Download app.py from allinaigc/coder002: direct link, hf CLI and curl.
- Browser
- Download file 36.7 kB
-
https://huggingface.co/spaces/allinaigc/coder002/resolve/main/app.py
- Command line
-
hf download hf://spaces/allinaigc/coder002/app.py
-
curl -L -o app.py https://huggingface.co/spaces/allinaigc/coder002/resolve/main/app.py
36.7 kB
| ''' | |
| 参考: https://github.com/shroominic/codeinterpreter-api | |
| 1. 可以存在本地,然后再调出来。 working. | |
| 1. 可以在临时文件夹中读取文件。 | |
| 1. 可以直接在内存中读出图片。 | |
| 1. 中文字体成功。 | |
| from matplotlib.font_manager import FontProperties | |
| myfont=FontProperties(fname='/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/rawdata/SimHei.ttf') | |
| sns.set_style('whitegrid',{'font.sans-serif':['simhei','Arial']}) | |
| 1. 解决了account login的问题,主要格式: | |
| ## 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}) | |
| ''' | |
| # TODO:2. account system. 3. local enterprise database. | |
| import database as db | |
| from deta import Deta # pip3 install deta | |
| import requests | |
| from codeinterpreterapi import CodeInterpreterSession, File | |
| import streamlit as st | |
| # from codeinterpreterapi import CodeInterpreterSession | |
| import openai | |
| import os | |
| import matplotlib.pyplot as plt | |
| 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 | |
| import database as db # python文件同目录下的.py程序,直接导入。 | |
| import deta | |
| from langchain.chat_models import ChatOpenAI | |
| from llama_index import StorageContext, load_index_from_storage, GPTVectorStoreIndex, LLMPredictor, PromptHelper | |
| # from llama_index import ServiceContext, QuestionAnswerPrompt ## QuestionAnswerPrompt在新版本中有import错。 | |
| from llama_index import ServiceContext | |
| import sys | |
| import time | |
| import PyPDF2 ## read the local_KB PDF file. | |
| # import localKB_construct | |
| import save_database_info | |
| from datetime import datetime | |
| import pytz | |
| import openai | |
| from openai import OpenAI | |
| os.environ["OPENAI_API_KEY"] = os.environ['user_token'] | |
| openai.api_key = os.environ['user_token'] | |
| os.environ["VERBOSE"] = "True" # 可以看到具体的错误? | |
| #* 如果碰到接口问题,可以启用如下设置。 | |
| # openai.proxy = { | |
| # "http": "http://127.0.0.1:7890", | |
| # "https": "http://127.0.0.1:7890" | |
| # } | |
| # layout settings. | |
| st.title("专业版大语言模型商业智能中心") | |
| st.subheader("Artificial Intelligence Backend Center for Professionals") | |
| # clear conversion. | |
| reset_button_key = "reset_button" | |
| reset_button = st.button(label=("扫清世间烦恼,清除所有记录,并开启一轮新对话 ▶"), | |
| key=reset_button_key, use_container_width=True, type="secondary") | |
| if reset_button: | |
| st.session_state.conversation = None | |
| st.session_state.chat_history = None | |
| st.session_state.messages = [] | |
| message_placeholder = st.empty() | |
| def clear_all(): | |
| st.session_state.conversation = None | |
| st.session_state.chat_history = None | |
| st.session_state.messages = [] | |
| message_placeholder = st.empty() | |
| return None | |
| # # with tab2: | |
| # 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: | |
| # # pdf_file = PyPDF2.PdfReader(uploaded_file) | |
| # PyPDF2.PdfReader(uploaded_file) | |
| # # st.write(pdf_file.pages[0].extract_text()) | |
| # # 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 st.spinner('正在为您解析新知识库...请耐心等待'): | |
| # with spinner: | |
| # import localKB_construct | |
| # # sleep(3) | |
| # # st.write(upload_file) | |
| # localKB_construct.process_file(uploaded_file) | |
| # st.markdown('新知识库解析成功,可以开始对话!') | |
| # spinner = st.empty() | |
| # # sleep(3) | |
| # # display = [] | |
| # else: | |
| # if '.csv' in filename: | |
| # csv_file = pd.read_csv(uploaded_file) | |
| # csv_file.to_csv('./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('./upload.csv', index=False) | |
| # st.write(xls_file[:3]) | |
| # 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.') | |
| # except Exception as e: | |
| # st.write(e) | |
| # # 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 None | |
| 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 | |
| # openai.api_key = st.secrets["OPENAI_API_KEY"] | |
| async def text_mode(): | |
| # Set a default model | |
| if "openai_model" not in st.session_state: | |
| st.session_state["openai_model"] = "gpt-3.5-turbo-16k" | |
| if radio_1 == '模型A': | |
| # print('----------'*5) | |
| print('radio_1: 模型A starts!') | |
| st.session_state["openai_model"] = "gpt-3.5-turbo-16k" | |
| else: | |
| print('radio_1: 模型B starts!') | |
| st.session_state["openai_model"] = "gpt-4-1106-preview" | |
| # 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: | |
| 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 radio_2 == '联网模式': | |
| print('联网模式入口,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}) | |
| 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, | |
| ): | |
| 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 = [] | |
| if radio_2 == '核心模式': | |
| print('GPT only starts!!!') | |
| print('messages:', st.session_state['messages']) | |
| openai_client = OpenAI() | |
| print('openai_client:', openai_client) | |
| 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, | |
| # messages=[{'role': 'system', 'content': 'you are ChatGPT'}, { | |
| # 'role': 'user', 'content': prompt}], | |
| # stream=True, | |
| ): | |
| full_response += str(response.choices[0].delta.content) | |
| message_placeholder.markdown(full_response + "▌") | |
| # print('session completed!') | |
| message_placeholder.markdown(full_response) | |
| st.session_state.messages.append( | |
| {"role": "assistant", "content": full_response}) | |
| ## load the local_KB PDF file. | |
| # async def localKB_mode(): | |
| def localKB_mode(username): | |
| ### clear all the prior conversation. | |
| # st.session_state.conversation = None | |
| # st.session_state.chat_history = None | |
| # st.session_state.messages = [] | |
| # message_placeholder = st.empty() | |
| clear_all() ## reset the conversation. | |
| 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 := st.chat_input("Say something"): | |
| # prompt = st.chat_input("Say something") | |
| # print('prompt now:', prompt) | |
| # print('----------'*5) | |
| # if prompt: | |
| if prompt := st.chat_input("Say something"): | |
| 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: | |
| with st.chat_message("assistant"): | |
| message_placeholder = st.empty() | |
| full_response = "" | |
| # if radio_2 == "知识库模式": | |
| # ! 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) | |
| # print('QA_PROMPT:', QA_PROMPT) | |
| # 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) | |
| storage_context = StorageContext.from_defaults(persist_dir=f"./{username}/") | |
| print('storage_context:',storage_context) | |
| index = load_index_from_storage(storage_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) | |
| # query_engine = index.as_query_engine(streaming=False, 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(llama_index_reply) | |
| # 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}) | |
| # 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}_upload.csv' | |
| # uploaded_file_path = "/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/test_upload.csv" | |
| print('file path:', uploaded_file_path) | |
| # st.write(f"passed file path in data_mode: {uploaded_file_path}") | |
| # tmp1 = pd.read_csv(uploaded_file_path) | |
| # st.markdown('成功启动数据模式,以下是加载的文件内容') | |
| # st.write(tmp1[:5]) | |
| # 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: | |
| if prompt: | |
| try: | |
| st.session_state.messages.append({"role": "user", "content": prompt}) | |
| with st.chat_message("user"): | |
| st.markdown(prompt) | |
| with st.chat_message("assistant"): | |
| print('111') | |
| llm_model = ChatOpenAI(model_name="gpt-4-1106-preview") | |
| # async with CodeInterpreterSession(llm=llm_model) as session: | |
| 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('Thinking...', 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}) | |
| 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.''' | |
| # 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":{}} | |
| # 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) | |
| # ## 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) | |
| '''''' | |
| # user, authentication_status, username = authenticator.login('用户登录', 'main') | |
| user, authentication_status, username = authenticator.login('用户登录', 'sidebar') | |
| # print("name", name, "username", username) | |
| if authentication_status: | |
| with st.sidebar: | |
| st.markdown( | |
| """ | |
| <style> | |
| [data-testid="stSidebar"][aria-expanded="true"]{ | |
| min-width: 400px; | |
| max-width: 400px; | |
| } | |
| """, | |
| unsafe_allow_html=True, | |
| ) | |
| 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') | |
| ## 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(): | |
| 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、且不支持长文。建议适当使用。") | |
| with st.text(body="说明"): | |
| st.markdown("* “联网模式”和“知识库模式”均基于检索功能,仅限一轮对话,不会保持之前的会话记录。") | |
| with st.text(body="说明"): | |
| st.markdown( | |
| "* “数据模式”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1-5分钟左右,期间需要保持网络畅通。") | |
| with st.text(body="说明"): | |
| st.markdown("* “数据模式”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。") | |
| st.markdown("#### 参考资料") | |
| with st.expander(label="**核心模式的专用提示词Prompt示例**", expanded=False): | |
| # with st.subheader(body="提示词Prompt"): | |
| 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2023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') | |
| col1, col2 = st.columns(spec=[1, 2]) | |
| radio_2 = col2.radio(label='模式选择', options=[ | |
| '核心模式', '联网模式', '知识库模式', '数据模式'], horizontal=True, label_visibility='visible') | |
| radio_1 = col1.radio(label='大模型选择', options=[ | |
| '模型A', '模型B'], horizontal=True, label_visibility='visible') | |
| elif authentication_status == False: | |
| st.error('⛔ 用户名或密码错误!') | |
| elif authentication_status == None: | |
| st.warning('⬅ 请先登录!') | |
| ### 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: | |
| # pdf_file = PyPDF2.PdfReader(uploaded_file) | |
| PyPDF2.PdfReader(uploaded_file) | |
| # st.write(pdf_file.pages[0].extract_text()) | |
| # 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 st.spinner('正在为您解析新知识库...请耐心等待'): | |
| with spinner: | |
| 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 🔃') | |
| # spinner = st.empty() | |
| else: | |
| if '.csv' in filename: | |
| csv_file = pd.read_csv(uploaded_file) | |
| csv_file.to_csv(f'./{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]) | |
| 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()) | |
| 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.') | |
| 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 None | |
| if __name__ == "__main__": | |
| import asyncio | |
| try: | |
| if radio_2 == "核心模式": | |
| print(f'radio 选择了 {radio_2}') | |
| # * 也可以用命令执行这个python文件。’streamlit run frontend/app.py‘ | |
| asyncio.run(text_mode()) | |
| if radio_2 == "联网模式": | |
| print(f'radio 选择了 {radio_2}') | |
| asyncio.run(text_mode()) | |
| if radio_2 == "知识库模式": | |
| print(f'radio 选择了 {radio_2}') | |
| path = f'./{username}/vector_store.json' | |
| if os.path.exists(path): | |
| 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) | |
| # st.markdown("注意:系统中已经存在一个知识库,您现在可以开始提问!") | |
| 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) | |
| localKB_mode(username) | |
| # asyncio.run(localKB_mode()) | |
| if radio_2 == "数据模式": | |
| 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) | |
| # asyncio.run(data_mode()) | |
| data_mode() | |
| except: | |
| # st.markdown('**请先登录!**') | |
| pass | |