Update app.py

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
 import os
-import logging
 from langchain.chains import ConversationalRetrievalChain
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.document_loaders import PyPDFLoader, Docx2txtLoader, TextLoader
@@ -8,9 +7,6 @@ from langchain_community.vectorstores import Chroma
 from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from dotenv import load_dotenv
 
-# 設定日誌級別，顯示更多詳細資訊
-logging.basicConfig(level=logging.DEBUG)
-
 # 加載環境變量
 load_dotenv()
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
@@ -20,9 +16,12 @@ api_key = os.getenv('OPENAI_API_KEY')
 if not api_key:
     raise ValueError("請設置 'OPENAI_API_KEY' 環境變數")
 
+# OpenAI API key
+openai_api_key = api_key
+
 # 將聊天歷史轉換為適合 LangChain 的二元組格式
 def transform_history_for_langchain(history):
-    return [(chat[0], chat[1]) for chat in history if chat[0]]
+    return [(chat[0], chat[1]) for chat in history if chat[0]]  # 使用整數索引來訪問元組中的元素
 
 # 將 Gradio 的歷史紀錄轉換為 OpenAI 格式
 def transform_history_for_openai(history):
@@ -49,11 +48,9 @@ def load_and_process_documents(folder_path):
             loader = TextLoader(file_path)
             documents.extend(loader.load())
 
-    # 使用 CharacterTextSplitter 分割文檔
     text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=10)
     documents = text_splitter.split_documents(documents)
 
-    # 建立向量數據庫
     vectordb = Chroma.from_documents(
         documents,
         embedding=OpenAIEmbeddings(),
@@ -82,7 +79,7 @@ def handle_query(user_message, temperature, chat_history):
         previous_answers = transform_history_for_langchain(chat_history)
 
         pdf_qa = ConversationalRetrievalChain.from_llm(
-            ChatOpenAI(temperature=temperature, model_name='gpt-4'),  # 修正模型名稱
+            ChatOpenAI(temperature=temperature, model_name='gpt-4o'),
             retriever=vectordb.as_retriever(search_kwargs={'k': 6}),
             return_source_documents=True,
             verbose=False
@@ -101,20 +98,19 @@ def handle_query(user_message, temperature, chat_history):
         return chat_history
 
     except Exception as e:
-        logging.error(f"處理查詢時出現錯誤: {e}")
         return chat_history + [("系統", f"出現錯誤: {str(e)}")]
 
 # 使用 Gradio 的 Blocks API 創建自訂聊天介面
 with gr.Blocks() as demo:
     gr.Markdown("<h1 style='text-align: center;'>AI 小助教</h1>")
 
-    chatbot = gr.Chatbot(type='messages')  # 指定 type='messages'
+    chatbot = gr.Chatbot()
     state = gr.State([])
 
     with gr.Row():
-        with gr.Column(scale=8):  # 使用整數 scale
+        with gr.Column(scale=0.85):
             txt = gr.Textbox(show_label=False, placeholder="請輸入您的問題...")
-        with gr.Column(scale=2, min_width=0):  # 使用整數 scale
+        with gr.Column(scale=0.15, min_width=0):
             submit_btn = gr.Button("提問")
 
     # 用戶輸入後立即顯示提問文字，不添加回應部分，並清空輸入框
@@ -138,5 +134,5 @@ with gr.Blocks() as demo:
         bot_response, state, [chatbot, state]
     )
 
-# 啟動 Gradio 應用，啟用 share=True 生成公開連結
-demo.launch(share=True)
+# 啟動 Gradio 應用
+demo.launch()