Update app.py

app.py

@@ -1,51 +1,33 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-import wikipedia
-from PIL import Image
-import requests
-import torch
-from torchvision import transforms
-from torchvision.models import resnet50
 
-# Initialize inference client for chat
-chat_client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-# Initialize Wikipedia API
-wiki_wiki = wikipediaapi.Wikipedia('en')
+"""
+For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-# Load pre-trained image classification model
-model = resnet50(pretrained=True)
-model.eval()
-transform = 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]),
-])
 
-def search_wikipedia(query):
-    page = wiki_wiki.page(query)
-    if page.exists():
-        return page.summary
-    else:
-        return "No information found on that topic."
-
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    # Search Wikipedia for information
-    search_response = search_wikipedia(message)
-    
-    # Prepare the chat messages
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
+
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
-    
+
     messages.append({"role": "user", "content": message})
-    
-    # Generate response from chat model
+
     response = ""
-    for message in chat_client.chat_completion(
+
+    for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
@@ -53,67 +35,30 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-        response += token
-        yield response, search_response  # Return both responses
 
-def classify_image(image):
-    image = transform(image).unsqueeze(0)
-    with torch.no_grad():
-        output = model(image)
-    _, predicted = torch.max(output, 1)
-    return f"Predicted class index: {predicted.item()}"
-
-# Gradio interface setup using Blocks
-with gr.Blocks() as demo:
-    gr.Markdown("## Multi-Functional AI Interface")
-    
-    with gr.Tab("Chatbot with Wikipedia Search"):
-        with gr.Row():
-            with gr.Column():
-                system_message = gr.Textbox(value="You are a friendly Chatbot named Tirth.", label="System message")
-                max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
-                temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
-                top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
-            
-            with gr.Column():
-                chat_output = gr.Chatbot(label="Chat History")
-                user_input = gr.Textbox(placeholder="Type your message here...", label="Your Message")
-                submit_btn = gr.Button("Send")
-
-        def on_submit(message, history):
-            response, search_response = respond(message, history, system_message.value, max_tokens.value, temperature.value, top_p.value)
-            return history + [(message, response)], search_response
-
-        submit_btn.click(on_submit, inputs=[user_input, chat_output], outputs=[chat_output, gr.Textbox(label="Wikipedia Summary")])
-
-    with gr.Tab("Image Classification"):
-        image_input = gr.Image(type="pil", label="Upload an Image")
-        classify_btn = gr.Button("Classify Image")
-        classification_output = gr.Textbox(label="Classification Result")
-        
-        classify_btn.click(classify_image, inputs=image_input, outputs=classification_output)
-
-    with gr.Tab("Video Generation"):
-        video_input = gr.Video(label="Upload a Video")
-        generate_video_btn = gr.Button("Generate Video")
-        video_output = gr.Video(label="Generated Video")
-        
-        # Placeholder for video generation logic (implement as needed)
-        def generate_video(video):
-            return video  # Just returns the input video for now
+        response += token
+        yield response
 
-        generate_video_btn.click(generate_video, inputs=video_input, outputs=video_output)
 
-    with gr.Tab("Video Classification"):
-        video_class_input = gr.Video(label="Upload a Video for Classification")
-        classify_video_btn = gr.Button("Classify Video")
-        video_classification_output = gr.Textbox(label="Video Classification Result")
-        
-        # Placeholder for video classification logic (implement as needed)
-        def classify_video(video):
-            return "Video classification logic not implemented."  # Placeholder
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot named Tirth.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
 
-        classify_video_btn.click(classify_video, inputs=video_class_input, outputs=video_classification_output)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()