Upload 2 files

app.py

@@ -0,0 +1,123 @@
+"""
+CLIP Image Embedding API - Hosted on Streamlit Cloud
+Returns 512-dimensional embeddings for image similarity search
+"""
+
+import streamlit as st
+import torch
+from PIL import Image
+from transformers import CLIPProcessor, CLIPModel
+import requests
+from io import BytesIO
+import base64
+import json
+
+# Load model once (cached)
+@st.cache_resource
+def load_model():
+    model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+    processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+    return model, processor
+
+model, processor = load_model()
+
+def get_image_embedding(image):
+    """Get CLIP embedding for an image"""
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        image_features = model.get_image_features(**inputs)
+    # Normalize
+    embedding = image_features / image_features.norm(dim=-1, keepdim=True)
+    return embedding[0].tolist()
+
+def load_image_from_source(source):
+    """Load image from URL or base64"""
+    if source.startswith('http'):
+        response = requests.get(source, timeout=30)
+        return Image.open(BytesIO(response.content)).convert('RGB')
+    elif source.startswith('data:image'):
+        # Base64 data URI
+        base64_data = source.split(',')[1]
+        image_data = base64.b64decode(base64_data)
+        return Image.open(BytesIO(image_data)).convert('RGB')
+    else:
+        raise ValueError("Invalid image source")
+
+# Streamlit UI
+st.title("🖼️ CLIP Image Embedding API")
+st.write("Get 512-dimensional embeddings for image similarity search")
+
+# API Mode - check query params
+query_params = st.query_params
+api_mode = query_params.get("api", "false") == "true"
+image_url = query_params.get("image", None)
+
+if api_mode and image_url:
+    # API mode - return JSON
+    try:
+        image = load_image_from_source(image_url)
+        embedding = get_image_embedding(image)
+        result = {
+            "success": True,
+            "embedding": embedding,
+            "dimensions": len(embedding),
+            "model": "openai/clip-vit-base-patch32"
+        }
+        st.json(result)
+    except Exception as e:
+        st.json({"success": False, "error": str(e)})
+else:
+    # Interactive UI mode
+    st.markdown("---")
+    
+    # Input options
+    tab1, tab2 = st.tabs(["🔗 Image URL", "📤 Upload Image"])
+    
+    with tab1:
+        url_input = st.text_input("Enter image URL:", placeholder="https://example.com/image.jpg")
+        if st.button("Get Embedding from URL", key="url_btn"):
+            if url_input:
+                with st.spinner("Processing..."):
+                    try:
+                        image = load_image_from_source(url_input)
+                        st.image(image, caption="Input Image", width=300)
+                        embedding = get_image_embedding(image)
+                        st.success(f"✅ Got {len(embedding)}-dimensional embedding!")
+                        st.json({
+                            "embedding": embedding[:10],  # Show first 10
+                            "dimensions": len(embedding),
+                            "note": "Showing first 10 values only"
+                        })
+                        # Full embedding in expander
+                        with st.expander("📋 Full Embedding (copy this)"):
+                            st.code(json.dumps(embedding), language="json")
+                    except Exception as e:
+                        st.error(f"Error: {e}")
+    
+    with tab2:
+        uploaded_file = st.file_uploader("Upload an image", type=['jpg', 'jpeg', 'png', 'webp'])
+        if uploaded_file:
+            image = Image.open(uploaded_file).convert('RGB')
+            st.image(image, caption="Uploaded Image", width=300)
+            if st.button("Get Embedding", key="upload_btn"):
+                with st.spinner("Processing..."):
+                    embedding = get_image_embedding(image)
+                    st.success(f"✅ Got {len(embedding)}-dimensional embedding!")
+                    with st.expander("📋 Full Embedding (copy this)"):
+                        st.code(json.dumps(embedding), language="json")
+    
+    # API Usage instructions
+    st.markdown("---")
+    st.subheader("🔌 API Usage")
+    st.code("""
+# Call from your backend:
+GET https://your-app.streamlit.app/?api=true&image=https://example.com/image.jpg
+
+# Response:
+{
+  "success": true,
+  "embedding": [0.0123, -0.0456, ...],
+  "dimensions": 512,
+  "model": "openai/clip-vit-base-patch32"
+}
+    """, language="python")

requirements.txt

@@ -0,0 +1,6 @@
+streamlit>=1.28.0
+gradio>=4.0.0
+torch>=2.0.0
+transformers>=4.35.0
+Pillow>=10.0.0
+requests>=2.31.0