| ''' | |
| 1. 基于ChatGPT的多场景应用： | |
| 1. 核心模式 | |
| 1. 联网模式 | |
| 1. 知识库模式 | |
| 1. 数据分析模式 | |
| 1. 智能体模式 | |
| 1. RAG： | |
| 1. 核心文件包括： | |
| 1. langchain_KB.py包含了形成vector database的函数，和产生total prompt的函数。 | |
| 1. rag_source.py包含了从vector database中提取信息来源的函数，包括文档名称和页码。 | |
| ''' | |
| # TODO：1. 更新huggingface上code01的版本，包括：知识库和数据分析模块。 2. 将知识库模块更新为：multi-query + source。 3. 将数据分析模块重写。 | |
| import numpy as np | |
| import pandas as pd | |
| from dotenv import load_dotenv # pip3 install python-dotenv | |
| import requests | |
| import streamlit as st | |
| import openai | |
| import os | |
| import matplotlib.pyplot as plt | |
| import xlrd | |
| import pandas as pd | |
| # import csv | |
| import tempfile | |
| from tempfile import NamedTemporaryFile | |
| import pathlib | |
| from pathlib import Path | |
| from matplotlib.font_manager import FontProperties | |
| import seaborn as sns | |
| from time import sleep | |
| import streamlit_authenticator as stauth | |
| # from langchain.chat_models import ChatOpenAI | |
| # from langchain.llms import openai | |
| import sys | |
| import time | |
| import PyPDF2 ## read the local_KB PDF file. | |
| # import localKB_construct | |
| # from streamlit_option_menu import option_menu | |
| # import st_reset_conversation | |
| from st_reset_conversation import reset_all, reset_message | |
| import save_database_info | |
| import pytz | |
| from datetime import datetime | |
| from dotenv import load_dotenv | |
| from openai import OpenAI | |
| import st_msautogen | |
| import rag_source | |
| # import add_fonts | |
| import asyncio | |
| import warnings | |
| warnings.filterwarnings("ignore") | |
| #make it look nice from the start | |
| # st.set_page_config(layout='wide',initial_sidebar_state='collapsed',) | |
| ### 设置openai的API key | |
| load_dotenv() | |
| openai.api_key = os.environ['user_token'] | |
| os.environ["OPENAI_API_KEY"] = os.environ['user_token'] | |
| bing_search_api_key = os.environ['bing_api_key'] | |
| # # #* 如果数据分析模块在本地调试时碰到接口问题，可以启用如下设置。还可能是一个bash命令的问题，见ChatGPT讲课要点.txt. | |
| openai.proxy = { | |
| "http": "http://127.0.0.1:7890", | |
| "https": "http://127.0.0.1:7890" | |
| } | |
| ## layout settings. | |
| st.title("专业版大语言模型智能中心") | |
| st.subheader("Artificial Intelligence Backend Center for Professionals") | |
| st.caption("_声明：本网站仅提供技术测试与评估服务。内容由人工智能生成，仅供参考。如果您本人使用或对外传播本服务生成的输出，您应当主动核查输出内容的真实性、准确性，避免传播虚假信息。_") | |
| # st.divider() | |
| # ## clear conversion. | |
| # def reset_all(): | |
| # # st.session_state.conversation = None | |
| # st.session_state.chat_history = None | |
| # st.session_state.messages = [] | |
| # message_placeholder = st.empty() | |
| # return None | |
| # navigation menu using Hydralit. 并没有解决menu跳转的问题。 | |
| # option_data = [ | |
| # {'icon': "house", 'label':"核心模式"}, | |
| # {'icon':"cloud-upload",'label':"信息检索模式"}, | |
| # {'icon': "gear", 'label':"数据分析模式"}, | |
| # {'icon': "list-task", 'label':"智能体模式"}, | |
| # ] | |
| # navi_menu = op = hc.option_bar(option_definition=option_data,title=None,key='PrimaryOption', horizontal_orientation=True) | |
| # navi_menu = hc.nav_bar(menu_definition=option_data, key='navi_menu', use_animation=True, option_menu=False, sticky_mode='pinned', sticky_nav=False, hide_streamlit_markers=False) | |
| ### 使用streamlit_option_menu格式的类似横幅选项。但是会出现第一次无法运行，需要手动清零或者做一个动作，才可以。 | |
| # navi_menu = option_menu( | |
| # menu_title=None, | |
| # options=['核心模式', '信息检索模式', '数据分析模式', '智能体模式'], | |
| # # options=['GPT-3.5', 'GPT-4.0','清华GLM2-6B','百川Baichuan-13B', '阿里通义千问14B'], | |
| # icons=['house', 'cloud-upload','gear','list-task'], | |
| # menu_icon='cast', | |
| # default_index=0, | |
| # orientation='horizontal', | |
| # # manual_select=0, | |
| # # styles={ | |
| # # "container": {"padding": "0!important", "background-color": "#fafafa"}, | |
| # # "icon": {"color": "orange", "font-size": "25px"}, | |
| # # "nav-link": {"font-size": "25px", "text-align": "left", "margin":"0px", "--hover-color": "#eee"}, | |
| # # "nav-link-selected": {"background-color": "green"}, | |
| # # } | |
| # ) | |
| ### 常规streamlit选择 | |
| navi_menu = st.radio(label='选择一个大语言模型工作模式', options=['核心模式', '联网模式', '知识库模式','数据分析模式', '智能体模式'],index=0,horizontal=True) | |
| # navi_menu = st.selectbox('选择一个大语言模型工作模式', ['核心模式', '信息检索模式', '数据分析模式', '智能体模式'],index=0) ### 原始agent001模式。 | |
| reset_button_key = "reset_button" | |
| reset_button = st.button(label=("清除所有记录，并开启一轮新对话 ▶"), | |
| key=reset_button_key, use_container_width=True, type="primary") | |
| def clear_all(): | |
| st.session_state.conversation = None | |
| st.session_state.chat_history = None | |
| st.session_state.messages = [] | |
| message_placeholder = st.empty() | |
| return None | |
| ## 清除所有对话记录, reset all conversation. | |
| if reset_button: | |
| reset_all() | |
| ### 上传文件的模块 | |
| def upload_file(uploaded_file): | |
| if uploaded_file is not None: | |
| # filename = uploaded_file.name | |
| # st.write(filename) # print out the whole file name to validate. not to show in the final version. | |
| try: | |
| # if '.pdf' in filename: ### original code here. | |
| if '.pdf' in uploaded_file.name: | |
| pdf_filename = uploaded_file.name ### original code here. | |
| filename = uploaded_file.name | |
| # print('PDF file:', pdf_filename) | |
| # with st.status('正在为您解析新知识库...', expanded=False, state='running') as status: | |
| spinner = st.spinner('正在为您解析新知识库...请耐心等待') | |
| with spinner: | |
| ### 一下是llama_index方法，但是升级后，可能会报错。 | |
| # import localKB_construct | |
| # # st.write(upload_file) | |
| # localKB_construct.process_file(uploaded_file, username) | |
| # ## 在屏幕上展示当前知识库的信息，包括名字和加载日期。 | |
| # save_database_info.save_database_info(f'./{username}/database_name.csv', filename, str(datetime.now(pytz.timezone('Asia/Shanghai')).strftime("%Y-%m-%d %H:%M"))) | |
| # st.markdown('新知识库解析成功，请务必刷新页面，然后开启对话 🔃') | |
| ### 以下是langchain方案。 | |
| import langchain_KB | |
| import save_database_info | |
| uploaded_file_name = "File_provided" | |
| temp_dir = tempfile.TemporaryDirectory() | |
| # ! working. | |
| uploaded_file_path = pathlib.Path(temp_dir.name) / uploaded_file_name | |
| with open(pdf_filename, 'wb') as output_temporary_file: | |
| # with open(f'./{username}_upload.pdf', 'wb') as output_temporary_file: ### original code here. 可能会造成在引用信息来源时文件名不对的问题。 | |
| # ! 必须用这种格式读入内容，然后才可以写入temporary文件夹中。 | |
| # output_temporary_file.write(uploaded_file.getvalue()) | |
| output_temporary_file.write(uploaded_file.getvalue()) | |
| langchain_KB.langchain_localKB_construct(output_temporary_file, username) | |
| ## 在屏幕上展示当前知识库的信息，包括名字和加载日期。 | |
| save_database_info.save_database_info(f'./{username}/database_name.csv', pdf_filename, str(datetime.now(pytz.timezone('Asia/Shanghai')).strftime("%Y-%m-%d %H:%M"))) | |
| st.markdown('新知识库解析成功，请务必刷新页面，然后开启对话 🔃') | |
| return pdf_filename | |
| else: | |
| # if '.csv' in filename: ### original code here. | |
| if '.csv' in uploaded_file.name: | |
| print('start the csv file processing...') | |
| csv_filename = uploaded_file.name | |
| filename = uploaded_file.name | |
| csv_file = pd.read_csv(uploaded_file) | |
| csv_file.to_csv(f'./{username}/{username}_upload.csv', encoding='utf-8', index=False) | |
| st.write(csv_file[:3]) # 这里只是显示文件，后面需要定位文件所在的绝对路径。 | |
| else: | |
| xls_file = pd.read_excel(uploaded_file) | |
| xls_file.to_csv(f'./{username}_upload.csv', index=False) | |
| st.write(xls_file[:3]) | |
| print('end the csv file processing...') | |
| # uploaded_file_name = "File_provided" | |
| # temp_dir = tempfile.TemporaryDirectory() | |
| # ! working. | |
| # uploaded_file_path = pathlib.Path(temp_dir.name) / uploaded_file_name | |
| # with open('./upload.csv', 'wb') as output_temporary_file: | |
| # with open(f'./{username}_upload.csv', 'wb') as output_temporary_file: | |
| # print(f'./{name}_upload.csv') | |
| # ! 必须用这种格式读入内容，然后才可以写入temporary文件夹中。 | |
| # output_temporary_file.write(uploaded_file.getvalue()) | |
| # st.write(uploaded_file_path) #* 可以查看文件是否真实存在，然后是否可以 | |
| except Exception as e: | |
| st.write(e) | |
| ## 以下代码是为了解决上传文件后，文件路径和文件名不对的问题。 | |
| # uploaded_file_name = "File_provided" | |
| # temp_dir = tempfile.TemporaryDirectory() | |
| # # ! working. | |
| # uploaded_file_path = pathlib.Path(temp_dir.name) / uploaded_file_name | |
| # # with open('./upload.csv', 'wb') as output_temporary_file: | |
| # with open(f'./{name}_upload.csv', 'wb') as output_temporary_file: | |
| # # print(f'./{name}_upload.csv') | |
| # # ! 必须用这种格式读入内容，然后才可以写入temporary文件夹中。 | |
| # # output_temporary_file.write(uploaded_file.getvalue()) | |
| # output_temporary_file.write(uploaded_file.getvalue()) | |
| # # st.write(uploaded_file_path) # * 可以查看文件是否真实存在，然后是否可以 | |
| # # st.write('Now file saved successfully.') | |
| # return pdf_filename, csv_filename | |
| return filename | |
| ### 互联网搜索模块 | |
| bing_search_api_key = os.environ['bing_api_key'] | |
| bing_search_endpoint = 'https://api.bing.microsoft.com/v7.0/search' | |
| def search(query): | |
| # Construct a request | |
| # mkt = 'en-EN' | |
| mkt = 'zh-CN' | |
| params = {'q': query, 'mkt': mkt} | |
| headers = {'Ocp-Apim-Subscription-Key': bing_search_api_key} | |
| # Call the API | |
| try: | |
| response = requests.get(bing_search_endpoint, | |
| headers=headers, params=params) | |
| response.raise_for_status() | |
| json = response.json() | |
| return json["webPages"]["value"] | |
| # print("\nJSON Response:\n") | |
| # pprint(response.json()) | |
| except Exception as e: | |
| raise e | |
| # async def text_mode(): | |
| def text_mode(): | |
| # reset_message() ## reset the message and placeholder. | |
| print('text mode starts!') | |
| # Set a default model | |
| if "openai_model" not in st.session_state: | |
| st.session_state["openai_model"] = "gpt-4o-mini" | |
| if radio_1 == 'ChatGPT-3.5': | |
| # print('----------'*5) | |
| print('radio_1: GPT-3.5 starts!') | |
| st.session_state["openai_model"] = "gpt-4o-mini" | |
| elif radio_1 == 'ChatGPT-4': | |
| print('radio_1: GPT-4.0 starts!') | |
| st.session_state["openai_model"] = "gpt-4o-mini" | |
| else: | |
| st.markdown("**当前大模型无效，请在左侧工具栏中选择一个有效的模型。您现在访问的站点仅提供ChatGPT中的GPT-3.5/4。**") | |
| print(st.session_state["openai_model"]) | |
| # Initialize chat history | |
| if "messages" not in st.session_state: | |
| st.session_state.messages = [] | |
| # Display chat messages from history on app rerun | |
| for message in st.session_state.messages: | |
| with st.chat_message(message["role"]): | |
| st.markdown(message["content"]) | |
| # Display assistant response in chat message container | |
| # if prompt := st.chat_input("说点什么吧"): | |
| prompt = st.chat_input("说点什么吧...") | |
| print('prompt now:', prompt) | |
| print('----------'*5) | |
| if prompt: | |
| st.session_state.messages.append({"role": "user", "content": prompt}) | |
| with st.chat_message("user"): | |
| st.markdown(prompt) | |
| with st.chat_message("assistant"): | |
| message_placeholder = st.empty() | |
| full_response = "" | |
| if navi_menu == '联网模式': | |
| # if (navi_menu=='信息检索模式') and (radio_2=='互联网'): ### original code here. | |
| print('联网模式下的prompt:', prompt) | |
| input_message = prompt | |
| internet_search_result = search(input_message) | |
| search_prompt = [ | |
| f"Source:\nTitle: {result['name']}\nURL: {result['url']}\nContent: {result['snippet']}" for result in internet_search_result] | |
| prompt = "基于如下的互联网公开信息, 回答问题:\n\n" + \ | |
| "\n\n".join(search_prompt[:3]) + "\n\n问题: " + input_message + \ | |
| "你需要注意的是回答问题时必须用提问的语言（如英文或者中文）来提示：'答案基于互联网公开信息。'" + "\n\n答案: " # 限制了只有3个搜索结果。 | |
| # prompt = "Use these sources to answer the question:\n\n" + "\n\n".join(search_prompt[0:3]) + "\n\nQuestion: " + input_message + "（注意：回答问题时请提示'以下答案基于互联网公开信息。'）\n\n" + "\n\nAnswer: " | |
| st.session_state.messages.append( | |
| {"role": "user", "content": prompt}) | |
| ## old version of openai API. | |
| # for response in openai.ChatCompletion.create( | |
| # model=st.session_state["openai_model"], | |
| # messages=[ | |
| # {"role": m["role"], "content": m["content"]} | |
| # for m in st.session_state.messages | |
| # ], | |
| # stream=True, | |
| # ): | |
| # full_response += response.choices[0].delta.get( | |
| # "content", "") | |
| # message_placeholder.markdown(full_response + "▌") | |
| # message_placeholder.markdown(full_response) | |
| # st.session_state.messages.append( | |
| # {"role": "assistant", "content": full_response}) | |
| # st.session_state.messages = [] | |
| ## new version of openai API. | |
| openai_client = OpenAI() | |
| for response in openai_client.chat.completions.create( | |
| model=st.session_state["openai_model"], | |
| messages=[ | |
| {"role": m["role"], "content": m["content"]} | |
| for m in st.session_state.messages | |
| ], | |
| stream=True, | |
| ): | |
| if str(response.choices[0].delta.content) != 'None': | |
| full_response += str(response.choices[0].delta.content) | |
| message_placeholder.markdown(full_response + "▌") | |
| message_placeholder.markdown(full_response) | |
| st.session_state.messages.append( | |
| {"role": "assistant", "content": full_response}) | |
| st.session_state.messages = [] | |
| # elif radio_2 != '互联网': | |
| else: | |
| print('ChatGPT only starts!!!') | |
| ## 这里需要确认是直接从import openai中获得的函数，而不是langchain中调用openai，否则随着langchain的更新，会出现问题。 | |
| # for response in openai.ChatCompletion.create( | |
| # model=st.session_state["openai_model"], | |
| # max_tokens=max_tokens, | |
| # temperature=temperature, | |
| # top_p=top_p, | |
| # presence_penalty=presence_penalty, | |
| # frequency_penalty=frequency_penalty, | |
| # ## 多轮会话，需要记住历史记录。 | |
| # messages=[ | |
| # {"role": m["role"], "content": m["content"]} | |
| # for m in st.session_state.messages | |
| # ], | |
| # # messages=[{'role': 'system', 'content': 'you are ChatGPT'}, { | |
| # # 'role': 'user', 'content': prompt}], ## 这是单轮会话。 | |
| # stream=True, | |
| # ): | |
| openai_client = OpenAI() | |
| for response in openai_client.chat.completions.create( | |
| model=st.session_state["openai_model"], | |
| max_tokens=max_tokens, | |
| temperature=temperature, | |
| top_p=top_p, | |
| presence_penalty=presence_penalty, | |
| frequency_penalty=frequency_penalty, | |
| ## 多轮会话，需要记住历史记录。 | |
| messages=[ | |
| {"role": m["role"], "content": m["content"]} | |
| for m in st.session_state.messages | |
| ], | |
| # messages=[{'role': 'system', 'content': 'you are ChatGPT'}, { | |
| # 'role': 'user', 'content': prompt}], ## 这是单轮会话。 | |
| stream=True, | |
| ): | |
| # print('full response now:', full_response) | |
| # print('response now:', response) | |
| ## old version output format. | |
| # full_response += response.choices[0].delta.get( | |
| # "content", "") | |
| ## new version output format. | |
| if str(response.choices[0].delta.content) != 'None': ## 注意这里是内容，而不是response，否则一个chunk的回复。 | |
| # print('response now:',response) | |
| full_response += str(response.choices[0].delta.content) | |
| message_placeholder.markdown(full_response + "▌") | |
| message_placeholder.markdown(full_response) | |
| st.session_state.messages.append( | |
| {"role": "assistant", "content": full_response}) | |
| ## load the local_KB PDF file. | |
| # # def local_KB(uploaded_file): | |
| # print('now starts the local KB version of ChatGPT') | |
| # max_input_size = 4096 | |
| # # set number of output tokens | |
| # # num_outputs = 3000 #* working | |
| # num_outputs = 1000 | |
| # # set maximum chunk overlap | |
| # max_chunk_overlap = -1000 #* working | |
| # # set chunk size limit | |
| # # chunk_size_limit = 600 | |
| # chunk_size_limit = 6000 #* working | |
| # history = [] | |
| # if input: | |
| # # ! 这里需要重新装载一下storage_context。 | |
| # QA_PROMPT_TMPL = ( | |
| # "We have provided context information below. \n" | |
| # "---------------------\n" | |
| # "{context_str}" | |
| # "\n---------------------\n" | |
| # "Given all this information, please answer the following questions," | |
| # "You MUST use the SAME language as the question:\n" | |
| # "{query_str}\n") | |
| # QA_PROMPT = QuestionAnswerPrompt(QA_PROMPT_TMPL) | |
| # llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.8, model_name="gpt-3.5-turbo", max_tokens=4096,streaming=True)) | |
| # prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit) | |
| # service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper) | |
| # # # index = load_index_from_storage(storage_context) | |
| # storage_context = StorageContext.from_defaults(persist_dir="./") | |
| # index = load_index_from_storage(storage_context,service_context=service_context) | |
| # # query_engine = index.as_query_engine(streaming=True, similarity_top_k=3, text_qa_template=QA_PROMPT) | |
| # # query_engine = index.as_query_engine(streaming=True) | |
| # query_engine = index.as_query_engine(streaming=True, text_qa_template=QA_PROMPT) | |
| # reply = query_engine.query(input) | |
| # async def localKB_mode(username): | |
| def localKB_mode(username): | |
| # reset_all() ## reset the conversation. | |
| reset_message() ## only reset the message and placeholder. | |
| print('now starts the local KB version of ChatGPT') | |
| # # Initialize chat history | |
| # if "messages" not in st.session_state: | |
| # st.session_state.messages = [] | |
| # for message in st.session_state.messages: | |
| # with st.chat_message(message["role"]): | |
| # st.markdown(message["content"]) | |
| # Display assistant response in chat message container | |
| # if prompt: | |
| if prompt := st.chat_input("说点什么吧"): | |
| st.session_state.messages.append({"role": "user", "content": prompt}) | |
| with st.chat_message("user"): | |
| st.markdown(prompt) | |
| with st.status('检索中...', expanded=True, state='running') as status: | |
| # try: | |
| with st.chat_message("assistant"): | |
| message_placeholder = st.empty() | |
| full_response = "" | |
| ### llama_index框架的RAG代码，最近更新版本后不成功，会报错。 | |
| ### outdated version. | |
| # llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.8, model_name="gpt-3.5-turbo", max_tokens=4024,streaming=True)) | |
| # # print('llm_predictor:', llm_predictor) | |
| # prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit) | |
| # print('prompt_helper:', prompt_helper) | |
| # service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper) | |
| # print('service_context:', service_context) | |
| # # # index = load_index_from_storage(storage_context) | |
| # print("storage_context:", storage_context) | |
| # index = load_index_from_storage(storage_context,service_context=service_context) | |
| ## sample code for reference. | |
| # docstore = 'storage/docstore.json' | |
| # index_store = 'storage/index_store.json' | |
| # vector_store = 'storage/vector_store.json' | |
| # print('storage_context:', storage_context) | |
| ##NOTE: 这里需要重新装载一下storage_context。 | |
| # storage_context = StorageContext.from_defaults(persist_dir=f"./{username}/") | |
| # print('--'*30) | |
| # print('storage_context:',storage_context) | |
| # print('type of storage_context.index_store:', type(storage_context.index_store)) | |
| # print('--'*30) | |
| # # storage_context = {storage_context} | |
| # index = load_index_from_storage(storage_context) | |
| # print('--'*30) | |
| # print('index now:', index) | |
| # context_str = index | |
| # ##TODO 重新构建Prompt，加入QA_Template. | |
| # QA_PROMPT_TMPL = ( | |
| # "We have provided context information below. \n" | |
| # "---------------------\n" | |
| # "{context_str}" | |
| # "\n---------------------\n" | |
| # "Given all this information, please answer the following questions," | |
| # "You MUST use the SAME language as the question and the default language is Chinese:\n" | |
| # "{query_str}\n") | |
| # # QA_PROMPT = QuestionAnswerPrompt(QA_PROMPT_TMPL) ## outdated version. | |
| # ##TODO: newer version but may run into llama_index import problem. | |
| # # qa_template = PromptTemplate(QA_PROMPT_TMPL) | |
| # # prompt = qa_template.format(context_str=context_str, query_str=prompt) | |
| # # prompt = qa_template.format(context_str=context_str, query_str=QA_PROMPT) | |
| # # query_engine = index.as_query_engine(streaming=True, similarity_top_k=3, text_qa_template=QA_PROMPT) | |
| # query_engine = index.as_query_engine(streaming=False) | |
| # print('111') | |
| ## older version. | |
| # query_engine = index.as_query_engine(streaming=True, text_qa_template=QA_PROMPT) | |
| # query_engine = index.as_query_engine() | |
| # reply = query_engine.query(prompt) | |
| # llama_index_reply = query_engine.query(prompt) | |
| # # full_response += query_engine.query(prompt) | |
| # print('local KB reply:', llama_index_reply) | |
| # # query_engine.query(prompt).print_response_stream() #* 能在terminal中流式输出。 | |
| # # for resp in llama_index_reply.response_gen: | |
| # # print(resp) | |
| # # full_response += resp | |
| # # message_placeholder.markdown(full_response + "▌") | |
| # message_placeholder.markdown(str(llama_index_reply)) | |
| # print('333') | |
| # # st.session_state.messages.append( | |
| # # {"role": "assistant", "content": full_response}) | |
| # # st.session_state.messages = [] | |
| # # full_response += reply | |
| # # full_response = reply | |
| # # st.session_state.messages.append( | |
| # # {"role": "assistant", "content": full_response}) | |
| ### 用langchain的FAISS来做RAG | |
| import langchain_KB | |
| ### 默认选择使用multi-query的方法进行查询。 | |
| ##NOTE: 目前这个版本是把所有的multiquery当成一个问题提交给大模型。后续可以考虑将每一个问题分别送入大模型，然后得到的多个答案，然后在一并汇总。 | |
| if True: | |
| import multiQuery_prompt | |
| prompt = multiQuery_prompt.generate_sim_query(orignal_question=prompt) | |
| # print('multiQuery prompts now:', prompt) | |
| prompt = str(prompt) ## 需要强制转换成str格式。 | |
| total_prompt, docs = langchain_KB.langchain_RAG(prompt, username) | |
| print('total_prompt now:', total_prompt) | |
| st.session_state.messages.append({"role": "user", "content": total_prompt}) | |
| ## new version of openai API. | |
| openai_client = OpenAI() | |
| for response in openai_client.chat.completions.create( | |
| model=st.session_state["openai_model"], | |
| messages=[ | |
| {"role": m["role"], "content": m["content"]} | |
| for m in st.session_state.messages | |
| ], | |
| stream=True, | |
| ): | |
| if str(response.choices[0].delta.content) != 'None': | |
| full_response += str(response.choices[0].delta.content) | |
| message_placeholder.markdown(full_response + "▌") | |
| message_placeholder.markdown(full_response) | |
| st.session_state.messages.append( | |
| {"role": "assistant", "content": full_response}) | |
| st.session_state.messages = [] | |
| try: | |
| ### 显示RAG的source，即查询得到的信息来源出处。 | |
| print('docs now:', docs) | |
| source = rag_source.rag_source(docs) ## get the k reference source of the RAG answer, in a designed format. | |
| # print('返回的source内容：', source) | |
| st.divider() | |
| st.caption(source) | |
| except Exception as e: | |
| print('Exception:', e) | |
| pass | |
| ##TODO 确认是否需要？ | |
| st.session_state.messages = [] | |
| # except Exception as e: | |
| # print('Exception:', e) | |
| # pass | |
| # async def data_mode(): | |
| def data_mode(): | |
| clear_all() ## reset the conversation. | |
| print('数据分析模式启动！') | |
| # uploaded_file_path = './upload.csv' | |
| uploaded_file_path = f'./{username}/{username}_upload.csv' | |
| # uploaded_file_path = f'./{username}_upload.csv' ### original code here. | |
| print('file path:', uploaded_file_path) | |
| # Initialize chat history | |
| if "messages" not in st.session_state: | |
| st.session_state.messages = [] | |
| # Display chat messages from history on app rerun | |
| for message in st.session_state.messages: | |
| with st.chat_message(message["role"]): | |
| st.markdown(message["content"]) | |
| # Display assistant response in chat message container | |
| # if prompt := st.chat_input("Say something"): | |
| prompt = st.chat_input("Say something") | |
| print('prompt now:', prompt) | |
| print('----------'*5) | |
| if prompt: | |
| try: | |
| st.session_state.messages.append({"role": "user", "content": prompt}) | |
| with st.chat_message("user"): | |
| st.markdown(prompt) | |
| with st.status('思考中...需要1至10分钟左右，请耐心等待 🏃', expanded=True, state='running') as status: | |
| with st.chat_message("assistant"): | |
| #### Using the open-source CodeInterpreter solution below. May not work after version update, need to upgrade the code accoridngly later on. | |
| # from langchain.chat_models import ChatOpenAI | |
| # llm_model = ChatOpenAI(model_name="gpt-4-1106-preview") | |
| # # llm_model = ChatOpenAI(model_name="gpt-4") | |
| # # async with CodeInterpreterSession(llm=llm_model) as session: | |
| # import interpreter | |
| # interpreter.llm.model = "gpt-3.5-turbo" | |
| # with CodeInterpreterSession(llm=llm_model) as session: | |
| # # with CodeInterpreterSession(llm=llm_model) as session: | |
| # print('222') | |
| # # user_request = "对于文件中的'SepalLengthCm’数据给我一个'直方图'，提供图表，并给出分析结果" | |
| # #! 可以用设定dpi=300来输出高质量的图表。（注：图的解析度dpi设定为300） | |
| # environ_settings = """【背景要求】如果我没有告诉你任何定制化的要求，那么请你按照以下的默认要求来回答： | |
| # ------------------------------------------------------------------------- | |
| # 1. 你需要用我提问的语言来回答，且默认情况下用中文来回答。 | |
| # 2. 如果要求你输出图表，那么图的解析度dpi需要设定为600。图尽量使用seaborn库。seaborn库的参数设定：sns.set(rc={'axes.facecolor':'#FFF9ED','figure.facecolor':'#FFF9ED'}, palette='dark'。 | |
| # 3. 图上所有的文字全部翻译成<英文English>来表示。 | |
| # 4. 你回答的文字内容必须尽可能的详细且通俗易懂。 | |
| # 5. 回答时尽可能地展示分析所对应的图表，并提供分析结果。 你需要按如下格式提供内容： | |
| # 5.1 提供详细且专业的分析结果，提供足够的分析依据。 | |
| # 5.2 给出可能造成这一结果的可能原因有哪些？ | |
| # 以上内容全部用【1, 2, 3这样的序列号格式】来表达。 | |
| # ------------------------------------------------------------------------- | |
| # """ # seaborn中的palette参数可以设定图表的颜色,选项包括：deep, muted, pastel, bright, dark, colorblind，Spectral。更多参数可以参考：https://seaborn.pydata.org/generated/seaborn.color_palette.html。 | |
| # # uploaded_file_path = upload_file() | |
| # user_request = environ_settings + "\n\n" + \ | |
| # "你需要完成以下任务：\n\n" + prompt + "\n\n" \ | |
| # f"注：文件位置在 {uploaded_file_path}" | |
| # # user_request = str(prompt) ### only prompt without environment prompt. | |
| # print('user_request: \n', user_request) | |
| # # 加载上传的文件，主要路径在上面代码中。 | |
| # files = [File.from_path(str(uploaded_file_path))] | |
| # # files = [File.from_path("/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/rawdata/short_csv.csv")] | |
| # # st.write(pd.DataFrame(files)) | |
| # # print('session.__init__', session.__init__) | |
| # # print('session', session.__init__) | |
| # with st.status('思考中...', expanded=True, state='running') as status: | |
| # # generate the response | |
| # # response = await session.generate_response(user_msg=user_request, files=files, detailed_error=True) | |
| # # response = await session.generate_response(user_msg=user_request, files=files) | |
| # response = session.generate_response(user_msg=user_request, files=files) | |
| # # output to the user | |
| # print("AI: ", response.content) | |
| # full_response = response.content | |
| # ### full_response = "this is full response" | |
| # # for file in response.files: | |
| # for i, file in enumerate(response.files): | |
| # # await file.asave(f"/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/output{i}.png") ##working. | |
| # # st.image(file.get_image()) #! working. | |
| # # * 注意这里的设定，可以提高图片的精细程度。 | |
| # st.image(file.get_image(), width=None, | |
| # output_format='PNG') | |
| # # message_placeholder.markdown(full_response + "▌") ## orignal code. | |
| # # message_placeholder.markdown(full_response) ## orignal code. | |
| # st.write(full_response) | |
| # status.update(label='complete', state='complete') | |
| # # TODO: 确认是否要记录所有的full response。 | |
| # st.session_state.messages.append( | |
| # {"role": "assistant", "content": full_response}) | |
| # # await session.astop() # ! 确认需要关闭。 | |
| # session.astop() # ! 确认需要关闭。 | |
| # # st.session_state.messages.append({"role": "assistant", "content": full_response}) | |
| #### #### Using the OpenAI's assistant API， wrap into the st_openai_assistant.py. | |
| import st_openai_assistant | |
| ### NOTE:在st_openai_assistant.py中可以设置system_prompt. | |
| # sys_prompt = """ 1. 你是一位智能AI助手，你连接着一台电脑，但请注意不能联网。在使用Python解决任务时，你可以运行代码并得到结果，如果运行结果有错误，你需要尽可能对代码进行改进。你可以处理用户上传到电脑上的文件。 | |
| # 2. 你使用matplotlib.pylab（plt）或者seaborn（sns）画图时，需要添加中文字库，代码如下： | |
| # matplotlib.rcParams['font.sans-serif'] = ['Microsoft YaHei UI'] | |
| # sns.set(rc={'axes.facecolor':'#FFF9ED','figure.facecolor':'#FFF9ED'}, palette='dark', font='Microsoft YaHei UI') | |
| # 3. 如果我没有告诉你任何定制化的要求，那么请你按照以下的默认要求来回答： | |
| # 3.1 你回答的文字内容必须尽可能的详细且通俗易懂。 | |
| # 3.2 回答时尽可能地展示分析所对应的图表，并提供分析结果。图表上的文字采用中文。你需要按如下格式提供内容： | |
| # * 提供详细且专业的分析结果，提供足够的分析依据。 | |
| # * 给出可能造成这一结果的可能原因有哪些？ | |
| # 以上内容你用序列号1、2、3这样的格式表达。 | |
| # """ | |
| # prompt = [ | |
| # {"role": "system", "content": sys_prompt}, | |
| # {"role": "user", "content": prompt}, | |
| # ] | |
| messages, text_response, img_response, image_files, final_answer = st_openai_assistant.openai_assistant(prompt=prompt, filepath=uploaded_file_path, username=username) | |
| # st.image(img_response) ## show one single image. | |
| # st.markdown(text_response) ## show one single text response. | |
| try: | |
| from PIL import Image | |
| print("返回到Agent001程序中的图表个数：", len(image_files)) | |
| # plt.imshow(img) | |
| # plt.show() | |
| for img in image_files: | |
| img = Image.open(img) ## image object. | |
| st.image(img, output_format='PNG') | |
| # st.image(f"./{username}/{img_response[i]}", output_format='PNG') | |
| # st.image(f'/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/joeshi/output{i}.png', output_format='PNG') | |
| except: | |
| pass | |
| try: | |
| st.markdown(final_answer) ## all messages are appended together, need to print out one by one? | |
| except: | |
| pass | |
| except Exception as e: | |
| print(e) | |
| pass | |
| ### authentication with a local yaml file. | |
| import yaml | |
| from yaml.loader import SafeLoader | |
| with open('./config.yaml') as file: | |
| config = yaml.load(file, Loader=SafeLoader) | |
| authenticator = stauth.Authenticate( | |
| config['credentials'], | |
| config['cookie']['name'], | |
| config['cookie']['key'], | |
| config['cookie']['expiry_days'], | |
| config['preauthorized'] | |
| ) | |
| # authentication with a remove cloud-based database. | |
| # 导入云端用户数据库。 | |
| # DETA_KEY = "c0zegv33efm_4MBTaoQAn76GzUfsZeKV64Uh9qMY3WZb" | |
| # load_dotenv(".env") | |
| # DETA_KEY = os.getenv("DETA_KEY") | |
| # print(DETA_KEY) | |
| # deta = Deta(DETA_KEY) | |
| # mybase is the name of the database in Deta. You can change it to any name you want. | |
| # credentials = {"usernames":{}} | |
| # # credentials = {"users": {}} | |
| # # db = db() | |
| # users = [] | |
| # email = [] | |
| # passwords = [] | |
| # names = [] | |
| # for row in db.fetch_all_users(): | |
| # users.append(row["username"]) | |
| # email.append(row["email"]) | |
| # names.append(row["key"]) | |
| # passwords.append(row["password"]) | |
| # hashed_passwords = stauth.Hasher(passwords).generate() | |
| ## 需要严格的按照yaml文件的格式来定义如下几个字段。 | |
| # for un, name, pw in zip(users, names, hashed_passwords): | |
| # # user_dict = {"name":name,"password":pw} | |
| # user_dict = {"name": un, "password": pw} | |
| # # credentials["usernames"].update({un:user_dict}) | |
| # credentials["usernames"].update({un: user_dict}) | |
| # ## sign-up模块，未完成。 | |
| # database_table = [] | |
| # # print(pd.DataFrame(credentials)) | |
| # for i in credentials['usernames'].keys(): | |
| # # print("i:",i) | |
| # # print("name",credentials['usernames'][i]['name']) | |
| # # print("password",credentials['usernames'][i]['password']) | |
| # database_table.append([i,credentials['usernames'][i]['name'],credentials['usernames'][i]['password']]) | |
| # print("database_table:",database_table) | |
| # authenticator = stauth.Authenticate( | |
| # credentials=credentials, cookie_name="joeshi_gpt", key='abcedefg', cookie_expiry_days=30) | |
| user, authentication_status, username = authenticator.login('用户登录', 'main') | |
| #print("username", username) | |
| # ## sign-up widget，未完成。 | |
| # try: | |
| # if authenticator.register_user('新用户注册', preauthorization=False): | |
| # # for list in database_table: | |
| # # db.update_user(username=list[0], name=list[1], password=list[2]) | |
| # db.update_user(username=list[-1][0], name=list[-1][1], password=list[-1][2]) | |
| # # st.success('User registered successfully') | |
| # st.success('注册成功！') | |
| # except Exception as e: | |
| # st.error(e) | |
| if authentication_status: | |
| with st.sidebar: | |
| st.markdown( | |
| """ | |
| <style> | |
| [data-testid="stSidebar"][aria-expanded="true"]{ | |
| min-width: 450px; | |
| max-width: 450px; | |
| } | |
| """, | |
| unsafe_allow_html=True, | |
| ) | |
| ### siderbar的题目。 | |
| st.header(f'**欢迎 **{username}** 来到人工智能的世界** ♠') | |
| st.write(f'_Welcome and Hope U Enjoy Staying Here_') | |
| authenticator.logout('登出', 'sidebar') | |
| print(username) | |
| # reset_button_key = "reset_button" | |
| # reset_button = st.button(label=("清除所有记录，并开启一轮新对话 ▶"), | |
| # key=reset_button_key, use_container_width=True, type="primary") | |
| # ## 清除所有对话记录, reset all conversation. | |
| # if reset_button: | |
| # reset_all() | |
| # st.markdown("#### 大语言模型设置") | |
| # with st.expander(label='**选择一个大语言模型基座**', expanded=True): | |
| radio_1 = st.selectbox( | |
| label='选择一个大语言模型基座 (注：根据站点不同，部分基座不可用)', | |
| options=["ChatGPT-4", "ChatGPT-3.5", "Google Gemini","Claude 3", "清华ChatGLM3-6B", "百川Baichuan-13B", "阿里通义千问-14B", "阿里通义千问-72B", "Llama-2", "Mistral", "Vicuna"], | |
| index=0, | |
| placeholder="大语言模型列表", | |
| ) | |
| ## 在sidebar上的三个分页显示，用st.tabs实现。 | |
| tab_1, tab_2, tab_3, tab_4 = st.tabs(['使用须知', '模型参数', '提示词模板', '系统角色设定']) | |
| # with st.expander(label='**使用须知**', expanded=False): | |
| with tab_1: | |
| # st.markdown("#### 快速上手指南") | |
| # with st.text(body="说明"): | |
| # st.markdown("* 重启一轮新对话时，只需要刷新页面（按Ctrl/Command + R）即可。") | |
| with st.text(body="说明"): | |
| st.markdown("* 为了保护数据与隐私，所有对话均不会被保存，刷新页面立即删除。敬请放心。") | |
| with st.text(body="说明"): | |
| st.markdown("* “GPT-4”回答质量极佳，但速度缓慢，建议适当使用。") | |
| with st.text(body="说明"): | |
| st.markdown("* “信息检索模式”与所有的搜索引擎或者数据库检索方式一样，仅限一轮对话，将不会保持之前的会话记录。") | |
| with st.text(body="说明"): | |
| st.markdown( | |
| "* “数据分析模式”暂时只支持1000个单元格以内的数据分析，单元格中的内容不支持中文数据（表头也尽量不使用中文）。一般运行时间在1至10分钟左右，期间需要保持网络畅通。") | |
| with st.text(body="说明"): | |
| st.markdown("* “数据分析模式”推荐上传csv格式的文件，部分Excel文件容易出现数据不兼容的情况。") | |
| ## 大模型参数 | |
| # with st.expander(label='**大语言模型参数**', expanded=True): | |
| with tab_2: | |
| max_tokens = st.slider(label='Max_Token（生成结果时最大字数）', min_value=100, max_value=8096, value=4096,step=100) | |
| temperature = st.slider(label='Temperature (温度)', min_value=0.0, max_value=1.0, value=0.8, step=0.1) | |
| top_p = st.slider(label='Top_P (核采样)', min_value=0.0, max_value=1.0, value=0.6, step=0.1) | |
| frequency_penalty = st.slider(label='Frequency Penalty (重复度惩罚因子)', min_value=-2.0, max_value=2.0, value=1.0, step=0.1) | |
| presence_penalty = st.slider(label='Presence Penalty (控制主题的重复度)', min_value=-2.0, max_value=2.0, value=1.0, step=0.1) | |
| ## reset password widget | |
| # try: | |
| # if authenticator.reset_password(st.session_state["username"], 'Reset password'): | |
| # st.success('Password modified successfully') | |
| # except Exception as e: | |
| # st.error(e) | |
| # with st.header(body="欢迎"): | |
| # st.markdown("# 欢迎使用大语言模型商业智能中心") | |
| # with st.expander(label=("**重要的使用注意事项**"), expanded=True): | |
| # with st.container(): | |
| with tab_3: | |
| # st.markdown("#### Prompt提示词参考资料") | |
| with st.expander(label="**大语言模型基础提示词Prompt示例**", expanded=False): | |
| st.code( | |
| body="继续用中文写一篇关于 [文章主题] 的文章，以下列句子开头：[文章开头］。", language='plaintext') | |
| st.code(body="将以下文字概括为 100 个字，使其易于阅读和理解。避免使用复杂的句子结构或技术术语。", | |
| language='plaintext') | |
| st.code(body="给我出一个迪奥2024春季发布会活动策划。", language='plaintext') | |
| st.code(body="帮我按照正式会议结构写一个会邀：主题是xx手机游戏立项会议。", language='plaintext') | |
| st.code(body="帮我写一个车内健康监测全场景落地的项目计划，用表格。", language='plaintext') | |
| st.code( | |
| body="同时掷两枚质地均匀的骰子，则两枚骰子向上的点数之和为 7 的概率是多少。", language='plaintext') | |
| st.code(body="写一篇产品经理的演讲稿，注意使用以下词汇: 赋能,抓手,中台,闭环,落地,漏斗,沉淀,给到,同步,对齐,对标,迭代,拉通,打通,升级,交付,聚焦,倒逼,复盘,梳理,方案,联动,透传,咬合,洞察,渗透,兜底,解耦,耦合,复用,拆解。", language='plaintext') | |
| with st.expander(label="**数据分析模式的专用提示词Prompt示例**", expanded=False): | |
| # with st.subheader(body="提示词Prompt"): | |
| st.code(body="分析此数据集并绘制一些'有趣的图表'。", language='python') | |
| st.code( | |
| body="对于这个文件中的数据，你需要要找出[X,Y]数据之间的寻找'相关性'。", language='python') | |
| st.code(body="对于这个文件中的[xxx]数据给我一个'整体的分析'。", language='python') | |
| st.code(body="对于[xxx]数据给我一个'直方图'，提供图表，并给出分析结果。", language='python') | |
| st.code(body="对于[xxx]数据给我一个'小提琴图'，并给出分析结果。", language='python') | |
| st.code( | |
| body="对于[X,Y,Z]数据在一个'分布散点图 (stripplot)'，所有的数据在一张图上展现, 并给出分析结果。", language='python') | |
| st.code(body="对于[X，Y]数据，进行'T检验'，你需要展示图表，并给出分析结果。", | |
| language='python') | |
| st.code(body="对于[X，Y]数据给我一个3个类别的'聚类分析'，并给出分析结果。", | |
| language='python') | |
| with tab_4: | |
| st.text_area(label='系统角色设定', value='你是一个人工智能，你需要回答我提出的问题，或者完成我交代的任务。你需要使用我提问的语言（如中文、英文）来回答。', height=200, label_visibility='hidden') | |
| elif authentication_status == False: | |
| st.error('⛔ 用户名或密码错误！') | |
| elif authentication_status == None: | |
| st.warning('⬆ 请先登录！') | |
| if __name__ == "__main__": | |
| import asyncio | |
| try: | |
| match navi_menu: | |
| case "核心模式": | |
| # if navi_menu == "核心模式": | |
| print(f'navi_menu 选择了 {navi_menu}') | |
| # reset_all() | |
| # * 也可以用命令执行这个python文件。’streamlit run frontend/app.py‘ | |
| # asyncio.run(text_mode()) | |
| text_mode() | |
| # elif navi_menu == "信息检索模式": | |
| case "联网模式": | |
| # print(f'navi_menu 选择了 {navi_menu}') | |
| # reset_all() | |
| ##TODO 如下设置中的index=None, 可能可以解决了刷屏会调回第一项的问题？好像不会。 | |
| # radio_2 = st.radio(label='信息检索源选择:', options=['互联网', '维基百科', '本地文档', '文献库', '企业知识库','知识图谱库'], horizontal=True, label_visibility='visible') | |
| ### 横向排列的checkbox选项。也可以实现多项选择的功能。 | |
| # col_1, col_2, col_3, col_4, col_5 = st.columns(5) | |
| # rag_1 = col_1.checkbox(label='互联网', label_visibility='visible') | |
| # rag_2 = col_2.checkbox(label='上传文件', label_visibility='visible') | |
| # rag_3 = col_3.checkbox(label='企业知识库', label_visibility='visible') | |
| # rag_4 = col_4.checkbox(label='百科全书', label_visibility='visible') | |
| # rag_5 = col_5.checkbox(label='其他数据源', label_visibility='visible') | |
| if (navi_menu=='联网模式'): | |
| # print(f'radio 选择了 {radio_2}') | |
| # asyncio.run(text_mode()) | |
| text_mode() | |
| case "知识库模式": | |
| print(f'navi_menu 选择了 {navi_menu}') | |
| st.session_state.messages = [] | |
| # ### llama_index框架的RAG代码，最近更新版本后不成功，会报错。 | |
| # path = f'./{username}/vector_store.json' | |
| # if os.path.exists(path): | |
| # print(f'{path} local KB exists') | |
| # database_info = pd.read_csv(f'./{username}/database_name.csv') | |
| # current_database_name = database_info.iloc[-1][0] | |
| # current_database_date = database_info.iloc[-1][1] | |
| # database_claim = f"当前知识库为：{current_database_name}，创建于{current_database_date}。可以开始提问！" | |
| # st.markdown(database_claim) | |
| ### Langchain框架的RAG代码。 | |
| path = f'./{username}/faiss_index/index.faiss' | |
| if os.path.exists(path): | |
| print(f'{path} local KB exists') | |
| database_info = pd.read_csv(f'./{username}/database_name.csv', encoding='utf-8', header=None) ## 不加encoding的话，中文名字的PDF会报错。 | |
| print(database_info) | |
| current_database_name = database_info.iloc[-1][0] | |
| current_database_date = database_info.iloc[-1][1] | |
| database_claim = f"当前知识库为：{current_database_name}，创建于{current_database_date}。可以开始提问！" | |
| st.markdown(database_claim) | |
| try: | |
| uploaded_file = st.file_uploader( | |
| "选择上传一个新知识库", type=(["pdf"])) | |
| # 默认状态下没有上传文件，None，会报错。需要判断。 | |
| if uploaded_file is not None: | |
| # uploaded_file_path = upload_file(uploaded_file) | |
| upload_file(uploaded_file) | |
| except Exception as e: | |
| print(e) | |
| pass | |
| try: | |
| ## 启动本地知识库模式。 | |
| localKB_mode(username) | |
| # asyncio.run(localKB_mode(username)) | |
| except Exception as e: | |
| print(e) | |
| pass | |
| # elif navi_menu == "数据分析模式": | |
| case "数据分析模式": | |
| # reset_message() | |
| uploaded_file = st.file_uploader( | |
| "选择一个文件", type=(["csv", "xlsx", "xls"])) | |
| # 默认状态下没有上传文件，None，会报错。需要判断。 | |
| if uploaded_file is not None: | |
| # uploaded_file_path = upload_file(uploaded_file) ### original code here. | |
| csv_filename = upload_file(uploaded_file) | |
| # asyncio.run(data_mode()) | |
| reset_all() | |
| data_mode() | |
| # elif navi_menu == "智能体模式": | |
| case "智能体模式": | |
| uploaded_file = st.file_uploader( | |
| "选择一个文件", type=(["csv"])) | |
| reset_all() | |
| print('st uploaded_file:',uploaded_file) | |
| # 默认状态下没有上传文件，None，会报错。需要判断。 | |
| # if uploaded_file is not None: | |
| if uploaded_file is not None: | |
| uploaded_file_path = upload_file(uploaded_file) | |
| # asyncio.run(data_mode()) | |
| else: | |
| uploaded_file_path = None | |
| # st.markdown('**此功能还在内部测试阶段，尚未开放，敬请期待！**') | |
| # reset_message() | |
| print('st_msautogen starts!') | |
| uploaded_file_path = '/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/joeshi_upload.csv' | |
| # asyncio.run(st_msautogen.auto_gen(uploaded_file_path)) ## 好像不需要启动asyncio，也可以正常运行。在msautogen中已经启动了。 | |
| st_msautogen.auto_gen(uploaded_file_path) ## 这里不需要使用asyncio.run()，否则会streamlit中会刷新页面？ | |
| except Exception as e: | |
| print('Exception Raised:',e) | |
| pass |