Update app.py

app.py

@@ -1,45 +1,120 @@
+# app.py
 import gradio as gr
+import logging
 
-# （未来会引入更多模块，这里先写占位版）
+# ==== ① 向量检索 & LLM ====
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from langchain.llms import HuggingFacePipeline
+
+logging.basicConfig(level=logging.INFO)
+
+# --- 1) 加载本地向量库 ---
+embedding_model = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/paraphrase-multilingual-mpnet-base-v2"
+)
+vector_store = Chroma(
+    persist_directory="vector_store",
+    embedding_function=embedding_model,
+)
+
+# --- 2) 加载（较轻量）LLM ---
+# 如果 7B 跑不动，可以先用 openchat-mini 试试
+model_id = "openchat/openchat-3.5-0106"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype="auto",
+)
+gen_pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.9,
+)
+llm = HuggingFacePipeline(pipeline=gen_pipe)
+
+# --- 3) 构建 RAG 问答链 ---
+qa_chain = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=vector_store.as_retriever(search_kwargs={"k": 3}),
+)
+
+# ==== ② Gradio UI ====
+
+def simple_qa(user_query):
+    """智能问答：检索 + 生成（单轮演示版）"""
+    if not user_query.strip():
+        return "⚠️ 请输入学习问题，例如：什么是定积分？"
+    try:
+        answer = qa_chain.run(user_query)
+        return answer
+    except Exception as e:
+        logging.error(f"问答失败: {e}")
+        return "抱歉，暂时无法回答，请稍后再试。"
 
 def placeholder_fn(*args, **kwargs):
     return "功能尚未实现，请等待后续更新。"
 
 with gr.Blocks() as demo:
-    gr.Markdown("# Intelligent Learning Assistant v2.0\n— 大学生专业课学习助手 —")
+    gr.Markdown("# 智能学习助手 v2.0\n— 大学生专业课学习助手 —")
 
     with gr.Tabs():
+        # ---------- 智能问答 ----------
         with gr.TabItem("智能问答"):
-            gr.Markdown("（多轮对话模块，待开发）")
-            chat = gr.Chatbot()
-            user_msg = gr.Textbox(placeholder="在此输入您的学习问题")
-            send_button = gr.Button("发送")
-            send_button.click(fn=placeholder_fn, inputs=user_msg, outputs=chat)
+            gr.Markdown("> **示例：** 什么是函数的定义域？")
+            chatbot = gr.Chatbot()
+            user_msg = gr.Textbox(placeholder="输入您的学习问题，然后按回车或点击发送")
+            send_btn = gr.Button("发送")
+
+            # 单轮：把问答显示在 Chatbot
+            def update_chat(message, chat_history):
+                reply = simple_qa(message)
+                chat_history.append((message, reply))
+                return "", chat_history
 
+            send_btn.click(
+                fn=update_chat,
+                inputs=[user_msg, chatbot],
+                outputs=[user_msg, chatbot],
+            )
+            user_msg.submit(
+                fn=update_chat,
+                inputs=[user_msg, chatbot],
+                outputs=[user_msg, chatbot],
+            )
+
+        # ---------- 生成学习大纲 ----------
         with gr.TabItem("生成学习大纲"):
-            gr.Markdown("（学习大纲生成功能，待开发）")
-            topic_input = gr.Textbox(label="主题/章节名称", placeholder="如：线性代数 第五章 特征值与特征向量")
-            gen_button = gr.Button("生成大纲")
-            gen_button.click(fn=placeholder_fn, inputs=topic_input, outputs=topic_input)
+            gr.Markdown("（学习大纲模块，待开发）")
+            topic_input = gr.Textbox(label="主题/章节名称", placeholder="如：线性代数 第五章 特征值")
+            gen_outline_btn = gr.Button("生成大纲")
+            gen_outline_btn.click(placeholder_fn, inputs=topic_input, outputs=topic_input)
 
+        # ---------- 自动出题 ----------
         with gr.TabItem("自动出题"):
-            gr.Markdown("（练习题生成功能，待开发）")
+            gr.Markdown("（出题模块，待开发）")
             topic2 = gr.Textbox(label="知识点/主题", placeholder="如：高数 第三章 多元函数")
-            difficulty2 = gr.Dropdown(choices=["简单", "中等", "困难"], label="题目难度")
-            count2 = gr.Slider(minimum=1, maximum=10, step=1, label="题目数量")
-            gen2_button = gr.Button("开始出题")
-            # 先用 topic2 作为占位输出
-            gen2_button.click(fn=placeholder_fn, inputs=[topic2, difficulty2, count2], outputs=topic2)
+            difficulty2 = gr.Dropdown(choices=["简单", "中等", "困难"], label="难度")
+            count2 = gr.Slider(1, 10, step=1, label="题目数量")
+            gen_q_btn = gr.Button("开始出题")
+            gen_q_btn.click(placeholder_fn, inputs=[topic2, difficulty2, count2], outputs=topic2)
 
+        # ---------- 答案批改 ----------
         with gr.TabItem("答案批改"):
-            gr.Markdown("（答案批改功能，待开发）")
-            std_ans = gr.Textbox(label="标准答案", lines=5, placeholder="请在此粘贴标准答案")
-            user_ans = gr.Textbox(label="您的作答", lines=5, placeholder="请在此输入您的解答")
-            grade_button = gr.Button("开始批改")
-            # 先用 user_ans 作为占位输出
-            grade_button.click(fn=placeholder_fn, inputs=[user_ans, std_ans], outputs=user_ans)
-
-    gr.Markdown("---\nPowered by HuggingFace • v2.0")
+            gr.Markdown("（批改模块，待开发）")
+            std_ans = gr.Textbox(label="标准答案", lines=5)
+            user_ans = gr.Textbox(label="您的作答", lines=5)
+            grade_btn = gr.Button("开始批改")
+            grade_btn.click(placeholder_fn, inputs=[user_ans, std_ans], outputs=user_ans)
+
+    gr.Markdown("---\n由 HuggingFace 提供支持 • 版本 2.0")
 
 if __name__ == "__main__":
     demo.launch()