Create app.py

app.py

@@ -0,0 +1,26 @@
+import streamlit as st
+from PIL import Image
+import easyocr
+from transformers import CLIPProcessor, CLIPModel
+
+# Load OCR & CLIP
+reader = easyocr.Reader(['en'])
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+st.title("Multimodal AI Assistant")
+uploaded_file = st.file_uploader("Upload an Image", type=["png", "jpg", "jpeg"])
+
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+    
+    # Extract text from image
+    extracted_text = reader.readtext(uploaded_file, detail=0)
+    st.write("Extracted Text:", extracted_text)
+
+    # CLIP Analysis
+    text_descriptions = ["A car", "A dog", "A person", "A building"]
+    inputs = processor(text=text_descriptions, images=image, return_tensors="pt")
+    outputs = model(**inputs)
+    st.write("CLIP Model Scores:", outputs.logits_per_image.tolist())