Improve prompt

app.py

@@ -25,8 +25,8 @@ agent = ReactCodeAgent(
 )
 
 base_prompt = """You are an expert data analyst.
-Please load the source file with pandas and analyze its content (you cannot use 'os' module).
-According to the features you have, begin by finding which feature should be the target.
+Please load the source file with pandas (you cannot use 'os' module).
+According to the features you have and the dta structure given below, determine which feature should be the target.
 Then list 3 interesting questions that could be asked on this data, for instance about specific correlations with target variable.
 Then answer these questions one by one, by finding the relevant numbers.
 Meanwhile, plot some figures using matplotlib/seaborn and save them to the (already existing) folder './figures/': take care to clear each figure with plt.clf() before doing another plot.
@@ -35,7 +35,9 @@ In your final answer: summarize these correlations and trends
 After each number derive real worlds insights, for instance: "Correlation between is_december and boredness is 1.3453, which suggest people are more bored in winter".
 Your final answer should be a long string with at least 3 numbered and detailed parts.
 
-source file = {source_file}
+Source file for the data = {source_file}
+Structure of the data:
+{structure_notes}
 """
 
 example_notes="""This data is about the Titanic wreck in 1912.
@@ -68,13 +70,12 @@ def interact_with_agent(file_input, additional_notes):
     os.makedirs("./figures")
 
     read_file = pd.read_csv(file_input)
-    data_structure_notes = f"""\nStructure of the data:
-    - Description (output of .describe()):
+    data_structure_notes = f"""- Description (output of .describe()):
     {read_file.describe()}
     - Columns with dtypes:
-    {read_file.dtypes}
-    """
-    prompt = base_prompt + data_structure_notes
+    {read_file.dtypes}"""
+
+    prompt = base_prompt.format(source_file=file_input, structure_notes=data_structure_notes)
 
     if additional_notes and len(additional_notes) > 0:
         prompt += "\nAdditional notes on the data:\n" + additional_notes
@@ -83,7 +84,7 @@ def interact_with_agent(file_input, additional_notes):
     yield messages
 
     plot_image_paths = {}
-    for msg in stream_from_transformers_agent(agent, prompt.format(source_file=file_input)):
+    for msg in stream_from_transformers_agent(agent, prompt):
         messages.append(msg)
         for image_path in get_images_in_directory("./figures"):
             if image_path not in plot_image_paths:
@@ -99,10 +100,10 @@ def interact_with_agent(file_input, additional_notes):
     yield messages
 
 
-with gr.Blocks(theme="soft") as demo:
+with gr.Blocks() as demo:
     gr.Markdown("""# Llama-3.1 Data analyst
 
-Drop a `.csv` file to analyse, add notes if needed, and **Llama-3.1-70B will analyse the file content for you!**""")
+Drop a `.csv` file below, add notes to describe this data if needed, and **Llama-3.1-70B will analyze the file content and draw figures for you!**""")
     file_input = gr.File(label="Your file to analyze")
     text_input = gr.Textbox(
         label="Additional notes to support the analysis"