Update app.py

app.py

@@ -5,112 +5,78 @@ from openai import OpenAI
 
 UPSTAGE_API_KEY = os.getenv("UPSTAGE_API_KEY")
 
-def parse_document(filename):
-    """Parses a PDF document using the Upstage Document Parse API and returns the extracted HTML."""
-
-    # Define the API endpoint
+def parse_document(file):
     url = "https://api.upstage.ai/v1/document-ai/document-parse"
-
-    # Set the authorization header with your API key
     headers = {'Authorization': f'Bearer {UPSTAGE_API_KEY}'}
-
-    # Open the PDF file in binary mode and attach it to the request
-    files = {"document": open(filename, "rb")}
-
-    # Define additional request parameters
+    files = {"document": open(file.name, "rb")}
     data = {
-        "base64_encoding": "['table']",  # Request base64 encoding of table elements
-        "model": "document-parse"        # Specify the model to use
+        "base64_encoding": "['table']",
+        "model": "document-parse"
     }
-    # Send the POST request to the API
-    response = requests.post(url, headers=headers, files=files, data=data)
 
-    # Parse the JSON response
+    response = requests.post(url, headers=headers, files=files, data=data)
     result = response.json()
-
-    # For debugging: print the entire API response
-    # print(response.json())
-
-    # Extract the HTML content from the response
     html_text = result.get("content", {}).get("html", "")
-
     return html_text
-    
+
 def chat_with_document(history, html_text, user_question):
-    """Handles multi-turn Q&A based on the parsed HTML document using Upstage Solar Pro LLM."""
+    if not html_text.strip():
+        return history, history, "⚠️ 먼저 문서를 변환해주세요."
 
-    # Initialize the OpenAI client for Solar LLM
     client = OpenAI(
         api_key=UPSTAGE_API_KEY,
         base_url="https://api.upstage.ai/v1"
     )
 
-    # If this is the first turn, initialize an empty history
     history = history or []
 
-    # Construct a system prompt with instructions and the HTML content
     system_prompt = f"""The following is a financial statement document extracted in HTML format.
-                        Please answer user questions accurately and concisely in Korean, based on the text within HTML tags.
-                        
-                        Document:
-                        {html_text}
-                    """
+    Please answer user questions accurately and concisely in Korean, based on the text within HTML tags.
+
+    Document:
+    {html_text}
+    """
 
-    # Build the conversation history for the chat model
     messages = [{"role": "system", "content": system_prompt}]
     for user, bot in history:
         messages.append({"role": "user", "content": user})
         messages.append({"role": "assistant", "content": bot})
-
-    # Add the current user question
     messages.append({"role": "user", "content": user_question})
 
-    # Call the Solar LLM to generate a response
-    response = client.chat.completions.create(
-        model="solar-pro",
-        messages=messages,
-        temperature=0,
-        max_tokens=1024
-    )
-
-    # Extract the assistant's reply
-    bot_reply = response.choices[0].message.content
+    try:
+        response = client.chat.completions.create(
+            model="solar-pro",
+            messages=messages,
+            temperature=0,
+            max_tokens=1024
+        )
+        bot_reply = response.choices[0].message.content
+    except Exception as e:
+        bot_reply = f"⚠️ 오류가 발생했습니다: {str(e)}"
 
-    # Update the chat history
     history.append((user_question, bot_reply))
-
-    # Return updated chatbot display, state, and clear the input
     return history, history, ""
 
-    
-def set_example_question(example_text):
-    return example_text
-
 def toggle_html_view(current_html, is_visible):
     return (
-        gr.update(value=current_html, visible=not is_visible),  # html_output toggle
-        gr.update(value=current_html, visible=is_visible),      # html_display 반대로 toggle
+        gr.update(value=current_html, visible=not is_visible),
+        gr.update(value=current_html, visible=is_visible),
         not is_visible
     )
 
-
-# Gradio UI
 with gr.Blocks() as demo:
+
     gr.Markdown("# 📄 재무제표 분석 챗봇")
     gr.Markdown("1. Document Parse API로 PDF 문서를 HTML로 변환합니다.\n"
-                "2. Solar LLM을 통해 문서 기반 질문에 답변합니다.\n"
-                "예제 파일은 Files 버튼을 클릭하면 확인 및 다운로드 가능합니다."
-               )
+                "2. Solar LLM을 통해 문서 기반 질문에 답변합니다.")
+    gr.Markdown("예제 파일은 Files 버튼을 클릭하면 확인 및 다운로드 가능합니다.")
 
     with gr.Row():
         file_input = gr.File(label="📎 재무제표 업로드")
         parse_btn = gr.Button("문서 HTML 변환")
 
-    # html_output = gr.Textbox(label="📘 문서 내용", lines=10, visible=True)
-    # html_display = gr.HTML(visible=False)
     html_output = gr.Textbox(label="📘 문서 내용", lines=10, visible=True, elem_id="scrollable-html")
     html_display = gr.HTML(visible=False, elem_id="scrollable-html-display")
-
     toggle_html_btn = gr.Button("🔁 HTML 보기 전환")
     html_visible_state = gr.State(False)
 
@@ -124,7 +90,6 @@ with gr.Blocks() as demo:
     chatbot = gr.Chatbot(label="💬 문서 기반 Q&A", height=400)
     user_question = gr.Textbox(label="❓ 질문을 입력하세요", lines=2)
     answer_btn = gr.Button("답변 생성")
-
     chat_state = gr.State([])
 
     with gr.Row():
@@ -132,8 +97,28 @@ with gr.Blocks() as demo:
         ex1 = gr.Button("어떤 기업의 재무제표인가요?")
         ex2 = gr.Button("Q3 분기의 총 매출액은 얼마인가요?")
 
-    ex1.click(set_example_question, inputs=[], outputs=user_question)
-    ex2.click(set_example_question, inputs=[], outputs=user_question)
+    # 예제 질문 → 질문 입력 + 자동 응답
+    ex1.click(
+        fn=lambda: "어떤 기업의 재무제표인가요?",
+        inputs=[],
+        outputs=user_question
+    ).then(
+        fn=chat_with_document,
+        inputs=[chat_state, html_output, user_question],
+        outputs=[chatbot, chat_state, user_question],
+        show_progress=True
+    )
+
+    ex2.click(
+        fn=lambda: "Q3 분기의 총 매출액은 얼마인가요?",
+        inputs=[],
+        outputs=user_question
+    ).then(
+        fn=chat_with_document,
+        inputs=[chat_state, html_output, user_question],
+        outputs=[chatbot, chat_state, user_question],
+        show_progress=True
+    )
 
     answer_btn.click(
         fn=chat_with_document,
@@ -141,17 +126,58 @@ with gr.Blocks() as demo:
         outputs=[chatbot, chat_state, user_question],
         show_progress=True
     )
+
 demo.css = """
+body {
+    background-color: #F4F4FF;
+    color: #2F22A4;
+    font-family: 'Arial', sans-serif;
+}
+.markdown h1, .markdown h2 {
+    color: #2F22A4;
+}
+button {
+    background-color: #805CFB;
+    color: white;
+    border-radius: 8px;
+    padding: 8px 16px;
+    font-weight: bold;
+    border: none;
+}
+button:hover {
+    background-color: #6457DE;
+}
+input[type="file"] {
+    border: 1px solid #AEB3FA;
+    background-color: #E6EAFD;
+    color: #2F22A4;
+    border-radius: 8px;
+    padding: 6px;
+}
+textarea, input[type="text"] {
+    background-color: #FFFFFF;
+    border: 1px solid #AEB3FA;
+    border-radius: 8px;
+    padding: 8px;
+    color: #2F22A4;
+}
+.chatbot {
+    background-color: #E6EAFD;
+    border-radius: 12px;
+    padding: 12px;
+    border: 1px solid #AEB3FA;
+}
 #scrollable-html, #scrollable-html-display {
     max-height: 400px;
     overflow: auto;
-    border: 1px solid #AEB3FA;  /* Primary 30 */
+    border: 1px solid #AEB3FA;
     padding: 16px;
-    background-color: #F4F4FF;  /* Primary 10 */
+    background-color: #F4F4FF;
     border-radius: 12px;
     font-family: 'Arial', sans-serif;
-    color: #2F22A4;             /* Primary 60 */
-    box-shadow: 0 2px 6px rgba(128, 92, 251, 0.1);  /* Ups Purple */
+    color: #2F22A4;
+    font-size: 14px;
+    box-shadow: 0 2px 6px rgba(128, 92, 251, 0.1);
 }
 """