Gradio

pip install gradio

# Create a virtual environment
python -m venv gradio-env

# Activate on Windows
gradio-env\Scripts\activate

# Activate on macOS/Linux
source gradio-env/bin/activate

# Install Gradio
pip install gradio

# For plotting capabilities
pip install "gradio[plots]"

# For audio processing
pip install "gradio[audio]"

# For all optional dependencies
pip install "gradio[all]"

pip install gradio-client

import gradio as gr
import torch
from torchvision import transforms
from torchvision.models import resnet50, ResNet50_Weights

# Load pre-trained model
model = resnet50(weights=ResNet50_Weights.DEFAULT)
model.eval()

# Image preprocessing
preprocess = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                        std=[0.229, 0.224, 0.225]),
])

# Class labels
with open("imagenet_classes.txt") as f:
    categories = [s.strip() for s in f.readlines()]

# Classification function
def classify_image(image):
    if image is None:
        return None

    # Preprocess the image
    image_tensor = preprocess(image).unsqueeze(0)

    # Get predictions
    with torch.no_grad():
        output = model(image_tensor)
        probabilities = torch.nn.functional.softmax(output[0], dim=0)

    # Return top 5 predictions
    top5_prob, top5_catid = torch.topk(probabilities, 5)
    result = []
    for i in range(5):
        result.append((categories[top5_catid[i]], float(top5_prob[i])))

    return result

# Create Gradio interface
demo = gr.Interface(
    fn=classify_image,
    inputs=gr.Image(type="pil"),
    outputs=gr.Label(num_top_classes=5),
    title="Image Classifier",
    description="Upload an image to classify it using ResNet50 trained on ImageNet.",
    examples=[
        ["examples/dog.jpg"],
        ["examples/cat.jpg"]
    ]
)

# Launch the app
if __name__ == "__main__":
    demo.launch()

import gradio as gr
import random
import time

# Mock chat response function
def chat_response(message, history):
    # Simulate typing
    for i in range(random.randint(3, 10)):
        time.sleep(0.3)
        yield "Thinking" + "." * (i % 4)

    # Based on the input, generate a response
    if "hello" in message.lower() or "hi" in message.lower():
        response = "Hello there! How can I help you today?"
    elif "how are you" in message.lower():
        response = "I'm just a computer program, but thanks for asking! What can I do for you?"
    elif "bye" in message.lower():
        response = "Goodbye! Have a great day!"
    elif "help" in message.lower():
        response = "I can assist with answering questions, providing information, or just chatting. What would you like to know?"
    elif "weather" in message.lower():
        response = "I'm sorry, I don't have access to real-time weather data. You might want to check a weather website or app for that information."
    else:
        responses = [
            "That's interesting. Tell me more.",
            "I understand. How can I help with that?",
            "Could you elaborate on that?",
            "I see. Is there anything specific you'd like to know?",
            "Thanks for sharing. What else would you like to discuss?"
        ]
        response = random.choice(responses)

    # Simulate typing the response
    for i in range(len(response)):
        time.sleep(0.05)
        yield response[:i+1]

# Create the Gradio chatbot interface
demo = gr.ChatInterface(
    fn=chat_response,
    title="Simple Chatbot Demo",
    description="A demo of Gradio's ChatInterface component with a simple rule-based bot.",
    examples=["Hello", "How are you?", "Tell me about yourself", "What's the weather like?"],
    theme="soft"
)

# Launch the app
if __name__ == "__main__":
    demo.launch()