Fix CLIP model issue in app.py

app.py

@@ -19,29 +19,22 @@ from qdrant_client.http.models import VectorParams, Distance, PointStruct
 # -------------------------
 #  CONFIG (reads env vars)
 # -------------------------
-GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")  # set in Hugging Face Space secrets
-QDRANT_URL = os.environ.get("QDRANT_URL")          # set in Hugging Face Space secrets
-QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY")  # set in Hugging Face Space secrets
-
-# Local fallbacks (for local testing) - set them before running locally if needed:
-# os.environ["GEMINI_API_KEY"]="..." ; os.environ["QDRANT_URL"]="..." ; os.environ["QDRANT_API_KEY"]="..."
+GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")
+QDRANT_URL = os.environ.get("QDRANT_URL")
+QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY")
 
 # -------------------------
 #  Initialize clients/models
 # -------------------------
 print("Loading CLIP model (this may take 20-60s the first time)...")
 MODEL_ID = "sentence-transformers/clip-ViT-B-32-multilingual-v1"
-clip_model = SentenceTransformer(MODEL_ID)  # model maps text & images to same vector space
+clip_model = SentenceTransformer(MODEL_ID)
 
-# Gemini client (for tags/captions)
-if GEMINI_API_KEY:
-    genai_client = genai.Client(api_key=GEMINI_API_KEY)
-else:
-    genai_client = None
+# Gemini client
+genai_client = genai.Client(api_key=GEMINI_API_KEY) if GEMINI_API_KEY else None
 
 # Qdrant client
 if not QDRANT_URL:
-    # If you prefer local Qdrant for dev: client = QdrantClient(":memory:") or local url
     raise RuntimeError("Please set QDRANT_URL environment variable")
 qclient = QdrantClient(url=QDRANT_URL, api_key=QDRANT_API_KEY)
 
@@ -59,26 +52,20 @@ if not qclient.collection_exists(COLLECTION):
 #  Helpers
 # -------------------------
 def embed_text(text: str):
-    vec = clip_model.encode(text, convert_to_numpy=True)
+    vec = clip_model.encode([text], convert_to_numpy=True)[0]  # wrap in list
     return vec
 
 def embed_image_pil(pil_img: Image.Image):
-    # sentence-transformers supports directly encoding a PIL image for CLIP models
-    vec = clip_model.encode(pil_img, convert_to_numpy=True)
+    vec = clip_model.encode([pil_img], convert_to_numpy=True)[0]  # wrap in list
     return vec
 
 def gen_tags_from_image_file(local_path: str) -> str:
-    """Upload image file to Gemini and ask for 4 short tags.
-       Returns the raw text response (expected comma-separated tags)."""
-    if genai_client is None:
+    if not genai_client:
         return ""
-    # Upload file (Gemini Developer API supports client.files.upload)
     file_obj = genai_client.files.upload(file=local_path)
-    # Ask Gemini: produce short tags only
     prompt_text = (
         "Give 4 short tags (comma-separated) describing this item in the image. "
-        "Tags should be short single words or two-word phrases (e.g. 'black backpack', 'water bottle'). "
-        "Respond only with tags, no extra explanation."
+        "Tags should be short single words or two-word phrases. Respond only with tags."
     )
     response = genai_client.models.generate_content(
         model="gemini-2.5-flash",
@@ -90,36 +77,25 @@ def gen_tags_from_image_file(local_path: str) -> str:
 #  App logic: add item
 # -------------------------
 def add_item(mode: str, uploaded_image, text_description: str):
-    """
-    mode: 'lost' or 'found'
-    uploaded_image: PIL image or None
-    text_description: str
-    """
     item_id = str(uuid.uuid4())
     payload = {"mode": mode, "text": text_description}
 
     if uploaded_image is not None:
-        # Save image to temp file (so we can upload to Gemini)
         tmp_path = f"/tmp/{item_id}.png"
         uploaded_image.save(tmp_path)
-        # embed image
         vec = embed_image_pil(uploaded_image).tolist()
         payload["has_image"] = True
-        # optional: get tags from Gemini (if available)
         try:
             tags = gen_tags_from_image_file(tmp_path)
-        except Exception as e:
+        except Exception:
             tags = ""
         payload["tags"] = tags
-        # store image bytes (tiny) so we can show result in the UI (base64)
         with open(tmp_path, "rb") as f:
             b64 = f.read()
-        payload["image_b64"] = True  # flag (we will return/show image via Gradio from file bytes)
+        payload["image_b64"] = True
     else:
-        # only text provided
         vec = embed_text(text_description).tolist()
         payload["has_image"] = False
-        # ask Gemini to suggest tags from text
         if genai_client:
             try:
                 resp = genai_client.models.generate_content(
@@ -132,30 +108,24 @@ def add_item(mode: str, uploaded_image, text_description: str):
         else:
             payload["tags"] = ""
 
-    # Upsert into Qdrant
     point = PointStruct(id=item_id, vector=vec, payload=payload)
     qclient.upsert(collection_name=COLLECTION, points=[point], wait=True)
 
     return f"Saved item id: {item_id}\nTags: {payload.get('tags','')}"
 
-
 # -------------------------
 #  App logic: search
 # -------------------------
 def search_items(query_image, query_text, limit: int = 5):
-    # produce query embedding
     if query_image is not None:
         qvec = embed_image_pil(query_image).tolist()
-        q_type = "image"
-    else:
-        if (not query_text) or (len(query_text.strip()) == 0):
-            return "Please provide a query image or some query text."
+    elif query_text and query_text.strip():
         qvec = embed_text(query_text).tolist()
-        q_type = "text"
+    else:
+        return "Please provide a query image or some query text."
 
     hits = qclient.search(collection_name=COLLECTION, query_vector=qvec, limit=limit)
 
-    # Format output (list)
     results = []
     for h in hits:
         payload = h.payload or {}
@@ -163,36 +133,35 @@ def search_items(query_image, query_text, limit: int = 5):
         results.append(
             {
                 "id": h.id,
-                "score": float(score) if score is not None else None,
+                "score": float(score) if score else None,
                 "mode": payload.get("mode", ""),
                 "text": payload.get("text", ""),
                 "tags": payload.get("tags", ""),
                 "has_image": payload.get("has_image", False),
             }
         )
-    # Return a simple list for Gradio to show
+
     if not results:
         return "No results."
-    # Convert to text for display
-    out_lines = []
-    for r in results:
-        out_lines.append(f"id:{r['id']} score:{r['score']:.4f} mode:{r['mode']} tags:{r['tags']} text:{r['text']}")
+    out_lines = [
+        f"id:{r['id']} score:{r['score']:.4f} mode:{r['mode']} tags:{r['tags']} text:{r['text']}"
+        for r in results
+    ]
     return "\n\n".join(out_lines)
 
 # -------------------------
 #  Gradio UI
 # -------------------------
 with gr.Blocks(title="Lost & Found — Simple Helper") as demo:
-    gr.Markdown("## Lost & Found Helper (image/text search) — upload items, then search by image or text.")
+    gr.Markdown("## Lost & Found Helper (image/text search)")
     with gr.Row():
         with gr.Column():
             mode = gr.Radio(choices=["lost", "found"], value="lost", label="Add as")
             upload_img = gr.Image(type="pil", label="Item photo (optional)")
-            text_desc = gr.Textbox(lines=2, placeholder="Short description (e.g. 'black backpack with blue zipper')", label="Description (optional)")
+            text_desc = gr.Textbox(lines=2, placeholder="Short description", label="Description (optional)")
             add_btn = gr.Button("Add item")
             add_out = gr.Textbox(label="Add result", interactive=False)
         with gr.Column():
-            gr.Markdown("### Search")
             query_img = gr.Image(type="pil", label="Search by image (optional)")
             query_text = gr.Textbox(lines=2, label="Search by text (optional)")
             search_btn = gr.Button("Search")