app.py

import gradio as gr
from transformers import pipeline
from huggingface_hub import InferenceClient, login
import gtts

from transformers import pipeline

# Load sentiment analysis model
sentiment_pipeline = pipeline(
    "sentiment-analysis",
    model="distilbert/distilbert-base-uncased-finetuned-sst-2-english"
)

# Define sentiment analysis function
def analyze_sentiment(text):
    result = sentiment_pipeline(text)[0]
    label = result["label"]
    score = result["score"] * 100
    return f"{label} — {score:.2f}%"

from huggingface_hub import InferenceClient, login
import gradio as gr


# Load Mistral model
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")

# Response generator
def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    for user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})
    messages.append({"role": "user", "content": message})

    response = ""
    for chunk in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = chunk.choices[0].delta.content or ""
        response += token
        yield response

from transformers import pipeline

# Load summarization pipeline
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

# Define summarization function
def summarize_text(text):
    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
    return summary[0]["summary_text"]

import gtts

# Define text-to-speech function
def text_to_speech(text):
    tts = gtts.gTTS(text)
    tts.save("output.mp3")
    return "output.mp3"

"""*🚀* Gradio Multi-Tab Interface
(final step to connect all functions above into UI)
"""

import gradio as gr

with gr.Blocks(theme=gr.themes.Soft(primary_hue="purple")) as demo:
    gr.Image(
        value="https://www.leaders-mena.com/leaders/uploads/2024/09/Tuwaiq-Meta-780x470.jpg",
        show_label=False,
        show_download_button=False,
        height=120
    )

    gr.Markdown(
        "<h1 style='text-align: center; color: orange;'>🌟 TrailTrek Gears - All-in-One AI App</h1>",
        elem_id="main-title"
    )

    # 📊 Sentiment Analysis Tab
    with gr.Tab("📊 Sentiment Analysis"):
        sentiment_input = gr.Textbox(label="Enter your text")
        sentiment_output = gr.Textbox(label="Sentiment Result")
        sentiment_btn = gr.Button("Analyze Sentiment")
        sentiment_btn.click(analyze_sentiment, inputs=sentiment_input, outputs=sentiment_output)

    # 💬 Chatbot Tab
    with gr.Tab("💬 Chatbot"):
        gr.Markdown("### Simple Chat with Mistral-7B")
        chatbot_output = gr.Textbox(label="Chat History", lines=10, interactive=False, show_copy_button=True)
        chatbot_input = gr.Textbox(label="Your Message", placeholder="Type something...")
        chatbot_history = gr.State([])

        def custom_chat_simple(user_input, history):
            if history is None:
                history = []
            system_message = "You are a helpful and polite assistant."
            gen = respond(user_input, history, system_message, 256, 0.5, 0.95)
            final_response = ""
            for chunk in gen:
                final_response = chunk
            history.append((user_input, final_response))
            chat_display = ""
            for user, bot in history:
                chat_display += f"🧑: {user}\n🤖: {bot}\n\n"
            return chat_display, history

        send_button = gr.Button("Send")
        send_button.click(fn=custom_chat_simple, inputs=[chatbot_input, chatbot_history], outputs=[chatbot_output, chatbot_history])

    # ✂️ Summarization Tab
    with gr.Tab("✂️ Summarization"):
        input_text = gr.Textbox(lines=8, label="Enter long text")
        output_summary = gr.Textbox(label="Summary")
        summarize_btn = gr.Button("Summarize")
        summarize_btn.click(summarize_text, inputs=input_text, outputs=output_summary)

    # 🔈 Text-to-Speech Tab
    with gr.Tab("🔈 Text-to-Speech"):
        tts_input = gr.Textbox(label="Enter text to convert to audio")
        tts_output = gr.Audio(label="Generated Speech")
        tts_btn = gr.Button("Generate Audio")
        tts_btn.click(text_to_speech, inputs=tts_input, outputs=tts_output)

demo.launch()