Create app.py

app.py

@@ -0,0 +1,78 @@
+# app.py
+import gradio as gr
+from transformers import pipeline, AutoModel, AutoProcessor
+import torch
+import os
+import numpy as np
+from PIL import Image
+
+# Initialize models
+summarizer = pipeline("summarization", "csebuetnlp/mT5_multilingual_XLSum")
+translator_ar2en = pipeline("translation_ar_to_en", "Helsinki-NLP/opus-mt-ar-en")
+clip_model = AutoModel.from_pretrained("openai/clip-vit-base-patch32")
+clip_processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+# Image preprocessing
+def precompute_embeddings(image_dir="images"):
+    image_paths = [os.path.join(image_dir, f) for f in os.listdir(image_dir) 
+                  if f.lower().endswith(('.png', '.jpg', '.jpeg'))]
+    
+    embeddings = []
+    for path in image_paths:
+        image = Image.open(path)
+        inputs = clip_processor(images=image, return_tensors="pt")
+        with torch.no_grad():
+            embeddings.append(clip_model.get_image_features(**inputs))
+    return image_paths, torch.cat(embeddings)
+
+image_paths, image_embeddings = precompute_embeddings()
+
+def process(input_text, language):
+    # Text summarization
+    summary = summarizer(input_text, max_length=150, min_length=30)[0]['summary_text']
+    
+    # Translation if Arabic
+    if language == "Arabic":
+        translated = translator_ar2en(summary)[0]['translation_text']
+        query_text = translated
+    else:
+        query_text = summary
+    
+    # Text-image retrieval
+    text_inputs = clip_processor(
+        text=query_text, 
+        return_tensors="pt", 
+        padding=True, 
+        truncation=True
+    )
+    with torch.no_grad():
+        text_emb = clip_model.get_text_features(**text_inputs)
+    
+    similarities = (text_emb @ image_embeddings.T).softmax(dim=-1)
+    top_indices = similarities.topk(3).indices.numpy()
+    results = [image_paths[i] for i in top_indices]
+    
+    return summary, translated if language == "Arabic" else "", results
+
+# Gradio interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🌍 Multi-Task AI: Summarization & Image Retrieval")
+    
+    with gr.Row():
+        lang = gr.Dropdown(["English", "Arabic"], label="Input Language")
+        text_input = gr.Textbox(label="Input Text", lines=5)
+    
+    with gr.Row():
+        summary_out = gr.Textbox(label="Summary")
+        trans_out = gr.Textbox(label="English Query Text", visible=False)
+    
+    gallery = gr.Gallery(label="Retrieved Images", columns=3)
+    submit = gr.Button("Process", variant="primary")
+    
+    def toggle_translation(lang):
+        return gr.update(visible=lang == "Arabic")
+    
+    lang.change(toggle_translation, lang, trans_out)
+    submit.click(process, [text_input, lang], [summary_out, trans_out, gallery])
+
+demo.launch()