Create app.py

app.py

@@ -0,0 +1,233 @@
+# app.py
+
+import os
+import openai
+import gradio as gr
+from langchain.chains import ConversationalRetrievalChain
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.document_loaders import PyMuPDFLoader, PyPDFLoader
+from langchain.vectorstores import Chroma
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.chat_models import ChatOpenAI
+import shutil  # 用於文件複製
+
+# 獲取 OpenAI API 密鑰
+api_key = os.getenv("OPENAI_API_KEY")
+if not api_key:
+    raise ValueError("未能獲取 OpenAI_API_KEY。請在 Hugging Face Spaces 的 Secrets 中設置它。")
+openai.api_key = api_key
+print("OpenAI API 密鑰已設置。")
+
+# 確保向量資料庫目錄存在且有寫入權限
+VECTORDB_DIR = os.path.abspath("./data")
+os.makedirs(VECTORDB_DIR, exist_ok=True)
+os.chmod(VECTORDB_DIR, 0o755)  # 設置適當的權限
+print(f"VECTORDB_DIR set to: {VECTORDB_DIR}")
+
+# 定義測試 PDF 加載器的函數
+def test_pdf_loader(file_path, loader_type='PyMuPDFLoader'):
+    print(f"Testing PDF loader ({loader_type}) with file: {file_path}")
+    try:
+        if loader_type == 'PyMuPDFLoader':
+            loader = PyMuPDFLoader(file_path)
+        elif loader_type == 'PyPDFLoader':
+            loader = PyPDFLoader(file_path)
+        else:
+            print(f"Unknown loader type: {loader_type}")
+            return
+        loaded_docs = loader.load()
+        if loaded_docs:
+            print(f"Successfully loaded {file_path} with {len(loaded_docs)} documents.")
+            print(f"Document content (first 500 chars): {loaded_docs[0].page_content[:500]}")
+        else:
+            print(f"No documents loaded from {file_path}.")
+    except Exception as e:
+        print(f"Error loading {file_path} with {loader_type}: {e}")
+
+# 定義載入和處理 PDF 文件的函數
+def load_and_process_documents(file_paths, loader_type='PyMuPDFLoader'):
+    documents = []
+    print("開始載入上傳的 PDF 文件。")
+
+    for file_path in file_paths:
+        print(f"載入 PDF 文件: {file_path}")
+        if not os.path.exists(file_path):
+            print(f"文件不存在: {file_path}")
+            continue
+        try:
+            if loader_type == 'PyMuPDFLoader':
+                loader = PyMuPDFLoader(file_path)
+            elif loader_type == 'PyPDFLoader':
+                loader = PyPDFLoader(file_path)
+            else:
+                print(f"Unknown loader type: {loader_type}")
+                continue
+            loaded_docs = loader.load()
+            if loaded_docs:
+                print(f"載入 {file_path} 成功，包含 {len(loaded_docs)} 個文檔。")
+                # 打印第一個文檔的部分內容以確認
+                print(f"第一個文檔內容: {loaded_docs[0].page_content[:500]}")
+                documents.extend(loaded_docs)
+            else:
+                print(f"載入 {file_path} 但未找到任何文檔。")
+        except Exception as e:
+            print(f"載入 {file_path} 時出現錯誤: {e}")
+
+    if not documents:
+        raise ValueError("沒有找到任何 PDF 文件或 PDF 文件無法載入。")
+    else:
+        print(f"總共載入了 {len(documents)} 個文檔。")
+
+    # 分割長文本
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
+    documents = text_splitter.split_documents(documents)
+    print(f"分割後的文檔數量: {len(documents)}")
+
+    if not documents:
+        raise ValueError("分割後的文檔列表為空。請檢查 PDF 文件內容。")
+
+    # 初始化向量資料庫
+    try:
+        embeddings = OpenAIEmbeddings(openai_api_key=api_key)  # 直接傳遞 API 密鑰
+        print("初始化 OpenAIEmbeddings 成功。")
+    except Exception as e:
+        raise ValueError(f"初始化 OpenAIEmbeddings 時出現錯誤: {e}")
+
+    try:
+        vectordb = Chroma.from_documents(
+            documents,
+            embedding=embeddings,
+            persist_directory=VECTORDB_DIR
+        )
+        print("初始化 Chroma 向量資料庫成功。")
+    except Exception as e:
+        raise ValueError(f"初始化 Chroma 向量資料庫時出現錯誤: {e}")
+
+    return vectordb
+
+# 定義聊天處理函數
+def handle_query(user_message, chat_history, vectordb):
+    try:
+        if not user_message:
+            return chat_history
+
+        # 添加角色指令前綴
+        preface = """
+指令: 以繁體中文回答問題，200字以內。你是一位專業心理學家與調酒師，專精於 MBTI 人格與經典調酒主題。
+非相關問題，請回應：「目前僅支援 MBTI 分析與經典調酒主題。」。
+"""
+        query = f"{preface} 查詢內容：{user_message}"
+
+        # 初始化 ConversationalRetrievalChain，並傳遞 openai_api_key
+        pdf_qa = ConversationalRetrievalChain.from_llm(
+            ChatOpenAI(temperature=0.7, model="gpt-4", openai_api_key=api_key),
+            retriever=vectordb.as_retriever(search_kwargs={'k': 6}),
+            return_source_documents=True
+        )
+
+        # 呼叫模型並處理查詢
+        result = pdf_qa.invoke({"question": query, "chat_history": chat_history})
+
+        # 檢查結果並更新聊天歷史
+        if "answer" in result:
+            chat_history = chat_history + [(user_message, result["answer"])]
+        else:
+            chat_history = chat_history + [(user_message, "抱歉，未能獲得有效回應。")]
+        return chat_history
+
+    except Exception as e:
+        return chat_history + [("系統", f"出現錯誤: {str(e)}")]
+
+# 定義 Gradio 的處理函數
+def process_files(files, state):
+    print("process_files called")
+    if files:
+        try:
+            print(f"Received {len(files)} files")
+            saved_file_paths = []
+            for file_path in files:
+                print(f"Processing file: {file_path}")
+                save_path = os.path.join(VECTORDB_DIR, os.path.basename(file_path))
+                # 複製文件到 VECTORDB_DIR
+                shutil.copy(file_path, save_path)
+                # 確認文件是否存在
+                if os.path.exists(save_path):
+                    print(f"File successfully saved to: {save_path}")
+                else:
+                    print(f"Failed to save file to: {save_path}")
+                saved_file_paths.append(save_path)
+                # 測試 PDF 加載器
+                test_pdf_loader(save_path, loader_type='PyMuPDFLoader')
+            # 列出 VECTORDB_DIR 中的所有文件
+            saved_files = os.listdir(VECTORDB_DIR)
+            print(f"Files in VECTORDB_DIR ({VECTORDB_DIR}): {saved_files}")
+            vectordb = load_and_process_documents(saved_file_paths, loader_type='PyMuPDFLoader')
+            state['vectordb'] = vectordb
+            return "PDF 文件已成功上傳並處理。您現在可以開始提問。", state
+        except Exception as e:
+            print(f"Error in process_files: {e}")
+            return f"處理文件時出現錯誤: {e}", state
+    else:
+        return "請上傳至少一個 PDF 文件。", state
+
+def chat_interface(user_message, chat_history, state):
+    vectordb = state.get('vectordb', None)
+    if not vectordb:
+        return chat_history, state, "請先上傳 PDF 文件以進行處理。"
+
+    # 處理查詢
+    updated_history = handle_query(user_message, chat_history, vectordb)
+    return updated_history, state, ""
+
+# 設計 Gradio 介面
+with gr.Blocks() as demo:
+    gr.Markdown("<h1 style='text-align: center;'>MBTI 與經典調酒 AI 助理</h1>")
+
+    # 定義共享的 state
+    state = gr.State({"vectordb": None})
+
+    with gr.Tab("上傳 PDF 文件"):
+        with gr.Row():
+            with gr.Column(scale=1):
+                upload = gr.File(
+                    file_count="multiple",
+                    file_types=[".pdf"],
+                    label="上傳 PDF 文件",
+                    interactive=True,
+                    type="filepath"  # 保持為 "filepath"
+                )
+                upload_btn = gr.Button("上傳並處理")
+                upload_status = gr.Textbox(label="上傳狀態", interactive=False)
+
+    with gr.Tab("聊天機器人"):
+        chatbot = gr.Chatbot()
+
+        with gr.Row():
+            with gr.Column(scale=0.85):
+                txt = gr.Textbox(show_label=False, placeholder="請輸入您的問題...")
+            with gr.Column(scale=0.15, min_width=0):
+                submit_btn = gr.Button("提問")
+
+        # 綁定提問按鈕
+        submit_btn.click(
+            chat_interface,
+            inputs=[txt, chatbot, state],
+            outputs=[chatbot, state, txt]
+        )
+
+        # 綁定輸入框的提交事件
+        txt.submit(
+            chat_interface,
+            inputs=[txt, chatbot, state],
+            outputs=[chatbot, state, txt]
+        )
+
+    # 綁定上傳按鈕
+    upload_btn.click(
+        process_files,
+        inputs=[upload, state],
+        outputs=[upload_status, state]
+    )
+
+# 啟動 Gradio 應用
+demo.launch()