feat: Add Streamlit UI, Dockerfile, and HF Spaces config

Co-authored-by: archc0der <119496494+archc0der@users.noreply.github.com>

Dockerfile

@@ -0,0 +1,28 @@
+# Use the official Python 3.10 image from DockerHub
+FROM python:3.10-slim
+
+# Set the working directory
+WORKDIR /app
+
+# Copy the requirements file and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the application code
+COPY . .
+
+# Expose the default port for Streamlit and HuggingFace Spaces
+EXPOSE 7860
+
+# Create a non-root user for HuggingFace Spaces (required by HF)
+RUN useradd -m -u 1000 user
+USER user
+
+# Define environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    STREAMLIT_SERVER_PORT=7860 \
+    STREAMLIT_SERVER_ADDRESS=0.0.0.0
+
+# Start the Streamlit application
+CMD ["streamlit", "run", "app.py"]

README.md

@@ -1,8 +1,26 @@
+---
+title: AutoStream AI Agent
+emoji: 🤖
+colorFrom: blue
+colorTo: purple
+sdk: docker
+app_port: 7860
+---
+
 # AutoStream Conversational AI Agent
 
 ## Project Overview
 This project is a production-quality Conversational AI Agent built for **AutoStream**, a fictional SaaS company. It handles customer inquiries, answers product questions using a Knowledge Base (RAG), and detects high-intent users to seamlessly collect lead information and execute backend lead capture functions.
 
+## Web Interface (Streamlit)
+A highly interactive, modern web interface is included via `Streamlit`. It can be run locally or hosted directly on HuggingFace Spaces.
+
+### Running the Web Interface Locally
+```bash
+streamlit run app.py
+```
+This will open up a browser window where you can converse with the AutoStream Assistant directly.
+
 ## System Architecture
 The system is designed as an agentic workflow using **LangGraph**, replacing traditional linear chatbots with a stateful, branching graph architecture.
 1. **User Input & State Management**: User messages and conversational context are persisted in a shared `AgentState` that tracks details like intent, history, and collected lead fields.
@@ -12,7 +30,7 @@ The system is designed as an agentic workflow using **LangGraph**, replacing tra
 5. **Lead Qualification**: High-intent users are routed to a multi-turn lead collection workflow. The agent selectively asks for missing fields (Name, Email, Creator Platform).
 6. **Tool Execution**: Once all fields are collected, the agent safely executes a simulated backend lead-capture tool.
 
-## Running Locally
+## Running Locally (CLI)
 
 ### Prerequisites
 - Python 3.9+
@@ -30,7 +48,7 @@ The system is designed as an agentic workflow using **LangGraph**, replacing tra
    ```
 
 ### Running the CLI Agent
-To interact with the conversational agent:
+To interact with the conversational agent via the terminal:
 ```bash
 python main.py
 ```

app.py

@@ -0,0 +1,103 @@
+import streamlit as st
+import os
+from dotenv import load_dotenv
+from agent.graph import app
+from agent.state import AgentState
+
+
+load_dotenv()
+
+
+st.set_page_config(page_title="AutoStream AI Sales Assistant", page_icon="🤖", layout="centered")
+
+
+st.markdown("""
+<style>
+    .stChatFloatingInputContainer {
+        bottom: 20px;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+    st.session_state.agent_state = AgentState(
+        conversation_history=[],
+        current_message="",
+        detected_intent=None,
+        retrieved_documents=[],
+        user_name=None,
+        user_email=None,
+        creator_platform=None,
+        lead_ready=False,
+        response=""
+    )
+
+
+    st.session_state.messages.append({"role": "assistant", "content": "Hello! I'm the AutoStream assistant. I can answer questions about our features and pricing. How can I help you today?"})
+
+
+if not os.environ.get("OPENAI_API_KEY"):
+    st.warning("⚠️ OPENAI_API_KEY is not set. Please set it in your environment to use the agent.")
+
+st.title("🤖 AutoStream AI Sales Assistant")
+st.markdown("Ask me about AutoStream features and pricing, or sign up for a plan!")
+
+
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+
+if prompt := st.chat_input("What would you like to know?"):
+
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+
+    st.session_state.agent_state["current_message"] = prompt
+
+
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            try:
+
+                result_state = app.invoke(st.session_state.agent_state)
+                st.session_state.agent_state = result_state
+
+                response = result_state["response"]
+
+
+                st.session_state.agent_state["conversation_history"].append({"role": "user", "content": prompt})
+                st.session_state.agent_state["conversation_history"].append({"role": "assistant", "content": response})
+
+
+                if len(st.session_state.agent_state["conversation_history"]) > 12:
+                    st.session_state.agent_state["conversation_history"] = st.session_state.agent_state["conversation_history"][-12:]
+
+
+                st.markdown(response)
+
+
+                with st.expander("Agent Reasoning & State"):
+                    st.write(f"**Detected Intent:** `{result_state.get('detected_intent', 'UNKNOWN')}`")
+                    if result_state.get("retrieved_documents") and result_state.get("detected_intent") in ["PRODUCT_QUERY", "PRICING_QUERY"]:
+                        st.write(f"**RAG Retrieval:** Found {len(result_state['retrieved_documents'])} relevant knowledge chunks.")
+
+                    st.write("**Lead Data:**")
+                    st.json({
+                        "user_name": result_state.get("user_name"),
+                        "user_email": result_state.get("user_email"),
+                        "creator_platform": result_state.get("creator_platform"),
+                        "lead_ready": result_state.get("lead_ready")
+                    })
+
+            except Exception as e:
+                response = f"An error occurred: {str(e)}"
+                st.error(response)
+
+
+    st.session_state.messages.append({"role": "assistant", "content": response})

requirements.txt

@@ -8,3 +8,4 @@ python-dotenv
 pydantic
 pytest
 pytest-mock
+streamlit