Update: v1.4

app.py

@@ -1,79 +1,124 @@
 import streamlit as st
+import logging
 from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.legacy.callbacks import CallbackManager
 from llama_index.llms.openai_like import OpenAILike
+import os
 
-# Create an instance of CallbackManager
-callback_manager = CallbackManager()
+# 设置日志
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
-api_base_url =  "https://api.siliconflow.cn/v1"
-model = "internlm/internlm2_5-7b-chat"
-api_key = st.secrets["API_KEY"]
+# 页面配置
+st.set_page_config(
+    page_title="AI Assistant Demo",
+    page_icon="😄",
+    layout="wide"  # 使用宽布局
+)
 
-llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True, callback_manager=callback_manager)
+# 显示加载状态
+status_placeholder = st.empty()
 
-
-
-st.set_page_config(page_title="ai_assistant_demo", page_icon="😄")
-st.title("AI Assistant Demo")
-
-# 初始化模型
-@st.cache_resource
 def init_models():
-    embed_model = HuggingFaceEmbedding(
-        model_name="/home/user/model/paraphrase-multilingual-MiniLM-L12-v2"
-    )
-    Settings.embed_model = embed_model
-
-    #用初始化llm
-    Settings.llm = llm
-
-    documents = SimpleDirectoryReader("/home/user/data").load_data()
-    index = VectorStoreIndex.from_documents(documents)
-    query_engine = index.as_query_engine()
-
-    return query_engine
+    try:
+        logger.info("Starting model initialization...")
+        status_placeholder.text("正在初始化模型...")
+
+        # 初始化 API 设置
+        api_key = os.getenv("API_KEY")
+        if not api_key:
+            raise ValueError("API_KEY environment variable is not set")
+            
+        api_base_url = "https://api.siliconflow.cn/v1"
+        model = "internlm/internlm2_5-7b-chat"
+        
+        logger.info("Initializing callback manager...")
+        callback_manager = CallbackManager()
+
+        logger.info("Initializing LLM...")
+        llm = OpenAILike(
+            model=model,
+            api_base=api_base_url,
+            api_key=api_key,
+            is_chat_model=True,
+            callback_manager=callback_manager
+        )
+        Settings.llm = llm
+
+        logger.info("Initializing embedding model...")
+        embed_model = HuggingFaceEmbedding(
+            model_name="/home/user/model/paraphrase-multilingual-MiniLM-L12-v2"
+        )
+        Settings.embed_model = embed_model
+
+        logger.info("Loading documents...")
+        documents = SimpleDirectoryReader("/home/user/data").load_data()
+        
+        logger.info("Creating vector store index...")
+        index = VectorStoreIndex.from_documents(documents)
+        
+        logger.info("Creating query engine...")
+        query_engine = index.as_query_engine()
+
+        logger.info("Model initialization completed successfully!")
+        status_placeholder.empty()
+        return query_engine
+
+    except Exception as e:
+        error_msg = f"Error during initialization: {str(e)}"
+        logger.error(error_msg)
+        st.error(error_msg)
+        raise
+
+# 初始化标题和说明
+st.title("AI Assistant Demo")
+st.markdown("---")
 
 # 检查是否需要初始化模型
 if 'query_engine' not in st.session_state:
     st.session_state['query_engine'] = init_models()
 
-def greet2(question):
-    response = st.session_state['query_engine'].query(question)
-    return response
-
-      
-# Store LLM generated responses
-if "messages" not in st.session_state.keys():
-    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]    
+def generate_response(question):
+    try:
+        logger.info(f"Generating response for question: {question}")
+        response = st.session_state['query_engine'].query(question)
+        logger.info("Response generated successfully")
+        return response
+    except Exception as e:
+        error_msg = f"Error generating response: {str(e)}"
+        logger.error(error_msg)
+        st.error(error_msg)
+        return None
+
+# 初始化消息历史
+if "messages" not in st.session_state:
+    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
 
-    # Display or clear chat messages
+# 显示消息历史
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.write(message["content"])
 
+# 清除聊天历史的功能
 def clear_chat_history():
     st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
 
-st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
-
-# Function for generating LLaMA2 response
-def generate_llama_index_response(prompt_input):
-    return greet2(prompt_input)
+# 侧边栏按钮
+st.sidebar.button('清除聊天历史', on_click=clear_chat_history)
 
-# User-provided prompt
+# 用户输入处理
 if prompt := st.chat_input():
     st.session_state.messages.append({"role": "user", "content": prompt})
     with st.chat_message("user"):
         st.write(prompt)
 
-# Gegenerate_llama_index_response last message is not from assistant
-if st.session_state.messages[-1]["role"] != "assistant":
-    with st.chat_message("assistant"):
-        with st.spinner("Thinking..."):
-            response = generate_llama_index_response(prompt)
-            placeholder = st.empty()
-            placeholder.markdown(response)
-    message = {"role": "assistant", "content": response.response}
-    st.session_state.messages.append(message)
+    # 生成回复
+    if st.session_state.messages[-1]["role"] != "assistant":
+        with st.chat_message("assistant"):
+            with st.spinner("思考中..."):
+                response = generate_response(prompt)
+                if response:
+                    st.markdown(response)
+                    message = {"role": "assistant", "content": response.response}
+                    st.session_state.messages.append(message)