app.py

#!/usr/bin/env python3
"""
FAR Chatbot - Hugging Face Spaces Version
Federal Acquisition Regulation Assistant with Clickable Citations
"""

import streamlit as st
import time
import logging
import os
import sys
import re
from datetime import datetime

# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

# Import the chatbot
from far_chatbot import FARChatbot

try:
    import markdown
except ImportError:
    markdown = None

# Configure page
st.set_page_config(
    page_title="FAR Chatbot - Federal Acquisition Regulation Assistant",
    page_icon="🏛️",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Authentication
VALID_CREDENTIALS = {"testuser": "farbot2025"}

def check_password():
    def password_entered():
        username = st.session_state.get("username", "")
        password = st.session_state.get("password", "")
        if username in VALID_CREDENTIALS and VALID_CREDENTIALS[username] == password:
            st.session_state["authenticated"] = True
            del st.session_state["password"]
        else:
            st.session_state["authenticated"] = False

    if "authenticated" not in st.session_state:
        st.session_state["authenticated"] = False

    if not st.session_state["authenticated"]:
        col1, col2, col3 = st.columns([1, 2, 1])
        with col2:
            st.markdown("## 🏛️ FAR Chatbot Login")
            st.text_input("Username", key="username")
            st.text_input("Password", type="password", key="password")
            st.button("🔐 Log In", on_click=password_entered, type="primary", use_container_width=True)
            if st.session_state.get("authenticated") == False and "username" in st.session_state and st.session_state["username"]:
                st.error("❌ Invalid credentials")
        return False
    return True

if not check_password():
    st.stop()

# CSS Styling
st.markdown("""
<style>
    .main-header {
        text-align: center; padding: 1.5rem;
        background: linear-gradient(135deg, #1a365d 0%, #2c5282 50%, #2b6cb0 100%);
        color: white; border-radius: 16px; margin-bottom: 2rem;
    }
    .main-header h1 { margin: 0; font-size: 2.5rem; }
    .main-header p { margin: 0.5rem 0 0 0; opacity: 0.9; }
    .user-message {
        background: #f7fafc; padding: 1rem; border-radius: 16px;
        margin: 1rem 0; border-left: 4px solid #e53e3e;
    }
    .bot-message {
        background: linear-gradient(135deg, #ebf8ff 0%, #e6fffa 100%);
        padding: 1.25rem; border-radius: 16px; margin: 1rem 0;
        border-left: 4px solid #2b6cb0;
    }
    .citation-link {
        background: linear-gradient(135deg, #fef3c7 0%, #fde68a 100%);
        padding: 2px 8px; border-radius: 6px; font-family: monospace;
        font-weight: 600; color: #92400e; text-decoration: none;
        border: 1px solid #f59e0b;
    }
    .citation-link:hover { background: #fde68a; }
    .source-card {
        background: white; border: 1px solid #e2e8f0;
        border-radius: 12px; padding: 1rem; margin: 0.75rem 0;
    }
</style>
""", unsafe_allow_html=True)

# Session state
if 'chatbot' not in st.session_state:
    st.session_state.chatbot = None
if 'chat_history' not in st.session_state:
    st.session_state.chat_history = []
if 'show_sources' not in st.session_state:
    st.session_state.show_sources = True

@st.cache_resource
def load_chatbot():
    """Load the FAR chatbot"""
    try:
        logger.info("Loading FAR Chatbot...")
        chatbot = FARChatbot(
            faiss_index_path="data/faiss_index.index",
            texts_path="data/texts.txt",
            use_gpt5=True
        )
        return chatbot
    except Exception as e:
        logger.error(f"Error loading chatbot: {e}")
        st.error(f"Error loading chatbot: {e}")
        return None

def get_acquisition_gov_url(citation: str) -> str:
    base_citation = re.sub(r'\([a-z]\)$', '', citation)
    return f"https://www.acquisition.gov/far/{base_citation}"

def make_citations_clickable(response: str, search_results: list) -> str:
    if not markdown:
        return response
    
    text = response
    
    def make_link(citation):
        url = get_acquisition_gov_url(citation)
        return f'<a href="{url}" target="_blank" class="citation-link">'
    
    # Replace citation patterns
    text = re.sub(r'\[FAR\s+(\d+\.\d+(?:-\d+)?(?:\([a-z]\))?)\]', 
                  lambda m: f'{make_link(m.group(1))}[{m.group(1)}]</a>', text)
    text = re.sub(r'\[(\d+\.\d+(?:-\d+)?(?:\([a-z]\))?)\]',
                  lambda m: f'{make_link(m.group(1))}[{m.group(1)}]</a>', text)
    text = re.sub(r'(?<!View )FAR\s+(\d+\.\d+(?:-\d+)?(?:\([a-z]\))?)',
                  lambda m: f'{make_link(m.group(1))}FAR {m.group(1)}</a>', text)
    
    return markdown.markdown(text, extensions=['tables', 'fenced_code', 'nl2br'])

# Header
st.markdown("""
<div class="main-header">
    <h1>🏛️ FAR Chatbot</h1>
    <p>Federal Acquisition Regulation Assistant</p>
</div>
""", unsafe_allow_html=True)

# Sidebar
with st.sidebar:
    st.markdown("## ⚙️ Settings")
    
    if st.session_state.chatbot is None:
        st.session_state.chatbot = load_chatbot()
    
    if st.session_state.chatbot:
        st.success("✅ Chatbot Ready!")
    else:
        st.error("❌ Failed to load")
    
    st.session_state.show_sources = st.checkbox("Show sources", value=True)
    
    st.markdown("### 💡 Sample Questions")
    samples = [
        "What are small business set-asides?",
        "Explain the simplified acquisition threshold",
        "What is the micro-purchase threshold?",
        "When can I use sole source?"
    ]
    for q in samples:
        if st.button(f"💬 {q}", key=f"s_{hash(q)}"):
            st.session_state.current_question = q
            st.rerun()
    
    if st.button("🗑️ Clear Chat"):
        st.session_state.chat_history = []
        st.rerun()
    
    if st.button("🚪 Logout"):
        st.session_state["authenticated"] = False
        st.rerun()

# Main content
if st.session_state.chatbot is None:
    st.error("Chatbot not loaded")
    st.stop()

# Display chat history
for entry in st.session_state.chat_history:
    question, answer, search_results, timestamp = entry[:4]
    
    st.markdown(f'<div class="user-message">👤 <b>You:</b> {question}</div>', unsafe_allow_html=True)
    
    formatted = make_citations_clickable(answer, search_results)
    st.markdown(f'<div class="bot-message">🤖 <b>FAR Bot:</b><br>{formatted}</div>', unsafe_allow_html=True)
    
    if st.session_state.show_sources and search_results:
        with st.expander("📚 Sources"):
            for cit, txt in search_results[:5]:
                url = get_acquisition_gov_url(cit)
                st.markdown(f"**[FAR {cit}]({url})**: {txt[:300]}...")

# Input
st.markdown("## 💬 Ask a Question")

question = ""
if 'current_question' in st.session_state:
    question = st.session_state.current_question
    del st.session_state.current_question

question = st.text_input("Your question:", value=question, placeholder="Ask about FAR regulations...")

if st.button("🚀 Ask", type="primary") and question.strip():
    with st.spinner("Processing..."):
        try:
            result = st.session_state.chatbot.chat(question, top_k=None)
            
            timestamp = datetime.now().strftime("%H:%M")
            st.session_state.chat_history.append((
                question,
                result['response'],
                result.get('search_results', []),
                timestamp
            ))
            st.rerun()
        except Exception as e:
            st.error(f"Error: {e}")

st.markdown("---")
st.markdown("🏛️ FAR Chatbot | Powered by GPT-4 Turbo | [acquisition.gov](https://acquisition.gov)")