| import gradio as gr | |
| import models | |
| import results | |
| import theme | |
| text = "<h1 style='text-align: center; color: #333333; font-size: 40px;'>AI TCO Comparison Calculator" | |
| text2 = "<h1 style='color: #333333; font-size: 20px;'>🙌 Want to contribute?" | |
| text3 = "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." | |
| intro = f""" | |
| <p>Discover and compare various AI model services, including SaaS and "Deploy Yourself" solutions, based on the Total Cost of Ownership for their deployment. 😊</p> | |
| <p>Please keep in mind that our focus is on getting the AI model service up and running, not accounting for additional maintenance costs.🚀</p> | |
| """ | |
| contribution = f""" | |
| <p>If you want to contribute to the calculator by <strong>adding your own AI service option</strong>, follow this <a href="https://huggingface.co/spaces/mithril-security/TCO_calculator/blob/main/How_to_contribute.md">tutorial</a> 👈. </p> | |
| """ | |
| formula = r""" | |
| $CR = \frac{CIT_{1K} \times IT + COT_{1K} \times OT}{1000}$ <br> | |
| with: <br> | |
| $CR$ = Cost per Request <br> | |
| $CIT_{1K}$ = Cost per 1000 Input Tokens <br> | |
| $COT_{1K}$ = Cost per 1000 Output Tokens <br> | |
| $IT$ = Input Tokens <br> | |
| $OT$ = Output Tokens | |
| """ | |
| 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=intro + text2) | |
| gr.Markdown(value=contribution) | |
| 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() | |
| results.set_shared_pages(page1, 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(text3) | |
| 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) |