app.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient(
    "mistralai/Mixtral-8x7B-Instruct-v0.1"
)

# Function to handle dynamic content display
def show_info(section):
    if section == "Experiences":
        return "Details about Rishiraj's experiences..."
    elif section == "Communities":
        return "Details about communities Rishiraj is involved in..."
    elif section == "Recommendations":
        return "Rishiraj's recommendations..."
    elif section == "Conferences":
        return "Conferences attended by Rishiraj..."
    else:
        return "Select a section to display information."

# Creating Gradio Interface
with gr.Blocks() as app:
    with gr.Row():
        with gr.Column():
            gr.Markdown("# Hi 👋, I'm Rishiraj Acharya (ঋষিরাজ আচার্য্য)")
            gr.Markdown("## Google Developer Expert in ML ✨ | Hugging Face Fellow 🤗 | GSoC '22 at TensorFlow 👨🏻‍🔬 | TFUG Kolkata Organizer 🎙️ | Kaggle Master 🧠 | Dynopii ML Engineer 👨🏻‍💻")
        with gr.Column():
            gr.Image("profile.png")
    
    with gr.Row():
        section_dropdown = gr.Dropdown(["Experiences", "Communities", "Recommendations", "Conferences"], label="Select Information to Display")
        info_display = gr.Textbox(label="Information")
    
    section_dropdown.change(show_info, inputs=section_dropdown, outputs=info_display)

def format_prompt(message, history):
  prompt = "<s>"
  for user_prompt, bot_response in history:
    prompt += f"[INST] {user_prompt} [/INST]"
    prompt += f" {bot_response}</s> "
  prompt += f"[INST] {message} [/INST]"
  return prompt

def generate(
    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output


additional_inputs=[
    gr.Textbox(
        label="System Prompt",
        max_lines=1,
        interactive=True,
    ),
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=1048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

examples=[["Can you explain how the QuickSort algorithm works and provide a Python implementation?", None, None, None, None, None,],
          ["What are some unique features of Rust that make it stand out compared to other systems programming languages like C++?", None, None, None, None, None,],
         ]

llm = gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="bubble"),
    additional_inputs=additional_inputs,
    title="Hi 👋, I'm Rishiraj Acharya (ঋষিরাজ আচার্য্য)",
    examples=examples,
    concurrency_limit=20,
)

demo = gr.TabbedInterface([app, llm], ["About", "Chat"])
demo.launch()