Update app.py

app.py

@@ -2,16 +2,16 @@ import streamlit as st
 from PIL import Image
 import torch
 import easyocr
-from transformers import CLIPProcessor, CLIPModel
+from transformers import CLIPModel, CLIPImageProcessor
 
-# ---- Load CLIP Model ---- #
+# ---- Load CLIP Model (Vision Only) ---- #
 @st.cache_resource
 def load_clip_model():
     model = CLIPModel.from_pretrained(
         "fxmarty/clip-vision-model-tiny", 
-        ignore_mismatched_sizes=True  # Fix model size mismatch
+        ignore_mismatched_sizes=True  # Fix size mismatch
     )
-    processor = CLIPProcessor.from_pretrained("fxmarty/clip-vision-model-tiny")
+    processor = CLIPImageProcessor.from_pretrained("fxmarty/clip-vision-model-tiny")
     return model, processor
 
 model, processor = load_clip_model()
@@ -46,13 +46,10 @@ if uploaded_file is not None:
     else:
         st.warning("No readable text found in the image.")
 
-    # ---- Ask a Question About the Image ---- #
-    user_question = st.text_input("🤖 Ask a question about the image:")
+    # ---- Process Image with CLIP Vision Model ---- #
+    with st.spinner("🔍 Analyzing image with CLIP Model..."):
+        inputs = processor(images=image, return_tensors="pt")
+        outputs = model.get_image_features(**inputs)
 
-    if user_question:
-        with st.spinner("🔍 Analyzing image and generating response..."):
-            inputs = processor(text=[user_question], images=image, return_tensors="pt")
-            outputs = model.get_image_features(**inputs)
-        
-        st.write("### 🏆 AI Response:")
-        st.write("CLIP Model has processed the image! (Further improvements coming soon)")
+    st.write("### 🏆 AI Response:")
+    st.write("CLIP Model has processed the image! (More features coming soon)")