import gradio as gr import models import results import theme text = "

AI TCO Comparison Calculator" text2 = "Please note that 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"""

In this calculator, we help you compare different AI model services, such as SaaS or "Deploy yourself" solutions, based on the Total Cost of Ownership for their deployment. 😊

Please note that we focus on getting the AI model service up and running, but not the additional maintenance costs that follow.🚀

If you want to contribute to the calculator by adding your own AI service option, follow this tutorial 👈.

""" formula = r""" $CR = \frac{CIT_{1K} \times IT + COT_{1K} \times OT}{1000}$
with:
$CR$ = Cost per Request
$CIT_{1K}$ = Cost per 1000 Input Tokens
$COT_{1K}$ = Cost per 1000 Output Tokens
$IT$ = Input Tokens
$OT$ = Output Tokens """ def set_shared_data(page1, page2): return page1, page2 def on_use_case_change(use_case): if use_case == "Summarize": return gr.update(value=500), gr.update(value=200) elif use_case == "Question-Answering": return gr.update(value=300), gr.update(value=300) else: return gr.update(value=50), gr.update(value=10) style = theme.Style() with gr.Blocks(theme=style) as demo: Models: list[models.BaseTCOModel] = [models.OpenAIModelGPT4, models.OpenAIModelGPT3_5, models.CohereModel, models.DIYLlama2Model] model_names = [Model().get_name() for Model in Models] gr.Markdown(value=text) gr.Markdown(value=description) with gr.Row(): with gr.Column(): with gr.Row(): use_case = gr.Dropdown(["Summarize", "Question-Answering", "Classification"], value="Question-Answering", label=" Describe your use case ") with gr.Accordion("Click here if you want to customize the number of input and output tokens per request", open=False): with gr.Row(): input_tokens = gr.Slider(minimum=1, maximum=1000, value=300, step=1, label=" Input tokens per request", info="We suggest a value that we believe best suit your use case choice but feel free to adjust", interactive=True) output_tokens = gr.Slider(minimum=1, maximum=1000, value=300, step=1, label=" Output tokens per request", info="We suggest a value that we believe best suit your use case choice but feel free to adjust", interactive=True) with gr.Row(visible=False): num_users = gr.Number(value="1000", interactive = True, label=" Number of users for your service ") use_case.change(on_use_case_change, inputs=use_case, outputs=[input_tokens, output_tokens]) with gr.Row(): with gr.Column(): page1 = models.ModelPage(Models) dropdown = gr.Dropdown(model_names, interactive=True, label=" First AI service option ") with gr.Accordion("Click here for more information on the computation parameters for your first AI service option", open=False): page1.render() with gr.Column(): page2 = models.ModelPage(Models) dropdown2 = gr.Dropdown(model_names, interactive=True, label=" Second AI service option ") with gr.Accordion("Click here for more information on the computation parameters for your second AI service option", open=False): page2.render() shared_page1, shared_page2 = set_shared_data(page1, page2) results.set_shared_pages(shared_page1, shared_page2) dropdown.change(page1.make_model_visible, inputs=[dropdown, use_case], outputs=page1.get_all_components()) dropdown2.change(page2.make_model_visible, inputs=[dropdown2, use_case], outputs=page2.get_all_components()) compute_tco_btn = gr.Button("Compute & Compare", size="lg", variant="primary", scale=1) tco1, tco2, labor_cost1, labor_cost2, latency, latency2 = [gr.State() for _ in range(6)] with gr.Row(): with gr.Accordion("Click here to see the cost/request computation formula", open=False): tco_formula = gr.Markdown(formula) with gr.Row(variant='panel'): with gr.Column(): with gr.Row(): table = gr.Markdown() with gr.Row(): info = gr.Markdown(text2) with gr.Row(): with gr.Column(scale=1): image = gr.Image(visible=False) ratio = gr.Markdown() with gr.Column(scale=2): plot = gr.LinePlot(visible=False) compute_tco_btn.click(results.compute_cost_per_request, inputs=page1.get_all_components_for_cost_computing() + page2.get_all_components_for_cost_computing() + [dropdown, dropdown2, input_tokens, output_tokens], outputs=[tco1, latency, labor_cost1, tco2, latency2, labor_cost2])\ .then(results.create_table, inputs=[tco1, tco2, labor_cost1, labor_cost2, dropdown, dropdown2, latency, latency2], outputs=table)\ .then(results.compare_info, inputs=[tco1, tco2, dropdown, dropdown2], outputs=[image, ratio])\ .then(results.update_plot, inputs=[tco1, tco2, dropdown, dropdown2, labor_cost1, labor_cost2], outputs=plot) demo.launch(debug=True)