gradio
+uv run python src/sales_assistant/ui_dashboard/gradio_app.py
+
+# Terminal 2 - Streamlit  
+uv run streamlit run src/sales_assistant/ui_dashboard/streamlit_app.py --server.port 8501
+```
+
+## 💡 Example Queries
+
+Try these sample queries in either interface:
+
+- `"Show me information about our products"`
+- `"I need a quote for industrial equipment"`
+- `"What are the current exchange rates?"`
+- `"Find products with price under $1000"`
+- `"Generate a quote for customer 'Tech Solutions Inc'"`
+- `"Show me Samsung outdoor TVs"`
+
+## 🔧 Features
+
+Both interfaces provide access to:
+
+- **Product Database Search**: Explore the complete product catalog
+- **Quote Generation**: Create professional quotes with current pricing
+- **Data Analysis**: Get statistical insights about products
+- **Exchange Rates**: Current currency conversion information
+- **Natural Language Processing**: Ask questions in plain English
+
+## 🛠 Technical Details
+
+- **Backend**: LangGraph-based conversational agent
+- **Database**: MySQL with SSH tunnel connection
+- **AI Models**: OpenAI GPT models with tool calling
+- **State Management**: Persistent conversation history
+- **Tracing**: Optional LangSmith integration for debugging
+
+## 📋 Prerequisites
+
+Make sure you have:
+
+1. **Environment Variables** set in `.env`:
+   - `OPENAI_API_KEY`
+   - `MODEL_PROVIDER=openai`
+   - `MODEL_NAME=gpt-4`
+   - `MYSQL_HOST`, `MYSQL_USER`, `MYSQL_PASSWORD`, `MYSQL_DB`
+   - Optional: `LANGSMITH_API_KEY`, `LANGSMITH_PROJECT`
+
+2. **Dependencies** installed:
+   ```bash
+   uv add gradio streamlit
+   ```
+
+3. **Database Access**: Ensure your MySQL database is accessible and the SSH tunnel is configured if needed.
+
+## 🔍 Troubleshooting
+
+### Common Issues:
+
+1. **Agent Initialization Failed**
+   - Check your `.env` file configuration
+   - Verify database connectivity
+   - Ensure all required environment variables are set
+
+2. **Port Already in Use**
+   - Change ports in the launch commands
+   - Kill existing processes: `pkill -f "gradio_app\|streamlit"`
+
+3. **Database Connection Issues**
+   - Verify SSH tunnel configuration
+   - Check database credentials
+   - Ensure the database server is running
+
+### Logs and Debugging:
+
+- Both apps print initialization status to the console
+- Database queries are logged with SQL statements
+- LangSmith tracing can be enabled for detailed debugging
+
+## 🎯 Development Tips
+
+- **Hot Reload**: Streamlit supports hot reload for development
+- **Custom Styling**: Both apps support custom CSS/themes
+- **Configuration**: Modify the `ConversationConfig` for different settings
+- **Extensions**: Easy to add new features through the agent tools system

src/sales_assistant/ui_dashboard/gradio_app.py

@@ -0,0 +1,216 @@
+"""
+Gradio Chat UI for Sales Assistant
+
+This module provides a simple Gradio-based chat interface for the sales assistant.
+"""
+import os
+import sys
+import gradio as gr
+from typing import List, Tuple, Dict
+
+# Add the src directory to the path
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../..'))
+
+from sales_assistant.main import (
+    check_environment_setup,
+    create_custom_config
+)
+from sales_assistant.agent_main.agent_runner import (
+    create_agent_runner,
+    run_conversation_turn
+)
+
+
+class SalesAssistantChat:
+    """Chat interface for the sales assistant."""
+    
+    def __init__(self):
+        """Initialize the chat interface."""
+        self.compiled_graph = None
+        self.checkpointer = None
+        self.langsmith_client = None
+        self.thread_id = None
+        self.initialize_agent()
+    
+    def initialize_agent(self):
+        """Initialize the agent runner."""
+        try:
+            # Check environment setup
+            if not check_environment_setup():
+                print("❌ Environment setup failed")
+                return
+            
+            # Create configuration
+            config = create_custom_config(
+                session_id="gradio_session",
+                user_id="gradio_user",
+                enable_langsmith=True
+            )
+            
+            # Create agent runner
+            self.compiled_graph, self.checkpointer, self.langsmith_client, self.thread_id = create_agent_runner(config)
+            print("✅ Sales Assistant initialized successfully!")
+            
+        except Exception as e:
+            print(f"❌ Failed to initialize sales assistant: {e}")
+            self.compiled_graph = None
+    
+    def chat_function(self, message: str, history: List[Dict[str, str]]) -> Tuple[str, List[Dict[str, str]]]:
+        """
+        Process a chat message and return the response.
+        
+        Args:
+            message: User's input message
+            history: Chat history as list of message dictionaries
+            
+        Returns:
+            Tuple of (empty_string, updated_history)
+        """
+        if not self.compiled_graph:
+            error_response = "❌ Sales Assistant is not properly initialized. Please check your environment configuration."
+            history.append({"role": "user", "content": message})
+            history.append({"role": "assistant", "content": error_response})
+            return "", history
+        
+        try:
+            # Run conversation turn
+            response = run_conversation_turn(
+                compiled_graph=self.compiled_graph,
+                thread_id=self.thread_id,
+                user_input=message,
+                langsmith_client=self.langsmith_client
+            )
+            
+            # Add to history
+            history.append({"role": "user", "content": message})
+            history.append({"role": "assistant", "content": response})
+            
+        except Exception as e:
+            error_response = f"❌ Error processing your request: {str(e)}"
+            history.append({"role": "user", "content": message})
+            history.append({"role": "assistant", "content": error_response})
+        
+        return "", history
+
+
+def create_gradio_interface():
+    """Create and configure the Gradio interface."""
+    
+    # Initialize the chat assistant
+    chat_assistant = SalesAssistantChat()
+    
+    # Create the interface
+    with gr.Blocks(
+        title="Sales Assistant with Quote Generation",
+        theme=gr.themes.Soft(),
+        css="""
+        .gradio-container {
+            max-width: 1200px !important;
+        }
+        """
+    ) as interface:
+        
+        gr.Markdown(
+            """
+            # 🤖 Sales Assistant with Quote Generation
+            
+            Welcome to the Sales Assistant! I can help you:
+            - 🔍 Search and explore our product database
+            - 📊 Analyze product data and statistics
+            - 💰 Generate detailed quotes with pricing
+            - 🌍 Provide exchange rate information
+            - ❓ Answer questions about our products and services
+            
+            Simply type your question or request below to get started!
+            """
+        )
+        
+        # Chat interface
+        chatbot = gr.Chatbot(
+            value=[],
+            height=500,
+            label="Sales Assistant Chat",
+            show_label=True,
+            avatar_images=("👤", "🤖"),
+            type="messages"
+        )
+        
+        # Input components
+        with gr.Row():
+            msg_input = gr.Textbox(
+                placeholder="Ask me about products, request a quote, or explore our database...",
+                label="Your Message",
+                scale=4,
+                lines=1
+            )
+            send_btn = gr.Button("Send", variant="primary", scale=1)
+        
+        # Example queries
+        with gr.Row():
+            gr.Examples(
+                examples=[
+                    "Show me information about our products",
+                    "I need a quote for industrial equipment",
+                    "What are the current exchange rates?",
+                    "Find products with price under $1000",
+                    "Generate a quote for customer 'Tech Solutions Inc'",
+                    "Show me product statistics"
+                ],
+                inputs=msg_input,
+                label="Example Queries"
+            )
+        
+        # Additional information
+        with gr.Accordion("ℹ️ About This Assistant", open=False):
+            gr.Markdown(
+                """
+                This Sales Assistant is powered by advanced AI and has access to:
+                
+                - **Product Database**: Complete catalog with specifications and pricing
+                - **Quote Generation**: Professional quote creation with current exchange rates
+                - **Data Analysis**: Statistical insights and product comparisons
+                - **Real-time Information**: Current pricing and availability
+                
+                The assistant uses natural language processing to understand your requests
+                and can perform complex database queries to provide accurate information.
+                """
+            )
+        
+        # Event handlers
+        def submit_message(message, history):
+            return chat_assistant.chat_function(message, history)
+        
+        # Wire up the events
+        msg_input.submit(
+            submit_message,
+            inputs=[msg_input, chatbot],
+            outputs=[msg_input, chatbot]
+        )
+        
+        send_btn.click(
+            submit_message,
+            inputs=[msg_input, chatbot],
+            outputs=[msg_input, chatbot]
+        )
+    
+    return interface
+
+
+def main():
+    """Main function to run the Gradio app."""
+    print("🚀 Starting Gradio Sales Assistant...")
+    
+    # Create interface
+    interface = create_gradio_interface()
+    
+    # Launch the app
+    interface.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False,
+        show_error=True
+    )
+
+
+if __name__ == "__main__":
+    main()

src/sales_assistant/ui_dashboard/streamlit_app.py

@@ -0,0 +1,273 @@
+"""
+Streamlit Chat UI for Sales Assistant
+
+This module provides a simple Streamlit-based chat interface for the sales assistant.
+"""
+import os
+import sys
+import streamlit as st
+from typing import Dict, Any, List
+
+# Add the src directory to the path
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../..'))
+
+from sales_assistant.main import (
+    check_environment_setup,
+    create_custom_config
+)
+from sales_assistant.agent_main.agent_runner import (
+    create_agent_runner,
+    run_conversation_turn
+)
+
+
+# Page configuration
+st.set_page_config(
+    page_title="Sales Assistant with Quote Generation",
+    page_icon="🤖",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
+
+
+def initialize_session_state():
+    """Initialize Streamlit session state variables."""
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+    
+    if "compiled_graph" not in st.session_state:
+        st.session_state.compiled_graph = None
+    
+    if "checkpointer" not in st.session_state:
+        st.session_state.checkpointer = None
+    
+    if "langsmith_client" not in st.session_state:
+        st.session_state.langsmith_client = None
+    
+    if "thread_id" not in st.session_state:
+        st.session_state.thread_id = None
+    
+    if "agent_initialized" not in st.session_state:
+        st.session_state.agent_initialized = False
+
+
+def initialize_agent():
+    """Initialize the sales assistant agent."""
+    if st.session_state.agent_initialized:
+        return True
+    
+    try:
+        with st.spinner("Initializing Sales Assistant..."):
+            # Check environment setup
+            if not check_environment_setup():
+                st.error("❌ Environment setup failed. Please check your configuration.")
+                return False
+            
+            # Create configuration
+            config = create_custom_config(
+                session_id="streamlit_session",
+                user_id="streamlit_user",
+                enable_langsmith=True
+            )
+            
+            # Create agent runner
+            compiled_graph, checkpointer, langsmith_client, thread_id = create_agent_runner(config)
+            
+            # Store in session state
+            st.session_state.compiled_graph = compiled_graph
+            st.session_state.checkpointer = checkpointer
+            st.session_state.langsmith_client = langsmith_client
+            st.session_state.thread_id = thread_id
+            st.session_state.agent_initialized = True
+            
+            st.success("✅ Sales Assistant initialized successfully!")
+            return True
+            
+    except Exception as e:
+        st.error(f"❌ Failed to initialize sales assistant: {e}")
+        return False
+
+
+def display_sidebar():
+    """Display the sidebar with information and controls."""
+    with st.sidebar:
+        st.markdown("# 🤖 Sales Assistant")
+        st.markdown("---")
+        
+        # Status indicator
+        if st.session_state.agent_initialized:
+            st.success("🟢 Agent Online")
+        else:
+            st.error("🔴 Agent Offline")
+        
+        st.markdown("---")
+        
+        # Information section
+        st.markdown("### 🔧 Capabilities")
+        st.markdown("""
+        - 🔍 **Product Search**: Find products by criteria
+        - 📊 **Data Analysis**: Statistical insights
+        - 💰 **Quote Generation**: Professional quotes
+        - 🌍 **Exchange Rates**: Current currency rates
+        - 📈 **Database Insights**: Explore product data
+        """)
+        
+        st.markdown("---")
+        
+        # Example queries
+        st.markdown("### 💡 Example Queries")
+        example_queries = [
+            "Show me product information",
+            "Generate a quote for equipment",
+            "What are current exchange rates?",
+            "Find products under $1000",
+            "Show product statistics"
+        ]
+        
+        for query in example_queries:
+            if st.button(query, key=f"example_{hash(query)}", use_container_width=True):
+                st.session_state.messages.append({"role": "user", "content": query})
+                st.rerun()
+        
+        st.markdown("---")
+        
+        # Clear chat button
+        if st.button("🗑️ Clear Chat", use_container_width=True):
+            st.session_state.messages = []
+            st.rerun()
+        
+        # Restart agent button
+        if st.button("🔄 Restart Agent", use_container_width=True):
+            st.session_state.agent_initialized = False
+            st.session_state.compiled_graph = None
+            st.session_state.checkpointer = None
+            st.session_state.langsmith_client = None
+            st.session_state.thread_id = None
+            st.rerun()
+
+
+def display_chat_messages():
+    """Display the chat messages."""
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+
+def process_user_input(user_input: str) -> str:
+    """
+    Process user input and get response from the sales assistant.
+    
+    Args:
+        user_input: The user's message
+        
+    Returns:
+        The assistant's response
+    """
+    if not st.session_state.compiled_graph:
+        return "❌ Sales Assistant is not properly initialized. Please restart the agent."
+    
+    try:
+        # Run conversation turn
+        response = run_conversation_turn(
+            compiled_graph=st.session_state.compiled_graph,
+            thread_id=st.session_state.thread_id,
+            user_input=user_input,
+            langsmith_client=st.session_state.langsmith_client
+        )
+        return response
+        
+    except Exception as e:
+        return f"❌ Error processing your request: {str(e)}"
+
+
+def main():
+    """Main Streamlit application."""
+    # Initialize session state
+    initialize_session_state()
+    
+    # Main title
+    st.title("🤖 Sales Assistant with Quote Generation")
+    st.markdown("---")
+    
+    # Initialize agent if not done
+    if not st.session_state.agent_initialized:
+        if not initialize_agent():
+            st.stop()
+    
+    # Display sidebar
+    display_sidebar()
+    
+    # Main chat area
+    col1, col2 = st.columns([3, 1])
+    
+    with col1:
+        # Introduction message
+        if not st.session_state.messages:
+            st.markdown("""
+            ### Welcome to the Sales Assistant! 👋
+            
+            I'm here to help you with:
+            - 🔍 **Product Information**: Search and explore our product database
+            - 📊 **Data Analysis**: Get insights and statistics about products
+            - 💰 **Quote Generation**: Create professional quotes with current pricing
+            - 🌍 **Exchange Rates**: Get up-to-date currency information
+            - ❓ **General Questions**: Ask me anything about our products and services
+            
+            **To get started**, type your question in the chat box below or click one of the example queries in the sidebar.
+            """)
+            st.markdown("---")
+        
+        # Display chat messages
+        display_chat_messages()
+        
+        # Chat input
+        if prompt := st.chat_input("Ask me about products, request a quote, or explore our database..."):
+            # Add user message to chat history
+            st.session_state.messages.append({"role": "user", "content": prompt})
+            
+            # Display user message
+            with st.chat_message("user"):
+                st.markdown(prompt)
+            
+            # Get and display assistant response
+            with st.chat_message("assistant"):
+                with st.spinner("Thinking..."):
+                    response = process_user_input(prompt)
+                st.markdown(response)
+            
+            # Add assistant response to chat history
+            st.session_state.messages.append({"role": "assistant", "content": response})
+    
+    with col2:
+        # Stats section
+        st.markdown("### 📊 Chat Statistics")
+        total_messages = len(st.session_state.messages)
+        user_messages = len([m for m in st.session_state.messages if m["role"] == "user"])
+        assistant_messages = len([m for m in st.session_state.messages if m["role"] == "assistant"])
+        
+        st.metric("Total Messages", total_messages)
+        st.metric("Your Messages", user_messages)
+        st.metric("Assistant Responses", assistant_messages)
+        
+        # Recent activity
+        if st.session_state.messages:
+            st.markdown("### 🕒 Recent Activity")
+            recent_messages = st.session_state.messages[-3:]
+            for msg in recent_messages:
+                role_icon = "👤" if msg["role"] == "user" else "🤖"
+                st.text(f"{role_icon} {msg['content'][:50]}...")
+    
+    # Footer
+    st.markdown("---")
+    st.markdown(
+        """
+        <div style='text-align: center; color: #666;'>
+        Sales Assistant powered by AI | Built with Streamlit
+        </div>
+        """,
+        unsafe_allow_html=True
+    )
+
+
+if __name__ == "__main__":
+    main()