Update app.py

app.py

@@ -1,38 +1,24 @@
-pip install streamlit transformers pillow
 import streamlit as st
-from transformers import CLIPProcessor, CLIPModel
-from PIL import Image
-import torch
+from transformers import BartForConditionalGeneration, BartTokenizer
 
-# Load the pre-trained CLIP model and processor
-model_name = "dandelin/vilt-b32-finetuned-vqa"  # You can choose a different CLIP variant if needed
-model = CLIPModel.from_pretrained(model_name)
-processor = CLIPProcessor.from_pretrained(model_name)
+# Load the pre-trained BART model and tokenizer
+model_name = "facebook/bart-large-cnn"
+model = BartForConditionalGeneration.from_pretrained(model_name)
+tokenizer = BartTokenizer.from_pretrained(model_name)
 
-st.title("Visual Question Answering App")
+st.title("Text Summarization App")
 
-# Input image upload
-image = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
+# Input text area for user input
+input_text = st.text_area("Enter text to summarize:")
 
-# Input question area for user input
-question = st.text_area("Ask a question about the image:")
+if st.button("Summarize"):
+    if input_text:
+        # Tokenize and summarize the input text
+        inputs = tokenizer(input_text, return_tensors="pt", max_length=1024, truncation=True)
+        summary_ids = model.generate(inputs["input_ids"], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
+        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+        st.subheader("Summary:")
+        st.write(summary)
 
-if image and question:
-    # Display the uploaded image
-    st.image(image, caption="Uploaded Image", use_column_width=True)
-
-    # Process the image and question for VQA
-    inputs = processor(text=question, images=image, return_tensors="pt")
-    
-    # Get the CLIP model's prediction
-    with torch.no_grad():
-        outputs = model(**inputs)
-    
-    # Extract the textual answer
-    answer = outputs["text"]
-    
-    # Display the answer
-    st.write("Answer:", answer)
-
-st.write("Powered by Hugging Face's CLIP model.")
+st.write("Powered by Hugging Face's BART model.")