mes

app.py

@@ -0,0 +1,101 @@
+import os
+import streamlit as st
+import requests
+import torch
+import pinecone
+import numpy as np
+from io import BytesIO
+from PIL import Image
+from transformers import AutoProcessor, CLIPModel
+import logging
+import time
+
+# ✅ Configure Logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+# ✅ Initialize Pinecone
+pc = pinecone.Pinecone(api_key="pcsk_4r5jtC_N5ZNTHpGq2DJUAfZx33GmuXz7Jib6jKVQJuovkdUfB5qrw9njgCRTVrmJVMXbpC")  # Replace with your API key
+index_name = "unsplash-index"
+
+# ✅ Check if the index exists, otherwise create it
+existing_indexes = [index.name for index in pc.list_indexes()]
+if index_name not in existing_indexes:
+    pc.create_index(
+        name=index_name,
+        metric="cosine",
+        dimension=512,
+        spec=pinecone.ServerlessSpec(cloud="aws", region="us-east-1")
+    )
+    while not pc.describe_index(index_name).status.get("ready", False):
+        logger.info("Waiting for index to be ready...")
+        time.sleep(1)
+
+# Connect to Pinecone index
+index = pc.Index(index_name)
+
+# ✅ Load CLIP Model
+@st.cache_resource
+def load_clip():
+    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()
+
+# ✅ Streamlit UI
+st.title("🔍 Image & Text Search with CLIP & Pinecone")
+
+# 📌 **Option 1: Upload Image for Search**
+st.subheader("📤 Upload an Image to Search")
+uploaded_file = st.file_uploader("Upload an image...", type=["jpg", "png", "jpeg"])
+
+if uploaded_file:
+    # Convert file to Image
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    # Process image with CLIP
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        image_features = model.get_image_features(**inputs)
+
+    # Convert to NumPy & flatten
+    embeddings = image_features.detach().cpu().numpy().flatten().tolist()
+
+    # ✅ Search for Similar Images
+    st.subheader("🔎 Find Similar Images")
+    if st.button("Search Similar Images"):
+        search_results = index.query(vector=embeddings, top_k=5, include_metadata=True)
+        
+        if search_results and "matches" in search_results:
+            for match in search_results["matches"]:
+                st.write(f"🔹 **Match Score:** {match['score']}")
+                st.image(match["metadata"]["url"], caption=f"Similar Image - {match['id']}")
+        else:
+            st.warning("No similar images found.")
+
+# 📌 **Option 2: Text Search**
+st.subheader("🔍 Search Images with Text")
+text_query = st.text_input("Enter a description (e.g., 'a cute cat' or 'a red car')")
+
+if text_query and st.button("Search with Text"):
+    # Convert text to CLIP embedding
+    inputs = processor(text=text_query, return_tensors="pt")
+    with torch.no_grad():
+        text_features = model.get_text_features(**inputs)
+
+    # Convert to NumPy & flatten
+    text_embeddings = text_features.detach().cpu().numpy().flatten().tolist()
+
+    # ✅ Search in Pinecone
+    search_results = index.query(vector=text_embeddings, top_k=5, include_metadata=True)
+    
+    # ✅ Display results
+    if search_results and "matches" in search_results:
+        for match in search_results["matches"]:
+            st.write(f"🔹 **Match Score:** {match['score']}")
+            st.image(match["metadata"]["url"], caption=f"Matched Image - {match['id']}")
+    else:
+        st.warning("No matching images found.")
+