"""
Viz LLM - Gradio App

A RAG-powered assistant for data visualization guidance, powered by Jina-CLIP-v2
embeddings and research from the field of information graphics.
"""

import os
import gradio as gr
from dotenv import load_dotenv
from src.rag_pipeline import create_pipeline
from datetime import datetime, timedelta
from collections import defaultdict

# Load environment variables
load_dotenv()

# Rate limiting: Track requests per user (IP-based)
# Format: {ip: [(timestamp1, timestamp2, ...)]}
rate_limit_tracker = defaultdict(list)
DAILY_LIMIT = 20

# Initialize the RAG pipeline
print("Initializing Graphics Design Pipeline...")
try:
    pipeline = create_pipeline(
        retrieval_k=5,
        model=os.getenv("LLM_MODEL", "meta-llama/Llama-3.1-8B-Instruct"),
        temperature=float(os.getenv("LLM_TEMPERATURE", "0.2"))
    )
    print("✓ Pipeline initialized successfully")
except Exception as e:
    print(f"✗ Error initializing pipeline: {e}")
    raise


def check_rate_limit(request: gr.Request) -> tuple[bool, int]:
    """Check if user has exceeded rate limit"""
    if request is None:
        return True, DAILY_LIMIT  # Allow if no request object

    user_id = request.client.host
    now = datetime.now()
    cutoff = now - timedelta(days=1)

    # Remove old requests (older than 24 hours)
    rate_limit_tracker[user_id] = [
        ts for ts in rate_limit_tracker[user_id] if ts > cutoff
    ]

    remaining = DAILY_LIMIT - len(rate_limit_tracker[user_id])

    if remaining <= 0:
        return False, 0

    # Add current request
    rate_limit_tracker[user_id].append(now)
    return True, remaining - 1


def recommend_stream(message: str, history: list, request: gr.Request):
    """
    Streaming version of design recommendation function

    Args:
        message: User's design query
        history: Chat history
        request: Gradio request object for rate limiting

    Yields:
        Response chunks
    """
    # Check rate limit
    allowed, remaining = check_rate_limit(request)
    if not allowed:
        yield "⚠️ **Rate limit exceeded.** You've reached the maximum of 20 queries per day. Please try again in 24 hours."
        return

    try:
        response_stream = pipeline.generate_recommendations(message, stream=True)
        full_response = ""
        for chunk in response_stream:
            full_response += chunk
            yield full_response

        # Add rate limit info at the end
        if remaining <= 5:
            yield full_response + f"\n\n---\n*You have {remaining} queries remaining today.*"
    except Exception as e:
        yield f"Error generating response: {str(e)}\n\nPlease check your environment variables (HF_TOKEN, SUPABASE_URL, SUPABASE_KEY) and try again."


# Minimal CSS to fix UI artifacts
custom_css = """
/* Hide retry/undo buttons that appear as artifacts */
.chatbot button[aria-label="Retry"],
.chatbot button[aria-label="Undo"] {
    display: none !important;
}

/* Remove overflow-y scroll from textarea */
textarea[data-testid="textbox"] {
    overflow-y: hidden !important;
}
"""

# Create Gradio interface
with gr.Blocks(
    title="Viz LLM",
    css=custom_css
) as demo:
    gr.Markdown("""
    # 📊 Viz LLM

    Get design recommendations for creating effective data visualizations based on research and best practices.
    """)

    # Main chat interface
    chatbot = gr.ChatInterface(
        fn=recommend_stream,
        type="messages",
        examples=[
            "What's the best chart type for showing trends over time?",
            "How do I create an effective infographic for complex data?",
            "What are best practices for data visualization accessibility?",
            "How should I design a dashboard for storytelling?",
            "What visualization works best for comparing categories?"
        ],
        cache_examples=False,
        api_name="recommend"
    )

    # Knowledge base section (below chat interface)
    gr.Markdown("""
    ### Knowledge Base

    This assistant draws on research papers, design principles, and examples from the field of information graphics and data visualization.

    **Credits:** Special thanks to the researchers whose work informed this model: Robert Kosara, Edward Segel, Jeffrey Heer, Matthew Conlen, John Maeda, Kennedy Elliott, Scott McCloud, and many others.

    ---

    **Usage Limits:** This service is limited to 20 queries per day per user to manage costs. Responses are optimized for English.

    <div style="text-align: center; margin-top: 20px; opacity: 0.6; font-size: 0.9em;">
    Embeddings: Jina-CLIP-v2
    </div>
    """)

# Launch configuration
if __name__ == "__main__":
    # Check for required environment variables
    required_vars = ["SUPABASE_URL", "SUPABASE_KEY", "HF_TOKEN"]
    missing_vars = [var for var in required_vars if not os.getenv(var)]

    if missing_vars:
        print(f"⚠️  Warning: Missing environment variables: {', '.join(missing_vars)}")
        print("Please set these in your .env file or as environment variables")

    # Launch the app
    demo.launch(
        server_name="0.0.0.0",
        server_port=7860,
        share=False,
        show_api=True
    )