Update app.py

app.py

@@ -1,64 +1,63 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from PyPDF2 import PdfReader
+
+# PDF 텍스트 미리 읽어오기
+def extract_pdf_text(pdf_paths):
+    full_text = ""
+    for path in pdf_paths:
+        reader = PdfReader(path)
+        for page in reader.pages:
+            text = page.extract_text()
+            if text:
+                full_text += text + "\n"
+    return full_text.strip()
+
+# 사전 정의된 레퍼런스 문서들
+pdf_context = extract_pdf_text([
+    "assets/Programming-Fundamentals-1570222270.pdf",
+    "assets/1분파이썬_강의자료_전체.pdf"
+])
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # 사용자 입력 + 레퍼런스 문서를 결합
+    messages = [
+        {"role": "system", "content": system_message},
+        {"role": "user", "content": f"아래는 파이썬 프로그래밍 API 레퍼런스입니다:\n{pdf_context}\n\n질문: {message}"}
+    ]
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+    for user_msg, bot_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_msg:
+            messages.append({"role": "assistant", "content": bot_msg})
 
     response = ""
-
-    for message in client.chat_completion(
+    for chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
+        delta = chunk.choices[0].delta.content
+        if delta:
+            response += delta
+            yield response
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a friendly chatbot that answers questions based on the given document.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
+    title="📘 파이썬 API 레퍼런스 챗봇",
+    description="한국공대 수업자료 기반 챗봇입니다. 질문을 입력해 보세요!"
 )
 
-
 if __name__ == "__main__":
     demo.launch()