app.py

import os
import urllib.request
import nest_asyncio
import gradio as gr
import openai
from llama_parse import LlamaParse
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding

# Apply nest_asyncio to allow nested event loops in a synchronous environment
nest_asyncio.apply()

# --- 1. ENVIRONMENT & API INITIALIZATION ---
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
LLAMA_CLOUD_API_KEY = os.environ.get("LLAMA_CLOUD_API_KEY")

if not OPENAI_API_KEY or not LLAMA_CLOUD_API_KEY:
    raise ValueError("Missing essential API credentials. Ensure OPENAI_API_KEY and LLAMA_CLOUD_API_KEY are configured in Secrets.")

openai.api_key = OPENAI_API_KEY
os.environ["LLAMA_CLOUD_API_KEY"] = LLAMA_CLOUD_API_KEY

# --- 2. DATA ACQUISITION & PARSING ---
pdf_path = "apple_10k.pdf"
url = "https://s2.q4cdn.com/470004039/files/doc_financials/2021/q4/_10-K-2021-(As-Filed).pdf"

if not os.path.exists(pdf_path):
    print("Downloading Apple 10-K report...")
    urllib.request.urlretrieve(url, pdf_path)

print("Parsing document via LlamaParse...")
parser = LlamaParse(result_type="markdown")
document = parser.load_data(pdf_path)

with open("apple_10k.md", "w", encoding="utf-8") as f:
    f.write(document[0].text)

# FIXED: Changed deprecated 'parsing_instruction' to 'system_prompt'
documents_with_instruction = LlamaParse(
    result_type="markdown",
    system_prompt="This is the Apple annual report. Make sure the language is English, if not translate it to English."
).load_data(pdf_path)

with open("apple_10k_instructions.md", "w", encoding="utf-8") as f:
    f.write(documents_with_instruction[0].text)

# --- 3. LLAMAINDEX RAG CONFIGURATION ---
Settings.llm = OpenAI(
    model="gpt-5-nano",
    temperature=0.1,
    system_prompt=(
        "You are an expert financial analyst. Your task is to answer questions strictly "
        "and accurately based on the provided Apple 10-K report. Provide concise answers, "
        "directly referencing sections or figures from the report where possible. "
        "If the information is not explicitly present in the document, "
        "clearly state that the answer cannot be found in the provided text."
    )
)
Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")
Settings.chunk_size = 512

reader = SimpleDirectoryReader(input_files=["apple_10k.md", "apple_10k_instructions.md"])
docs = reader.load_data()
index = VectorStoreIndex.from_documents(docs)
query_engine = index.as_query_engine(similarity_top_k=5)

print("LlamaIndex Knowledge Base initialized.")

# --- 4. GRADIO INTERFACE CONFIGURATION ---
custom_css = """
.gradio-container {
    font-family: 'Inter', 'Helvetica Neue', sans-serif !important;
    background: linear-gradient(135deg, #f3f4f6 0%, #e5e7eb 100%);
}
.sidebar-panel {
    background: white;
    border-radius: 16px;
    padding: 20px;
    box-shadow: 0 10px 25px rgba(0,0,0,0.05);
    border: 1px solid #e5e7eb;
}
.gradient-text {
    background: linear-gradient(90deg, #1d4ed8, #9333ea);
    -webkit-background-clip: text;
    -webkit-text-fill-color: transparent;
    font-weight: 800;
}
.stat-card {
    background: linear-gradient(135deg, #1e293b 0%, #0f172a 100%);
    color: white;
    padding: 20px;
    border-radius: 12px;
    margin-bottom: 15px;
    text-align: center;
    box-shadow: 0 4px 6px rgba(0,0,0,0.1);
}
.action-button {
    background: linear-gradient(90deg, #3b82f6, #2563eb);
    border: none;
    color: white;
    font-weight: bold;
}
"""

def chat_with_financial_analyst(user_message, history):
    if not user_message.strip():
        return "", history

    history.append({"role": "user", "content": user_message})
    history.append({"role": "assistant", "content": "Calculating financials..."})
    yield "", history

    try:
        response = query_engine.query(user_message)
        final_answer = str(response)
    except Exception as e:
        final_answer = f"⚠️ **Error querying the document:** {str(e)}"

    history[-1]["content"] = final_answer
    yield "", history

def load_quick_prompt(prompt, history):
    for text, hist in chat_with_financial_analyst(prompt, history):
        pass
    return "", hist

# FIXED: Removed 'css=custom_css' from gr.Blocks() (Moved to app.launch())
with gr.Blocks(fill_width=True) as app:
    with gr.Row():
        gr.HTML("""
        <div style='text-align: center; padding: 20px 0;'>
            <img src='https://upload.wikimedia.org/wikipedia/commons/f/fa/Apple_logo_black.svg' width='50' style='margin: 0 auto 10px auto;'/>
            <h1 class='gradient-text' style='margin: 0; font-size: 2.5em;'>Apple Intelligence: 10-K Financial Oracle</h1>
            <p style='color: #64748b; font-size: 1.1em;'>Powered by LlamaIndex, OpenAI, and LlamaParse</p>
        </div>
        """)

    with gr.Row():
        with gr.Column(scale=1, elem_classes="sidebar-panel"):
            gr.HTML("<h3 style='color: #0f172a; margin-top: 0;'>📊 Document Context</h3>")
            
            gr.Image(
                value="https://images.unsplash.com/photo-1611974789855-9c2a0a7236a3?q=80&w=1000&auto=format&fit=crop",
                show_label=False,
                container=False,
                height=180
            )

            gr.HTML("""
            <div class='stat-card' style='margin-top: 15px;'>
                <h4 style='margin: 0; color: #94a3b8;'>Active Document</h4>
                <h2 style='margin: 5px 0; color: white;'>AAPL 2021 10-K</h2>
                <p style='margin: 0; font-size: 0.8em; color: #38bdf8;'>Vector Indexed & Parsed</p>
            </div>
            """)

            # FIX: Explicit inline styling with !important flags prevents system dark-mode overrides
            gr.HTML(
                """
                <div style='color: #1e293b; font-size: 0.95em; line-height: 1.6;'>
                   <strong style='color: #0f172a; font-size: 1.1em; display: block; margin-bottom: 8px;'>Capabilities:</strong>
                   <ul style='padding-left: 20px; margin-top: 5px; list-style-type: none;'>
                       <li style='color: #1e293b !important; margin-bottom: 6px;'>📈 Extracts exact revenue and profit figures.</li>
                       <li style='color: #1e293b !important; margin-bottom: 6px;'>⚠️ Analyzes corporate risk factors.</li>
                       <li style='color: #1e293b !important; margin-bottom: 6px;'>📊 Interprets 5-year cumulative return charts.</li>
                       <li style='color: #1e293b !important; margin-bottom: 6px;'>🌐 Translates complex financial jargon.</li>
                   </ul>
                </div>
                """
            )

        with gr.Column(scale=3):
            # FIXED: Removed type="messages" (This is what caused your fatal error)
            chatbot = gr.Chatbot(
                label="Financial Expert AI",
                height=550,
                avatar_images=(
                    "https://cdn-icons-png.flaticon.com/512/3135/3135715.png",
                    "https://cdn-icons-png.flaticon.com/512/12108/12108151.png"
                )
            )

            with gr.Row():
                msg_input = gr.Textbox(
                    show_label=False,
                    placeholder="Ask about Apple's net sales, iPhone revenue, or operational risks...",
                    container=False,
                    scale=4
                )
                submit_btn = gr.Button("Analyze ⚡", variant="primary", scale=1, elem_classes="action-button")

            gr.Markdown("### ⚡ Quick Actions")
            with gr.Row():
                btn_revenue = gr.Button("💰 Summarize Stock Classes", size="sm")
                btn_risk = gr.Button("⚠️ Filing Regulations", size="sm")
                btn_chart = gr.Button("📈 Explain Context", size="sm")
                btn_clear = gr.Button("🗑️ Clear Chat", size="sm", variant="secondary")

    # Event binding workflows
    msg_input.submit(fn=chat_with_financial_analyst, inputs=[msg_input, chatbot], outputs=[msg_input, chatbot])
    submit_btn.click(fn=chat_with_financial_analyst, inputs=[msg_input, chatbot], outputs=[msg_input, chatbot])

    btn_revenue.click(
        fn=lambda history: load_quick_prompt("Summarize the common stocks and notes listed in the report.", history),
        inputs=[chatbot],
        outputs=[msg_input, chatbot]
    )
    btn_risk.click(
        fn=lambda history: load_quick_prompt("What does 'Annual Report pursuant to Section 13 or 15(d) of the Securities Exchange Act of 1934' signify?", history),
        inputs=[chatbot],
        outputs=[msg_input, chatbot]
    )
    btn_chart.click(
        fn=lambda history: load_quick_prompt("Does the document contain numbers validating the 5-Year Cumulative Total Return chart?", history),
        inputs=[chatbot],
        outputs=[msg_input, chatbot]
    )
    btn_clear.click(lambda: [], None, chatbot, queue=False)

# FIXED: Passed BOTH theme and css inside the app.launch() method
app.launch(theme=gr.themes.Ocean(primary_hue="blue", neutral_hue="slate"), css=custom_css)