commit13

app.py

@@ -279,16 +279,35 @@ os.environ["PINECONE_API_KEY"] = "pcsk_TMCYK_LrbmZMTDhkxTjUXcr8iTcQ8LxurwKBFDvv4
 api_key = os.environ.get('PINECONE_API_KEY')
 pc = Pinecone(api_key=api_key)
 
+
+cloud = os.environ.get('PINECONE_CLOUD') or 'aws'
+region = os.environ.get('PINECONE_REGION') or 'us-east-1'
+
+spec = ServerlessSpec(cloud=cloud, region=region)
+
 index_name = "hybrid-image-search"
 spec = ServerlessSpec(cloud="aws", region="us-east-1")
+# choose a name for your index
+index_name = "hybrid-image-search"
+import time
 
+# check if index already exists (it shouldn't if this is first time)
 if index_name not in pc.list_indexes().names():
-    pc.create_index(index_name, dimension=512, metric="dotproduct", spec=spec)
-    import time
+    # if does not exist, create index
+    pc.create_index(
+        index_name,
+        dimension=512,
+        metric='dotproduct',
+        spec=spec
+    )
+    # wait for index to be initialized
     while not pc.describe_index(index_name).status['ready']:
         time.sleep(1)
 
+# connect to index
 index = pc.Index(index_name)
+# view index stats
+index.describe_index_stats()
 
 # ------------------- Dataset Loading -------------------
 fashion = load_dataset("ashraq/fashion-product-images-small", split="train")
@@ -313,24 +332,11 @@ def hybrid_scale(dense, sparse, alpha: float):
     hdense = [v * alpha for v in dense]
     return hdense, hsparse
 
-
-# def search_fashion(query: str, alpha: float):
-#     sparse = bm25.encode_queries(query)
-#     dense = model.encode(query).tolist()
-#     hdense, hsparse = hybrid_scale(dense, sparse, alpha=alpha)
-#     result = index.query(
-#         top_k=8,
-#         vector=hdense,
-#         sparse_vector=hsparse,
-#         include_metadata=True
-#     )
-#     imgs = [images[int(r["id"])] for r in result["matches"]]
-#     return imgs
-
-
 # ------------------- Metadata Filter Extraction -------------------
 from PIL import Image, ImageOps
 import numpy as np
+from PIL import Image, ImageOps
+import numpy as np
 
 def extract_metadata_filters(query: str):
     query_lower = query.lower()
@@ -452,7 +458,7 @@ def search_fashion(query: str, alpha: float):
         print(f"⚠️ No results with gender {gender}, relaxing gender filter")
         filter.pop("gender")
         result = index.query(
-            top_k=12,   
+            top_k=12,
             vector=hdense,
             sparse_vector=hsparse,
             include_metadata=True,
@@ -473,6 +479,14 @@ def search_fashion(query: str, alpha: float):
 
     return imgs_with_captions
 
+
+from transformers import CLIPProcessor, CLIPModel
+
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(device)
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+
+
 from PIL import Image, ImageOps
 import numpy as np
 
@@ -509,7 +523,6 @@ def search_by_image(uploaded_image, alpha=0.5):
 
 
 
-# ------------------- Gradio UI -------------------
 custom_css = """
 .search-btn {
     width: 100%;