app.py

from huggingface_hub import InferenceClient
import gradio as gr

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

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=9048, top_p=0.95, repetition_penalty=1.0):
    # ... existing code ...

    for response in stream:
        output += response.token.text
        if "http" in output:  # assuming the AI writes a direct image link in its response
            yield {"image": output}  # Gradio will display the image
        else:
            yield 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=9048, minimum=256, maximum=9048, 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")
]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="ConvoLite",
    concurrency_limit=20,
    
).launch(show_api=False,)