# app.py import streamlit as st import datetime import os # Import all necessary modules from your project from config import GOOGLE_API_KEY, STUDENT_DB_PATH, CHROMA_DB_PATH, RAG_COLLECTION_NAME from db_manager import init_student_db, get_all_student_names, get_student_characteristics, add_or_update_student from rag_manager import add_documents_to_rag, query_rag # get_all_student_observations_from_rag is used by chat_processor from chat_processor import extract_info_from_chat, update_student_characteristics_from_rag, batch_update_all_students_characteristics from feedback_generator import ( generate_boss_feedback, generate_public_feedback, generate_parent_feedback, get_events_summary_for_day ) # import prompts # Prompts are used by other modules, not directly here typically # --- Page Configuration and Initialization --- st.set_page_config(page_title="晚托反馈助手", layout="wide", initial_sidebar_state="expanded") # --- Check API Key --- # On Hugging Face, this will be set via Secrets. For local, from .env or environment. if not GOOGLE_API_KEY: st.error("错误：GOOGLE_API_KEY 未配置。请在Hugging Face Space的Secrets中设置该值，或在本地的.env文件中配置。应用功能将受限。") # st.stop() # Option to stop app, or let it run with limited functionality # --- Initialize Databases (Idempotent) --- # These functions now have internal error handling and directory creation init_student_db() # For SQLite # ChromaDB is initialized within rag_manager.py upon import/first use. # --- Session State Management --- # Helps persist data across Streamlit reruns if 'processed_chat_extracts' not in st.session_state: # Renamed for clarity st.session_state.processed_chat_extracts = [] # Stores list of {"student_name": ..., "observation": ...} if 'current_processing_date' not in st.session_state: # Renamed st.session_state.current_processing_date = datetime.date.today() if 'student_list_cache' not in st.session_state: # Renamed st.session_state.student_list_cache = get_all_student_names() # Initial load # Feedback text states if 'feedback_boss_text' not in st.session_state: st.session_state.feedback_boss_text = "" if 'feedback_public_text' not in st.session_state: st.session_state.feedback_public_text = "" if 'feedback_parent_text' not in st.session_state: st.session_state.feedback_parent_text = "" if 'selected_student_for_parent_fb' not in st.session_state: st.session_state.selected_student_for_parent_fb = None # --- Helper Functions for UI --- def refresh_student_list_cache(): st.session_state.student_list_cache = get_all_student_names() st.toast("学生列表已刷新。") # --- Main Application UI --- st.title("🚀 晚托反馈自动化助手") # Sidebar for navigation and info with st.sidebar: st.header("导航") menu_options = ["处理聊天记录", "生成反馈报告", "学生特点管理"] choice = st.radio("选择功能:", menu_options, key="nav_menu") st.markdown("---") st.subheader("系统状态") if GOOGLE_API_KEY: st.success("Gemini API Key 已加载。") else: st.warning("Gemini API Key 未配置。") # Simple check if DB files exist (more robust checks are within db/rag managers) # These paths are inside the container / HF Space file system student_db_exists = os.path.exists(STUDENT_DB_PATH) chroma_dir_exists = os.path.exists(CHROMA_DB_PATH) and os.listdir(CHROMA_DB_PATH) # Check if dir exists and is not empty if student_db_exists: st.markdown(f"✔️ 学生库: `{STUDENT_DB_PATH}`") else: st.markdown(f"⚠️ 学生库未找到: `{STUDENT_DB_PATH}`") if chroma_dir_exists: st.markdown(f"✔️ RAG库: `{CHROMA_DB_PATH}` (集合: {RAG_COLLECTION_NAME})") else: st.markdown(f"⚠️ RAG库未找到: `{CHROMA_DB_PATH}`") if st.button("🔄 刷新学生列表", key="sidebar_refresh_students"): refresh_student_list_cache() # --- Page 1: 处理聊天记录 --- if choice == "处理聊天记录": st.header("💬 聊天记录处理与数据构建") st.markdown("在此粘贴每日微信聊天记录，AI将提取关键信息并存入知识库。") # Date selection for the chat log selected_date_for_processing = st.date_input( "请选择聊天记录对应的日期", value=st.session_state.current_processing_date, # Use session state for persistence key="chat_date_input" ) # Update session state if date changes if selected_date_for_processing != st.session_state.current_processing_date: st.session_state.current_processing_date = selected_date_for_processing st.session_state.processed_chat_extracts = [] # Clear old extracts if date changes st.experimental_rerun() chat_log_text = st.text_area("在此粘贴聊天记录内容:", height=250, key="chat_log_input_area", help="输入聊天内容后，点击“分析聊天记录”。") if st.button("🤖 使用AI分析聊天记录", type="primary", key="analyze_chat_button"): if not chat_log_text.strip(): st.warning("请输入聊天记录内容。") elif not GOOGLE_API_KEY: st.error("API Key未配置，无法分析。") else: with st.spinner("AI正在分析聊天记录，提取信息中..."): st.session_state.processed_chat_extracts = extract_info_from_chat(chat_log_text) if st.session_state.processed_chat_extracts: st.success(f"AI成功提取到 {len(st.session_state.processed_chat_extracts)} 条信息！") else: st.info("AI分析完成，但未能从聊天记录中提取到格式化信息。") # No st.error here as extract_info_from_chat might return empty on purpose if st.session_state.processed_chat_extracts: st.subheader("提取到的信息预览:") preview_container = st.container() with preview_container: for item in st.session_state.processed_chat_extracts: st.markdown(f"- **{item.get('student_name', 'N/A')}**: {item.get('observation', 'N/A')}") st.markdown("---") if st.button("➕ 确认并存入数据库和RAG知识库", key="store_extracted_data_button"): with st.spinner("正在存储数据到RAG和学生数据库..."): docs_to_rag = [] metadatas_to_rag = [] ids_to_rag = [] # RAG manager now generates robust IDs if None processed_student_names_today = set() date_str = st.session_state.current_processing_date.strftime("%Y-%m-%d") for item_idx, item in enumerate(st.session_state.processed_chat_extracts): s_name = item.get("student_name") obs = item.get("observation") if not s_name or not obs: st.warning(f"跳过不完整的提取项: {item}") continue docs_to_rag.append(f"{s_name} 在 {date_str} 的表现: {obs}") metadatas_to_rag.append({"student_name": str(s_name), "date": str(date_str), "source": "chat_log"}) # Let rag_manager handle ID generation if not provided or use robust ones here # ids_to_rag.append(f"chat_{date_str.replace('-','')}_{str(s_name).replace(' ','_')}_{item_idx}") add_or_update_student(s_name) # Ensure student exists in DB processed_student_names_today.add(s_name) storage_successful = False if docs_to_rag: if add_documents_to_rag(docs_to_rag, metadatas_to_rag, ids_to_rag): # ids can be None storage_successful = True else: st.info("没有有效的提取信息可供存储。") if storage_successful: st.success(f"成功将 {len(docs_to_rag)} 条信息存入RAG。学生列表已更新。") refresh_student_list_cache() # Optionally trigger characteristics update for these students if processed_student_names_today: st.info("数据已存储。您可以前往“学生特点管理”页面更新这些学生的特点总结。") st.session_state.processed_chat_extracts = [] # Clear after storing st.experimental_rerun() # Rerun to clear preview and update UI elif docs_to_rag: # If docs were there but storage failed st.error("数据存入RAG失败。请检查日志。") # --- Page 2: 生成反馈报告 --- elif choice == "生成反馈报告": st.header("📝 生成每日反馈报告") st.markdown("根据已处理的信息或学生特点，选择不同模式生成反馈。") feedback_target_date = st.date_input( "请选择生成反馈对应的日期", value=st.session_state.current_processing_date, key="feedback_date_selector" ) feedback_date_str = feedback_target_date.strftime("%Y-%m-%d") # Determine summary for Boss/Public feedback # Use extracts if date matches and extracts exist, otherwise query RAG daily_summary_for_general_feedback = "" processed_extracts_for_feedback_date = [] if feedback_target_date == st.session_state.current_processing_date and st.session_state.processed_chat_extracts: processed_extracts_for_feedback_date = st.session_state.processed_chat_extracts st.info(f"将使用为 {feedback_date_str} 刚处理的聊天记录生成反馈。") temp_summary_parts = [] for item in processed_extracts_for_feedback_date: temp_summary_parts.append(f"- {item.get('student_name', 'N/A')}: {item.get('observation', 'N/A')}") if temp_summary_parts: daily_summary_for_general_feedback = "\n".join(temp_summary_parts) else: daily_summary_for_general_feedback = get_events_summary_for_day(feedback_date_str) # Fallback else: with st.spinner(f"正在为日期 {feedback_date_str} 从知识库获取信息摘要..."): daily_summary_for_general_feedback = get_events_summary_for_day(feedback_date_str) st.markdown("---") col1, col2 = st.columns(2) with col1: st.subheader("👔 给老板的反馈") if st.button("生成老板反馈", key="generate_boss_fb"): if not GOOGLE_API_KEY: st.error("API Key未配置。"); st.stop() with st.spinner("正在生成老板反馈..."): st.session_state.feedback_boss_text = generate_boss_feedback(daily_summary_for_general_feedback) if st.session_state.feedback_boss_text: st.success("老板反馈生成成功！") else: st.error("生成老板反馈失败或无内容返回。") if st.session_state.feedback_boss_text: st.text_area("老板反馈内容:", value=st.session_state.feedback_boss_text, height=200, key="boss_feedback_display") with col2: st.subheader("📢 公共反馈") if st.button("生成公共反馈", key="generate_public_fb"): if not GOOGLE_API_KEY: st.error("API Key未配置。"); st.stop() with st.spinner("正在生成公共反馈..."): st.session_state.feedback_public_text = generate_public_feedback(daily_summary_for_general_feedback) if st.session_state.feedback_public_text: st.success("公共反馈生成成功！") else: st.error("生成公共反馈失败或无内容返回。") if st.session_state.feedback_public_text: st.text_area("公共反馈内容:", value=st.session_state.feedback_public_text, height=200, key="public_feedback_display") st.markdown("---") st.subheader("👨‍👩‍👧‍👦 给家长的反馈") if not st.session_state.student_list_cache: st.warning("学生列表为空。请先通过“处理聊天记录”功能添加学生并处理数据。") else: st.session_state.selected_student_for_parent_fb = st.selectbox( "选择学生:", options=[""] + st.session_state.student_list_cache, # Add empty option for placeholder index=0, # Default to empty format_func=lambda x: "请选择..." if x == "" else x, key="parent_feedback_student_selector" ) feedback_modes_map = { "正常模式 (基于当日记录)": "normal", "偷懒模式 (组合历史事件)": "lazy", "LLM特点生成 (创意发挥)": "llm_direct" } selected_mode_display_name = st.radio( "选择反馈模式:", options=list(feedback_modes_map.keys()), key="parent_feedback_mode_selector" ) mode_value = feedback_modes_map[selected_mode_display_name] if st.button(f"为选定学生生成家长反馈", key="generate_parent_fb"): if not GOOGLE_API_KEY: st.error("API Key未配置。"); st.stop() if not st.session_state.selected_student_for_parent_fb: st.warning("请先选择一个学生。") else: student_name = st.session_state.selected_student_for_parent_fb with st.spinner(f"正在为 {student_name} ({selected_mode_display_name}) 生成家长反馈..."): # Pass today's extracted data for the student if available (for "normal" mode) student_specific_extracts_today = [] if feedback_target_date == st.session_state.current_processing_date and st.session_state.processed_chat_extracts: student_specific_extracts_today = [ item for item in st.session_state.processed_chat_extracts if item.get("student_name") == student_name ] st.session_state.feedback_parent_text = generate_parent_feedback( student_name, mode_value, feedback_date_str, student_specific_extracts_today # Pass specific extracts for normal mode ) if st.session_state.feedback_parent_text: st.success(f"为 {student_name} 生成家长反馈成功！") else: st.error(f"为 {student_name} 生成家长反馈失败或无内容返回。") if st.session_state.feedback_parent_text and st.session_state.selected_student_for_parent_fb: st.text_area( f"给 {st.session_state.selected_student_for_parent_fb} 家长的反馈:", value=st.session_state.feedback_parent_text, height=300, key="parent_feedback_display" ) # --- Page 3: 学生特点管理 --- elif choice == "学生特点管理": st.header("🧑‍🎓 学生特点数据库管理") st.markdown("查看和更新AI总结的学生特点。特点会基于RAG中的历史记录生成。") if st.button("🔄 强制刷新学生列表和显示", key="admin_refresh_students_btn"): refresh_student_list_cache() st.experimental_rerun() if not st.session_state.student_list_cache: st.info("当前没有学生数据。请先通过“处理聊天记录”功能添加并存储学生相关信息。") else: st.subheader("当前学生列表及特点:") num_students = len(st.session_state.student_list_cache) cols_per_row = 3 # Adjust number of columns for display for i in range(0, num_students, cols_per_row): cols = st.columns(cols_per_row) for j in range(cols_per_row): student_idx = i + j if student_idx < num_students: student_name = st.session_state.student_list_cache[student_idx] with cols[j]: with st.expander(f"{student_name}", expanded=False): characteristics = get_student_characteristics(student_name) st.markdown(f"**AI总结特点:**\n {characteristics if characteristics else '暂无总结。'}") if st.button(f"更新 {student_name} 特点", key=f"update_char_{student_name}_{student_idx}"): if not GOOGLE_API_KEY: st.error("API Key未配置。"); st.stop() with st.spinner(f"正在为 {student_name} 更新特点..."): update_student_characteristics_from_rag(student_name) st.success(f"{student_name} 的特点已更新！请重新展开查看。") st.experimental_rerun() # Rerun to reflect changes st.markdown("---") st.subheader("批量操作") if st.button("✨ 批量更新所有学生的特点总结", key="batch_update_all_chars_btn"): if not GOOGLE_API_KEY: st.error("API Key未配置。"); st.stop() if not st.session_state.student_list_cache: st.warning("没有学生可供批量更新。") else: # Confirmation dialog for safety # Using a more explicit confirmation placeholder = st.empty() with placeholder.container(): st.warning(f"此操作将为数据库中所有 {len(st.session_state.student_list_cache)} 位学生重新生成特点总结，可能需要较长时间并消耗API额度。") if st.button("我确认执行批量更新", key="confirm_batch_update"): placeholder.empty() # Remove confirmation message with st.spinner("正在批量更新所有学生特点，请耐心等待..."): batch_update_all_students_characteristics() # This function has internal st.progress st.success("所有学生特点总结批量更新完毕！") st.experimental_rerun() elif st.button("取消批量更新", key="cancel_batch_update"): placeholder.empty() st.info("批量更新已取消。") # --- Footer --- st.markdown("---") st.markdown("晚托反馈助手 v1.0.0 (HF Dockerized) | 技术支持: Gemini LLM + RAG")