Upload 2 files

app.py

@@ -0,0 +1,158 @@
+'''
+参考： https://github.com/shroominic/codeinterpreter-api
+
+1. 可以存在本地，然后再调出来。 working. 
+1. 可以直接在内存中读出图片。
+'''
+# TODO：如何在内存中读取文件。
+
+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
+from io import StringIO
+import csv
+import tempfile
+from tempfile import NamedTemporaryFile
+import pathlib
+from pathlib import Path
+
+
+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"
+#         }
+
+
+# st.title("ChatGPT-like clone")
+st.title("Business Data Analytics by ChatGPT")
+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)
+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。
+
+    uploaded_file_name = "File_provided"
+    temp_dir = tempfile.TemporaryDirectory()
+    uploaded_file_path = pathlib.Path(temp_dir.name) / uploaded_file_name #! working. 
+    with open(uploaded_file_path, 'wb') as output_temporary_file:
+        # output_temporary_file.write(uploaded_file.read())
+        output_temporary_file.write(uploaded_file.getvalue()) #! 必须用这种格式读入内容，然后才可以写入temporary文件夹中。
+        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')
+
+# openai.api_key = st.secrets["OPENAI_API_KEY"]
+
+async def main():
+    if "openai_model" not in st.session_state:
+        # st.session_state["openai_model"] = "gpt-3.5-turbo"
+        st.session_state["openai_model"] = "gpt-4" ##NOTE: data analysis module must use GPT-4. 
+
+    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"])
+
+    if prompt := st.chat_input("What is up?"):
+        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 = ""
+
+            ###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 = "【背景要求】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（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='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。
+
+                user_request = environ_settings + "\n\n"+ "你需要完成以下任务：\n\n" + prompt
+                # print('user_request: \n', user_request)
+
+                # files = [
+                #     # File.from_path("examples/assets/iris.csv"),
+                #     # File.from_path("/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/ChatGPT讲课要点 copy.txt"),
+                #     # File.from_path("/Users/yunshi/Downloads/360Data/文档/cars.csv"),
+                #     # File.from_path("/Users/yunshi/Downloads/360Data/PhD Program/SAS邓祖新/SAS(邓祖新)/sasdata/sasdata/mydir/sasxls.xls"),
+                #     # File.from_path("/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/rawdata/时间频数统计.xlsx"),
+                #     # File.from_path("/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/rawdata/文献相关数据.xls"),
+                #     File.from_path(
+                #         "/Users/yunshi/Downloads/360Data/Data Center/Working-On Task/演讲与培训/2023ChatGPT/Coding/code_interpreter/codeinterpreter-api-main/examples/assets/iris.csv"),
+                # ]  # user_request = "对于文件中的【SepalLengthCm	SepalWidthCm】数据，进行【IsolationForest】的异常值分析。你需要展示分析图表，并给出分析结果。最后，你要给出异常点的原始数据，"
+
+
+                ### 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))]
+
+                ### 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. 
+                
+
+                # message_placeholder.markdown(full_response + "▌") ## orignal code.
+            # message_placeholder.markdown(full_response) ## orignal code.
+            st.write(full_response)
+            await session.astop() #! 确认需要关闭。
+
+        st.session_state.messages.append(
+            {"role": "assistant", "content": full_response})
+
+        
+
+if __name__ == "__main__":
+    import asyncio
+    # * 也可以用命令执行这个python文件。’streamlit run frontend/app.py‘
+    asyncio.run(main())

requirements.txt

@@ -0,0 +1,5 @@
+codeinterpreterapi
+openai
+matplotlib
+pandas
+pathlib