Feature/streamlit

apps/datascience_assistant/README.md

@@ -6,21 +6,27 @@ Detailed information can be found in the [documentation](../../docs/source/agent
 ## Quick Start
 Streamlit is a Python library that makes it easy to create and share beautiful, custom web apps for machine learning and data science.
 
-To run the DS Assistant in streamlit, you need to install the Streamlit library. You can install it using pip:
+To run the DS Assistant in streamlit, you need to install additional libraries. You can install it using pip:
 ```bash
-pip install streamlit streamlit-jupyter
+pip install streamlit mistune matplotlib nbconvert
 ```
-Then, you need to set
+
 Then, you can run the DS Assistant using the following command:
 ```bash
-streamlit run app.py
+cd ../../
+streamlit run ./apps/datascience_assistant/app.py
 ```
 
 After running the command, a new tab will open in your default web browser with the DS Assistant running.
-The following are screenshots of the DS Assistant running in the browser:
 
+you can upload your dataset and write your request.
 ![img_2.png](../../resources/data_science_assistant_streamlit_1.png)
-you can view all of the codes and  in streamlit
+
+After submitting your request, DS Assistant will automatically generate a plan for this request.
+![img_2.png](../../resources/data_science_assistant_streamlit_4.png)
+
+After that, DS Assistant will automatically excute every task, you can view all of the codes and details in streamlit
 ![img_3.png](../../resources/data_science_assistant_streamlit_2.png)
+
 After you have finished using the DS Assistant, you can directly convert the running process to a pdf
 ![img_5.png](../../resources/data_science_assistant_streamlit_3.png)

apps/datascience_assistant/app.py

@@ -1,23 +1,45 @@
 import os
+import sys
 
 import streamlit as st
-from modelscope_agent.agents.data_science_assistant import DataScienceAssistant
-from modelscope_agent.tools.metagpt_tools.tool_recommend import \
-    TypeMatchToolRecommender
 
-llm_config = {
-    'model': 'qwen2-72b-instruct',
-    'model_server': 'dashscope',
-}
-os.environ['DASHSCOPE_API_KEY'] = input(
-    'Please input your dashscope api key: ')
-data_science_assistant = DataScienceAssistant(
-    llm=llm_config, tool_recommender=TypeMatchToolRecommender(tools=['<all>']))
-st.title('Data Science Assistant')
-st.write(
-    'This is a data science assistant that can help you with your data science tasks.'
-)
-st.write('Please input your request below and click the submit button.')
-user_request = st.text_input('User Request')
-if st.button('submit'):
-    data_science_assistant.run(user_request=user_request, streamlit=True)
+os.environ['DASHSCOPE_API_KEY'] = 'YOUR_API_KEY'
+
+
+def setup_project_paths():
+    current_dir = os.path.dirname(os.path.abspath(__file__))  # noqa
+    project_root_path = os.path.abspath(os.path.join(current_dir,
+                                                     '../../'))  # noqa
+    sys.path.append(project_root_path)  # noqa
+
+
+if __name__ == '__main__':
+    setup_project_paths()
+    from modelscope_agent.agents.data_science_assistant import \
+        DataScienceAssistant  # noqa
+    from modelscope_agent.tools.metagpt_tools.tool_recommend import \
+        TypeMatchToolRecommender  # noqa
+    st.title('Data Science Assistant')
+    st.write(
+        'This is a data science assistant that can help you with your data science tasks.'
+    )
+    st.write(
+        'Please input your request and upload files then click the submit button.'
+    )
+
+    files = st.file_uploader(
+        'Please upload files that you need. ', accept_multiple_files=True)
+    last_file_name = ''
+    user_request = st.text_area('User Request')
+    if st.button('submit'):
+        llm_config = {
+            'model': 'qwen2-72b-instruct',
+            'model_server': 'dashscope',
+        }
+        data_science_assistant = DataScienceAssistant(
+            llm=llm_config,
+            tool_recommender=TypeMatchToolRecommender(tools=['<all>']))
+        for file in files:
+            with open(file.name, 'wb') as f:
+                f.write(file.getbuffer())
+        data_science_assistant.run(user_request=user_request, streamlit=True)