Update app.py

app.py

@@ -86,14 +86,12 @@ class PromptRefiner:
                 {"role": "system", "content": "You are a helpful assistant. Answer in stylized version with latex format or markdown if relevant. Separate your answer into logical sections using level 2 headers (##) for sections and bolding (**) for subsections.Incorporate a variety of lists, headers, and text to make the answer visually appealing"},
                 {"role": "user", "content": prompt}
             ]
-
             response = self.client.chat_completion(
                 model=model,
                 messages=messages,
                 max_tokens=2000,
                 temperature=0.8
             )
-
             output = response.choices[0].message.content.strip()
             output = output.replace('\n\n', '\n').strip()
             return output
@@ -103,8 +101,6 @@ class PromptRefiner:
 class GradioInterface:
     def __init__(self, prompt_refiner: PromptRefiner):
         self.prompt_refiner = prompt_refiner
-
-        # Define custom CSS for containers
         custom_css = """
         .container {
             border: 2px solid #2196F3;
@@ -126,7 +122,6 @@ class GradioInterface:
             font-size: 1.2em;
         }
 
-        /* Remove default Gradio styles */
         .no-background > div:first-child {
             border: none !important;
             background: transparent !important;
@@ -140,7 +135,6 @@ class GradioInterface:
         .results-container::before { content: 'RESULTS'; }
         .examples-container::before { content: 'EXAMPLES'; }
 
-        /* Custom styling for radio buttons */
         .radio-group {
             display: flex;
             gap: 10px;
@@ -149,13 +143,11 @@ class GradioInterface:
         """
 
         with gr.Blocks(css=custom_css, theme=gr.themes.Default()) as self.interface:
-            # Title Container
             with gr.Column(elem_classes=["container", "title-container"]):
                 gr.Markdown("# PROMPT++")
                 gr.Markdown("### Automating Prompt Engineering by Refining your Prompts")
-                gr.Markdown("Learn how to generate an improved version of your prompts. Enter a main idea for a prompt, choose a meta prompt, and the model will attempt to generate an improved version.")
+                gr.Markdown("Learn how to generate an improved version of your prompts.")
 
-            # Input Container
             with gr.Column(elem_classes=["container", "input-container"]):
                 prompt_text = gr.Textbox(
                     label="Type the prompt (or let it empty to see metaprompt)",
@@ -171,7 +163,6 @@ class GradioInterface:
                 )
                 refine_button = gr.Button("Refine Prompt")
 
-            # Analysis Container
             with gr.Column(elem_classes=["container", "analysis-container"]):
                 gr.Markdown("### Initial prompt analysis")
                 analysis_evaluation = gr.Markdown()
@@ -186,7 +177,6 @@ class GradioInterface:
             with gr.Accordion("Full Response JSON", open=False, visible=False):
                 full_response_json = gr.JSON()
 
-            # Model Application Container
             with gr.Column(elem_classes=["container", "model-container"]):
                 gr.Markdown("## See MetaPrompt Impact")            
                 with gr.Row():
@@ -201,12 +191,11 @@ class GradioInterface:
                             "microsoft/Phi-3.5-mini-instruct"
                         ],
                         value="meta-llama/Meta-Llama-3-70B-Instruct",
-                        label="Choose the Model to apply to the prompts (the one you will used)",
+                        label="Choose the Model",
                         elem_classes="no-background"
                     )
                     apply_button = gr.Button("Apply MetaPrompt")
 
-            # Results Container
             with gr.Column(elem_classes=["container", "results-container"]):
                 with gr.Tabs():
                     with gr.TabItem("Original Prompt Output"):
@@ -214,7 +203,6 @@ class GradioInterface:
                     with gr.TabItem("Refined Prompt Output"):
                         refined_output = gr.Markdown()
 
-            # Examples Container
             with gr.Column(elem_classes=["container", "examples-container"]):
                 with gr.Accordion("Examples", open=True):
                     gr.Examples(
@@ -228,12 +216,11 @@ class GradioInterface:
                             ["Is nuclear energy good?", "verse"],
                             ["How does a computer work?", "phor"],
                             ["How to make money fast?", "done"],
-                            ["how can you  prove IT0's lemma in stochastic calculus ?", "arpe"],                    
+                            ["how can you prove IT0's lemma in stochastic calculus ?", "arpe"],                    
                         ],
                         inputs=[prompt_text, meta_prompt_choice]
                     )
 
-            # Connect the buttons to their functions
             refine_button.click(
                 fn=self.refine_prompt,
                 inputs=[prompt_text, meta_prompt_choice],
@@ -246,7 +233,6 @@ class GradioInterface:
                 outputs=[original_output, refined_output]
             )
 
-    # Your existing methods remain the same
     def refine_prompt(self, prompt: str, meta_prompt_choice: str) -> tuple:
         input_data = PromptInput(text=prompt, meta_prompt_choice=meta_prompt_choice)
         result = self.prompt_refiner.refine_prompt(input_data)
@@ -278,7 +264,6 @@ metaprompt_explanations = {
 
 explanation_markdown = "".join([f"- **{key}**: {value}\n" for key, value in metaprompt_explanations.items()])
 
-# Main code to run the application
 if __name__ == '__main__':
     meta_info=""
     api_token = os.getenv('HF_API_TOKEN')
@@ -297,7 +282,6 @@ if __name__ == '__main__':
     math_meta_prompt = os.getenv('metamath')
     autoregressive_metaprompt = os.getenv('autoregressive_metaprompt')
 
-
     prompt_refiner = PromptRefiner(api_token)
     gradio_interface = GradioInterface(prompt_refiner)
     gradio_interface.launch(share=True)