add img code

app.py

@@ -1,20 +1,18 @@
 import streamlit as st
 from pinecone import Pinecone
-
 import os
 from PIL import Image
 import requests
 from transformers import AutoProcessor, CLIPModel
 import numpy as np
+import torch
 
-
-
-# Initialize Pinecone
-pc = Pinecone(api_key="pcsk_6r4DPn_4P9LckhZak3PhebvSebnEBKQZuzYFeJL2X93LtLxZVBxyJ93inBAktefa8usvJC")
+# ✅ Initialize Pinecone
+pc = Pinecone(api_key="your-pinecone-api-key")  # Replace with your API key
 index_name = "unsplash-index"
 unsplash_index = pc.Index(index_name)
 
-# Load CLIP model and processor
+# ✅ Load CLIP Model & Processor
 @st.cache_resource
 def load_clip_model():
     model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
@@ -23,14 +21,23 @@ def load_clip_model():
 
 model, processor = load_clip_model()
 
-# Function to generate embedding from text
+# ✅ Function to Generate Embedding from Text
 def get_text_embedding(text):
     inputs = processor(text=[text], return_tensors="pt", padding=True, truncation=True)
-    text_features = model.get_text_features(**inputs)
+    with torch.no_grad():
+        text_features = model.get_text_features(**inputs)
     embedding = text_features.detach().cpu().numpy().flatten().tolist()
     return embedding
 
-# Function to query Pinecone and fetch similar images
+# ✅ Function to Generate Embedding from Image
+def get_image_embedding(image):
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        image_features = model.get_image_features(**inputs)
+    embedding = image_features.detach().cpu().numpy().flatten().tolist()
+    return embedding
+
+# ✅ Function to Query Pinecone and Fetch Similar Images
 def search_similar_images(embedding, top_k=10):
     results = unsplash_index.query(
         vector=embedding,
@@ -38,44 +45,64 @@ def search_similar_images(embedding, top_k=10):
         include_metadata=True,
         namespace="image-search-dataset"
     )
-    return results["matches"]
+    return results.get("matches", [])
 
-# Streamlit UI
-st.title("🔍Text-to-Image Lookup")
-st.write("Enter a description to find similar images!")
+# ✅ Streamlit UI
+st.title("🔍 Image & Text Search with CLIP & Pinecone")
+st.write("Search for images using text or upload an image to find similar ones!")
 
-# Text input widget
-search_query = st.text_input("Enter your search query (e.g.Flower)")
+# 📌 **Option 1: Text-to-Image Search**
+st.subheader("📝 Search by Text")
+search_query = st.text_input("Enter a description (e.g., 'a cute cat', 'a red car')")
 
-# Search button
-if st.button("Search"):
+if st.button("🔍 Search by Text"):
     if search_query:
-        # Generate embedding from text
         with st.spinner("Generating embedding..."):
             embedding = get_text_embedding(search_query)
-
-        # Search for similar images
         with st.spinner("Searching for similar images..."):
-            matches = search_similar_images(embedding, top_k=10)
+            matches = search_similar_images(embedding, top_k=5)
 
-        # Display results
-        st.subheader("Top Similar Images")
+        st.subheader("🔎 Top Similar Images")
         for match in matches:
-            score = match["score"]
-            photo_id = match["id"]
-            url = match["metadata"]["url"]
+            score = match.get("score", 0)
+            photo_id = match.get("id", "Unknown ID")
+            url = match.get("metadata", {}).get("url", None)
+
             st.write(f"**Photo ID**: {photo_id} | **Similarity Score**: {score:.4f}")
-            try:
-                # Fetch and display the image from the URL
-                response = requests.get(url, stream=True)
-                response.raw.decode_content = True  # Handle content-encoding
-                img = Image.open(response.raw)
-                st.image(img, caption=f"Photo ID: {photo_id}", use_container_width=True)
-            except Exception as e:
-                st.error(f"Could not load image from {url}: {e}")
+            if url:
+                st.image(url, caption=f"Photo ID: {photo_id}", use_column_width=True)
+            else:
+                st.warning(f"Image URL not found for Photo ID: {photo_id}")
     else:
-        st.warning("Please enter a search query!")
+        st.warning("⚠️ Please enter a search query!")
+
+# 📌 **Option 2: Image-to-Image Search**
+st.subheader("🖼️ Search by Image")
+uploaded_file = st.file_uploader("Upload an image...", type=["jpg", "png", "jpeg"])
+
+if uploaded_file:
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    if st.button("🔍 Search by Image"):
+        with st.spinner("Generating embedding..."):
+            embedding = get_image_embedding(image)
+
+        with st.spinner("Searching for similar images..."):
+            matches = search_similar_images(embedding, top_k=5)
+
+        st.subheader("🔎 Top Similar Images")
+        for match in matches:
+            score = match.get("score", 0)
+            photo_id = match.get("id", "Unknown ID")
+            url = match.get("metadata", {}).get("url", None)
+
+            st.write(f"**Photo ID**: {photo_id} | **Similarity Score**: {score:.4f}")
+            if url:
+                st.image(url, caption=f"Photo ID: {photo_id}", use_column_width=True)
+            else:
+                st.warning(f"Image URL not found for Photo ID: {photo_id}")
 
 # Instructions
 st.write("---")
-st.write("Note: This app searches an Unsplash dataset indexed in Pinecone using CLIP embeddings based on your text description.")
+st.write("Note: This app searches an Unsplash dataset indexed in Pinecone using CLIP embeddings for both text and images.")