Update: v1.7

Dockerfile

@@ -63,4 +63,4 @@ USER user
 EXPOSE 8501
 
 # Run streamlit with proper path
-CMD ["python", "-m", "streamlit", "run", "app.py", "--server.address", "0.0.0.0"]
+CMD ["streamlit", "run", "app.py"]

app.py

@@ -3,120 +3,81 @@ 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
+from download import prepare_data
 
-st.set_page_config(page_title="AI Assistant Demo", page_icon="😄")
+# prepare datas
+prepare_data()
+
+# Create an instance of CallbackManager
+callback_manager = CallbackManager()
+
+api_base_url =  "https://api.siliconflow.cn/v1"
+model = "internlm/internlm2_5-7b-chat"
+api_key = st.secrets["API_KEY"]
+
+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()
 
-def init_models():
-    try:
-        print("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:
-            print("Error: API_KEY environment variable is not set")
-            raise ValueError("API_KEY environment variable is not set")
-            
-        print("API key loaded successfully")
-        api_base_url = "https://api.siliconflow.cn/v1"
-        model = "internlm/internlm2_5-7b-chat"
-        
-        print("Initializing callback manager...")
-        callback_manager = CallbackManager()
-
-        print("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
-        print("LLM initialized successfully")
-
-        print("Initializing embedding model...")
-        embed_model = HuggingFaceEmbedding(
-            model_name="/home/user/model/paraphrase-multilingual-MiniLM-L12-v2"
-        )
-        Settings.embed_model = embed_model
-        print("Embedding model initialized successfully")
-
-        print("Loading documents...")
-        documents = SimpleDirectoryReader("/home/user/data").load_data()
-        print(f"Loaded {len(documents)} documents")
-        
-        print("Creating vector store index...")
-        index = VectorStoreIndex.from_documents(documents)
-        
-        print("Creating query engine...")
-        query_engine = index.as_query_engine()
-
-        print("Model initialization completed successfully!")
-        status_placeholder.empty()
-        return query_engine
-
-    except Exception as e:
-        error_msg = f"Error during initialization: {str(e)}"
-        print(error_msg)
-        st.error(error_msg)
-        raise
 
+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
+
 # 检查是否需要初始化模型
 if 'query_engine' not in st.session_state:
-    with st.spinner("正在初始化模型..."):
-        st.session_state['query_engine'] = init_models()
-        st.success("模型初始化完成！")
-
-def generate_response(question):
-    try:
-        print(f"Generating response for question: {question}")
-        response = st.session_state['query_engine'].query(question)
-        print("Response generated successfully")
-        return response
-    except Exception as e:
-        error_msg = f"Error generating response: {str(e)}"
-        print(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？"}]
+    st.session_state['query_engine'] = init_models()
 
-# 显示消息历史
+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？"}]    
+
+    # Display or clear chat messages
 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？"}]
-    print("Chat history cleared")
 
-# 侧边栏按钮
-st.sidebar.button('清除聊天历史', on_click=clear_chat_history)
+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)
 
-# 用户输入处理
+# User-provided prompt
 if prompt := st.chat_input():
-    print(f"Received user input: {prompt}")
     st.session_state.messages.append({"role": "user", "content": prompt})
     with st.chat_message("user"):
         st.write(prompt)
 
-    # 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)
-                    print("Response added to chat history")
+# 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)