new

app.py

@@ -0,0 +1,116 @@
+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
+
+# ✅ Set Page Config (Must be the first Streamlit command)
+st.set_page_config(page_title="Image Search App", layout="wide", initial_sidebar_state="expanded")
+
+# ✅ Initialize Pinecone
+pc = Pinecone(api_key="pcsk_6r4DPn_4P9LckhZak3PhebvSebnEBKQZuzYFeJL2X93LtLxZVBxyJ93inBAktefa8usvJC")  # Replace with your Pinecone API key
+index_name = "unsplash-index"
+unsplash_index = pc.Index(index_name)
+
+# ✅ Load CLIP Model & Processor
+@st.cache_resource
+def load_clip_model():
+    model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+    processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")
+    return model, processor
+
+model, processor = load_clip_model()
+
+# ✅ Sidebar for Inputs
+st.sidebar.title("🔍 Search Options")
+top_k = st.sidebar.slider("🔢 Number of Similar Images", 1, 20, 10)
+
+# 📌 **Option 1: Text-to-Image Search**
+st.sidebar.subheader("📝 Search by Text")
+search_query = st.sidebar.text_input("Enter a description (e.g., 'a cute cat', 'a red car')")
+text_search_btn = st.sidebar.button("🔍 Search by Text")
+
+# 📌 **Option 2: Image-to-Image Search**
+st.sidebar.subheader("🖼️ Search by Image")
+uploaded_file = st.sidebar.file_uploader("Upload an image...", type=["jpg", "png", "jpeg"])
+image_search_btn = st.sidebar.button("🔍 Search by Image")
+
+# ✅ Function to Generate Embedding from Text
+def get_text_embedding(text):
+    inputs = processor(text=[text], return_tensors="pt", padding=True, truncation=True)
+    with torch.no_grad():
+        text_features = model.get_text_features(**inputs)
+    return text_features.detach().cpu().numpy().flatten().tolist()
+
+# ✅ 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)
+    return image_features.detach().cpu().numpy().flatten().tolist()
+
+# ✅ Function to Query Pinecone and Fetch Similar Images
+def search_similar_images(embedding, top_k=10):
+    results = unsplash_index.query(
+        vector=embedding,
+        top_k=top_k,
+        include_metadata=True,
+        namespace="image-search-dataset"
+    )
+    return results.get("matches", [])
+
+# ✅ Streamlit UI
+st.title("🔍 Image & Text Search with CLIP & Pinecone")
+
+# 📌 **Process Text-to-Image Search**
+if search_query and text_search_btn:
+    with st.spinner("Generating embedding..."):
+        embedding = get_text_embedding(search_query)
+    with st.spinner("Searching for similar images..."):
+        matches = search_similar_images(embedding, top_k=top_k)
+
+    st.subheader("🔎 Top Similar Images")
+    if matches:
+        cols = st.columns(3)  # Arrange images in 3 columns
+        for i, match in enumerate(matches):
+            cosine_distance = 1 - match.get("score", 0)  # Convert similarity score to cosine distance
+            photo_id = match.get("id", "Unknown ID")
+            url = match.get("metadata", {}).get("url", None)
+
+            with cols[i % 3]:  # Alternate images in columns
+                st.write(f"📷 **Photo ID**: {photo_id} | 📏 **Cosine Distance**: {cosine_distance:.4f}")
+                if url:
+                    st.image(url, caption=f"Photo ID: {photo_id}", use_container_width=True)
+                else:
+                    st.warning(f"⚠️ Image URL not found for Photo ID: {photo_id}")
+    else:
+        st.warning("⚠️ No similar images found!")
+
+# 📌 **Process Image-to-Image Search**
+if uploaded_file and image_search_btn:
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Uploaded Image", use_container_width=True)
+
+    with st.spinner("Generating embedding..."):
+        embedding = get_image_embedding(image)
+    with st.spinner("Searching for similar images..."):
+        matches = search_similar_images(embedding, top_k=top_k)
+
+    st.subheader("🔎 Top Similar Images")
+    if matches:
+        cols = st.columns(3)  # Arrange in 3 columns
+        for i, match in enumerate(matches):
+            cosine_distance = 1 - match.get("score", 0)  # Convert similarity score to cosine distance
+            photo_id = match.get("id", "Unknown ID")
+            url = match.get("metadata", {}).get("url", None)
+
+            with cols[i % 3]:  # Alternate images in columns
+                st.write(f"📷 **Photo ID**: {photo_id} | 📏 **Cosine Distance**: {cosine_distance:.4f}")
+                if url:
+                    st.image(url, caption=f"Photo ID: {photo_id}", use_container_width=True)
+                else:
+                    st.warning(f"⚠️ Image URL not found for Photo ID: {photo_id}")
+

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+requests
+torch
+transformers
+pinecone
+numpy
+Pillow