Upload app.py

app.py

@@ -2,60 +2,68 @@
 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']})      
+
 '''
-# TODO：如何在内存中读取文件。
+# TODO：
 
-import matplotlib as mpl
 from codeinterpreterapi import CodeInterpreterSession, File
 import streamlit as st
 from codeinterpreterapi import CodeInterpreterSession
 import openai
 import os
 import matplotlib.pyplot as plt
+import xlrd
 import pandas as pd
-from io import StringIO
-import csv
+# from io import StringIO
+# import csv
 import tempfile
 from tempfile import NamedTemporaryFile
 import pathlib
 from pathlib import Path
-import matplotlib
 from matplotlib.font_manager import FontProperties
 import seaborn as sns
 
+
 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？
 
-# 设置中文字体。
-# myfont = FontProperties(fname='SimHei.ttf')  # NOTE: 注意这里的云服务器路径格式。
-# mpl.rcParams['font.family'] = ['myfont']
-# sns.set(font='myfont')
-# plt.rcParams['font.sans-serif'] = ['myfont']
-# plt.rcParams['font.family'] = 'sans-serif'
-# plt.title("这个是数据分布图", fontsize=12, fontproperties=myfont)
-# plt.xlabel('数据A', fontproperties=myfont)
-
-
-# # #* 如果碰到接口问题，可以启用如下设置。
+# #* 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",
+#     "http": "http://127.0.0.1:7890",
 #             "https": "http://127.0.0.1:7890"
-#         }
+# }
 
+# layout settings.
+st.title("个人大语言模型商业智能中心")
+st.subheader("Artificial Intelligence Backend Center for Individuals")
+# col1, col2 = st.columns(spec=[1, 2])
+# radio_1 = col1.radio(label='ChatGPT版本', options=[
+#     'GPT-3.5', 'GPT-4.0'], horizontal=True, label_visibility='visible')
+# radio_2 = col2.radio(label='模式选择', options=[
+#     '核心模式', '联网模式', '数据模式'], horizontal=True, label_visibility='visible')
 
-# st.title("ChatGPT-like clone")
-st.title("大语言模型商业数据分析中心")
-st.subheader("Business Data Analytics Based Upon LLM")
 uploaded_file = st.file_uploader(
-    "Choose a file", type=(["csv", "txt", "xlsx", "xls"]))
-# uploaded_file = st.file_uploader("选择一个文件", type=(["csv","txt","xlsx","xls"]))
-# st.write(uploaded_file)
+    "选择一个文件", type=(["csv", "xlsx", "xls"]))
+
 if uploaded_file is not None:
-    # csv_file = csv.reader(uploaded_file)
-    csv_file = pd.read_csv(uploaded_file)
-    st.write(csv_file[:5])  # 这里只是显示文件，后面需要定位文件所在的绝对路径。
+    filename=uploaded_file.name
+    # st.write(filename) ## print out the whole file name to validate. 
+    try:
+        if '.csv' in filename:
+            csv_file = pd.read_csv(uploaded_file)
+            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)
+            st.write(xls_file[:3])
+    except Exception as e:
+        st.write(e)
 
     uploaded_file_name = "File_provided"
     temp_dir = tempfile.TemporaryDirectory()
@@ -65,42 +73,61 @@ if uploaded_file is not None:
         # output_temporary_file.write(uploaded_file.read())
         # ! 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
-
-# how to read data inside streamlit.
-#     # files = pd.read_csv(uploaded_file)
-#     bytes_data = uploaded_file.getvalue()
-#     # st.write(bytes_data)
-
-#     # To convert to a string based IO:
-#     stringio = StringIO(uploaded_file.getvalue().decode("utf-8"))
-#     # st.write(stringio)
-
-#     # To read file as string:
-#     string_data = stringio.read()
-#     # st.write(string_data)
-
-#     # Can be used wherever a "file-like" object is accepted:
-#     # dataframe = pd.read_csv(uploaded_file)
-#     files = pd.read_csv(uploaded_file, encoding='utf-8')
+        st.write(uploaded_file_path)  # * 可以查看文件是否真实存在，然后是否可以
+
+import requests
+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 main():
 async def main():
+    col1, col2 = st.columns(spec=[1, 2])
+    radio_1 = col1.radio(label='ChatGPT版本', options=[
+    'GPT-3.5', 'GPT-4.0'], horizontal=True, label_visibility='visible')
+    radio_2 = col2.radio(label='模式选择', options=[
+    '核心模式', '联网模式', '数据模式'], horizontal=True, label_visibility='visible')
+
+    ## Set a default model
     if "openai_model" not in st.session_state:
-        # st.session_state["openai_model"] = "gpt-3.5-turbo"
-        # NOTE: data analysis module must use GPT-4.
+        st.session_state["openai_model"] = "gpt-3.5-turbo-16k"
+
+    if radio_1 == 'GPT-3.5':
+        print('radio_1: GPT-3.5 starts!')
+        st.session_state["openai_model"] = "gpt-3.5-turbo-16k"
+    else:
+        print('radio_1: GPT-4.0 starts!')
         st.session_state["openai_model"] = "gpt-4"
 
+    # 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"])
 
-    if prompt := st.chat_input("What is up?"):
+    # Display assistant response in chat message container
+    if prompt := st.chat_input("Ask something?"):
         st.session_state.messages.append({"role": "user", "content": prompt})
         with st.chat_message("user"):
             st.markdown(prompt)
@@ -109,78 +136,114 @@ async def main():
             message_placeholder = st.empty()
             full_response = ""
 
-            # 原始示例 https://docs.streamlit.io/knowledge-base/tutorials/build-conversational-apps
-            # 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 + "▌")
-
-            async with CodeInterpreterSession() as session:
-                # 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 = "【<默认要求> 如果我没有告诉你任何定制化的要求，那么请按照以下的默认要求来回答：1. 你需要用提问的语言来回答（即：如果我用中文提问，你就用中文来回答；我如果用英文提问吗，你就用英文来回答）。2. 如果要求你输出图表，那么图的解析度dpi需要设定为300。图尽量使用seaborn库。seaborn库的参数设定：sns.set(rc={'axes.facecolor':'#FFF9ED','figure.facecolor':'#FFF9ED'}, palette='deep')。】" ## 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。
-                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. 你需要用提问的语言来回答（如：中文提问你就用中文来回答，英文提问你就用英文来回答）。
-                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='bright')。
-                -------------------------------------------------------------------------
-                """  # 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。
-
-                # sns.set(font='myfont')
-
-                user_request = environ_settings + "\n\n" + \
-                    "你需要完成以下任务：\n\n" + prompt + f"注：文件位置在{uploaded_file_path}"
-                # 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))]
-
-                with st.status('processing...', expanded=True, state='running') as status:
-                    
-                    # generate the response
-
-                    response = await session.generate_response(
-                        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.
-                        # file.show_image()
-                        myfont = FontProperties(fname='SimHei.ttf')  # NOTE: 注意这里的云服务器路径格式。
-                        sns.axes_style("whitegrid", {'font.sans-serif':['myfont','Arial']})
-                        plt.rcParams['font.sans-serif'] = ['myfont']
-                        plt.title(label="这个是中文数据分布图", fontproperties=myfont)
-                        
-
-                        # * 注意这里的设定，可以提高图片的精细程度。
-                        file.show_image() #TODO: 看一下是否可以直接出图，图的质量和文字是否okay？
-                        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：看看是否缩进准确？ 放在这里好像可以。
-            await session.astop()  # ! 确认需要关闭。
-
-        st.session_state.messages.append(
-            {"role": "assistant", "content": full_response})
-
+            if radio_2 == '数据分析模式':
+                print('数据分析模式启动！')
+
+                # clear cache to avoid any potential history problems. 
+                st.cache_resource.clear()
+
+                with st.chat_message("assistant"):
+                    # message_placeholder = st.empty()
+                    # full_response = ""
+                    async with CodeInterpreterSession() as session:
+                        # 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. 你需要用提问的语言来回答（如：中文提问你就用中文来回答，英文提问你就用英文来回答）。
+                        2. 如果要求你输出图表，那么图的解析度dpi需要设定为300。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. 如果需要显示中文，那么设置如下：
+                            3.1 首先，你需要安装中文字体：
+                                myfont=FontProperties(fname='/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/rawdata/SimHei.ttf')
+                            3.2 然后，你需要设定在matplotlib（plt）和seaborn（sns）中设定：
+                                    sns.set_style({'font.sans-serif':['Arial','SimHei']})
+                                    plt.rcParams['font.sans-serif'] = ['SimHei'] 
+                                    plt.rcParams['font.family']='sans-serif'
+                                    plt.title(fontsize = 18)
+                        -------------------------------------------------------------------------
+                        """  # 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。
+
+                        user_request = environ_settings + "\n\n" + \
+                            "你需要完成以下任务：\n\n" + prompt + \
+                            f"注：文件位置在{uploaded_file_path}"
+                        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))]
+
+                        with st.status('processing...', expanded=True, state='running') as status:
+                            # generate the response
+                            response = await session.generate_response(
+                                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')
+                        # st.session_state.messages.append(
+                        #     {"role": "assistant", "content": full_response})
+
+                        await session.astop() #! 确认需要关闭。
+                # st.session_state.messages.append({"role": "assistant", "content": full_response})
+
+            elif 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})
+
+                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})
+
+            elif radio_2 == '核心模式':
+                print('GPT only starts!!!')
+                print('st.session_state now:', st.session_state)
+                # st.session_state.messages.append({"role": "system", "content": 'You are a helpful AI assistant: ChatGPT.'})
+                
+                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,
+                ):
+                    # if len(response)>0:
+                    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})
+                
 
 if __name__ == "__main__":
     import asyncio