Update app.py

app.py

@@ -8,6 +8,7 @@ text0 = "<h1 style='text-align: center; color: midnightblue; font-size: 30px;'>D
 text1 = "<h1 style='text-align: center; color: midnightblue; font-size: 25px;'>First option"
 text2 = "<h1 style='text-align: center; color: midnightblue; font-size: 25px;'>Second option"
 text3 = "<h1 style='text-align: center; color: midnightblue; font-size: 30px;'>Compute and compare TCOs"
+text4 = "The cost/request only defines the infrastructure cost for deployment. The labor cost must be added for the whole AI model service deployment TCO."
 description=f"""
 <p>In this demo application, we help you compare different AI model services, such as Open source or SaaS solutions, based on the Total Cost of Ownership for their deployment. Please note that we focus on getting the service up and running, but not the maintenance that follows.</p>
 <p>First, you'll have to select your use case. Then, select the two model service options you'd like to compare. Depending on the options you chose, you could be able to customize some parameters of the set-up. Eventually, we will provide you with the cost of deployment for the selected model services, as a function of the number of requests experienced by your service. You can compare both solutions to evaluate which one best suits your needs.</p>
@@ -35,7 +36,7 @@ def on_use_case_change(use_case):
     else:
         return gr.update(value=50), gr.update(value=10)
     
-def compare(tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2):
+def compare_info(tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2):
     r = tco1 / tco2
     comparison_result3 = ""
     
@@ -58,24 +59,24 @@ def compare(tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2):
     <br>
     <p> {comparison_result} </p>
     <br>
+    <p> {text4} </p>
+    <br>
     <p> {comparison_result3} </p>
     """
     return info
 
-def create_table(tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2):
+def create_table(tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2, latency, latency2):
     list_values = []
-    labor_cost1 = round(labor_cost1, 1)
-    labor_cost2 = round(labor_cost2, 1)
-    first_sol = [tco1, labor_cost1]
-    second_sol = [tco2, labor_cost2]
+    first_sol = [tco1, labor_cost1, latency]
+    second_sol = [tco2, labor_cost2, latency2]
     list_values.append(first_sol)
     list_values.append(second_sol)
 
-    data = pd.DataFrame(list_values, index=["1)" + " " + dropdown, "2)" + " " + dropdown2], columns=["Cost/request ($) ", "Labor Cost ($/month)"])
+    data = pd.DataFrame(list_values, index=[dropdown, dropdown2], columns=["Cost/request ($) ", "Labor Cost ($/month)", "Average latency (s)"])
     
     formatted_data = data.copy()
     formatted_data["Cost/request ($) "] = formatted_data["Cost/request ($) "].apply('{:.5f}'.format)
-    formatted_data["Labor Cost ($/month)"] = formatted_data["Labor Cost ($/month)"].apply('{:.1f}'.format)
+    formatted_data["Labor Cost ($/month)"] = formatted_data["Labor Cost ($/month)"].apply('{:.0f}'.format)
 
     styled_data = formatted_data.style\
         .set_properties(**{'background-color': '#081527', 'color': '#ffffff', 'border-color': '#ffffff', 'border-width': '1px', 'border-style': 'solid'})\
@@ -139,22 +140,16 @@ with gr.Blocks(theme=style) as demo:
     tco2 = gr.State()
     labor_cost1 = gr.State()
     labor_cost2 = gr.State()
+    latency = gr.State()
+    latency2 = gr.State()
     
-    with gr.Row():  
-        with gr.Column():
-            tco_output = gr.Text("Cost/request 1: ", label=" Cost/request for the first option ", info="This is only the infrastructure cost per request for deployment, the labor cost still has to be added for the AI model service deployment TCO.")
-            latency_info = gr.Markdown()
-            with gr.Accordion("Click here to see the formula", open=False):
-                tco_formula = gr.Markdown()
-    
-        with gr.Column():
-            tco_output2 = gr.Text("Cost/request 2: ", label=" Cost/request for the second option ", info="This is only the infrastructure cost per request for deployment, the labor cost still has to be added for the AI model service deployment TCO.")
-            latency_info2 = gr.Markdown()
-            with gr.Accordion("Click here to see the formula", open=False):
-                tco_formula2 = gr.Markdown()
-                
-    with gr.Row(): 
-        gr.Markdown(markdown)
+    with gr.Row():
+        with gr.Accordion("Click here to see the cost/request computation formula", open=False):
+            with gr.Row():
+                with gr.Column():
+                    tco_formula = gr.Markdown()
+                with gr.Column():
+                    tco_formula2 = gr.Markdown()
         
     with gr.Row(variant='panel'):
         with gr.Column(scale=1):
@@ -164,6 +159,6 @@ with gr.Blocks(theme=style) as demo:
     with gr.Row():
         plot = gr.LinePlot(visible=False)
     
-    compute_tco_btn.click(page1.compute_cost_per_token, inputs=page1.get_all_components_for_cost_computing() + [dropdown, input_tokens, output_tokens], outputs=[tco_output, tco1, tco_formula, latency_info, labor_cost1]).then(page2.compute_cost_per_token, inputs=page2.get_all_components_for_cost_computing() + [dropdown2, input_tokens, output_tokens], outputs=[tco_output2, tco2, tco_formula2, latency_info2, labor_cost2]).then(create_table, inputs=[tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2], outputs=table).then(compare, inputs=[tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2], outputs=info).then(update_plot, inputs=[tco1, tco2, dropdown, dropdown2, labor_cost1, labor_cost2], outputs=plot)
+    compute_tco_btn.click(page1.compute_cost_per_token, inputs=page1.get_all_components_for_cost_computing() + [dropdown, input_tokens, output_tokens], outputs=[tco1, tco_formula, latency, labor_cost1]).then(page2.compute_cost_per_token, inputs=page2.get_all_components_for_cost_computing() + [dropdown2, input_tokens, output_tokens], outputs=[tco2, tco_formula2, latency2, labor_cost2]).then(create_table, inputs=[tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2, latency, latency2], outputs=table).then(compare_info, inputs=[tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2], outputs=info).then(update_plot, inputs=[tco1, tco2, dropdown, dropdown2, labor_cost1, labor_cost2], outputs=plot)
 
 demo.launch(debug=True)