Fix CLIrrr2 model issue in appetete333.py

app.py

@@ -1,140 +1,169 @@
+# app.py
 import os
 import uuid
 import io
 import base64
 from PIL import Image
 import gradio as gr
+import numpy as np
+
+# CLIP via Sentence-Transformers
 from sentence_transformers import SentenceTransformer
-import google.generativeai as genai
+
+# Gemini (Google) client
+from google import genai
+
+# Qdrant client & helpers
 from qdrant_client import QdrantClient
 from qdrant_client.http.models import VectorParams, Distance, PointStruct
 
-# --- Configuration ---
-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")
-
-# --- Model Loading and Client Initialization ---
-print("Loading CLIP model...")
+# -------------------------
+# CONFIG (reads env vars)
+# -------------------------
+GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY", "").strip()
+QDRANT_URL = os.environ.get("QDRANT_URL", "").strip()
+QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY", "").strip()
+
+# -------------------------
+# 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)
 
-# Configure the Gemini client
-if GEMINI_API_KEY:
-    genai.configure(api_key=GEMINI_API_KEY)
+genai_client = genai.Client(api_key=GEMINI_API_KEY) if GEMINI_API_KEY else None
 
 if not QDRANT_URL:
-    raise RuntimeError("Set QDRANT_URL env var")
-qclient = QdrantClient(url=QDRANT_URL, api_key=QDRANT_API_KEY)
+    raise RuntimeError("Please set QDRANT_URL environment variable")
 
-# --- Qdrant Collection Setup ---
+qclient = QdrantClient(url=QDRANT_URL, api_key=QDRANT_API_KEY)
 COLLECTION = "lost_found_items"
 VECTOR_SIZE = 512
-if not qclient.collection_exists(COLLECTION):
-    print(f"Creating collection: {COLLECTION}")
-    qclient.create_collection(
-        collection_name=COLLECTION,
-        vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
-    )
-
-# --- Core Functions ---
+
+# Create collection if missing
+try:
+    if not qclient.collection_exists(COLLECTION):
+        qclient.create_collection(
+            collection_name=COLLECTION,
+            vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
+        )
+except Exception as e:
+    print("Error initializing Qdrant collection:", e)
+
+# -------------------------
+# Helpers
+# -------------------------
 def embed_text(text: str):
-    """Generates an embedding for the given text."""
     return clip_model.encode(text, convert_to_numpy=True)
 
 def embed_image_pil(pil_img: Image.Image):
-    """Generates an embedding for the given PIL image."""
+    pil_img = pil_img.convert("RGB")
     return clip_model.encode(pil_img, convert_to_numpy=True)
 
-def gen_tags_from_image_file(img_bytes: io.BytesIO) -> str:
-    """Generates descriptive tags for an image using the Gemini API."""
-    if not GEMINI_API_KEY:
-        print("Warning: GEMINI_API_KEY not set. Skipping tag generation.")
+def gen_tags_from_image_file(image_bytes: io.BytesIO) -> str:
+    if genai_client is None:
         return ""
     try:
-        img = Image.open(img_bytes)
-        model = genai.GenerativeModel('gemini-pro-vision')
-        prompt = ("Give 4 short tags (comma-separated) describing this item in the image. "
-                  "Respond only with tags.")
-        resp = model.generate_content([prompt, img])
-        return resp.text.strip()
-    except Exception as e:
-        print(f"Error calling Gemini API: {e}")
+        file_obj = genai_client.files.upload(file=image_bytes)
+        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."
+        )
+        response = genai_client.models.generate_content(
+            model="gemini-2.5-flash",
+            contents=[prompt_text, file_obj],
+        )
+        return response.text.strip()
+    except Exception:
         return ""
 
-def add_item(mode: str, uploaded_image: Image.Image, text_description: str):
-    """Adds a new lost or found item to the database."""
-    if not uploaded_image and not text_description:
-        return "Error: Please provide either an image or a description."
-
+# -------------------------
+# App logic: add item
+# -------------------------
+def add_item(mode: str, uploaded_image, text_description: str):
     item_id = str(uuid.uuid4())
     payload = {"mode": mode, "text": text_description}
 
-    if uploaded_image:
+    if uploaded_image is not None:
         img_bytes = io.BytesIO()
-        uploaded_image.save(img_bytes, format="PNG")
+        uploaded_image.convert("RGB").save(img_bytes, format="PNG")
         img_bytes.seek(0)
 
         vec = embed_image_pil(uploaded_image).tolist()
         payload["has_image"] = True
+
         payload["tags"] = gen_tags_from_image_file(img_bytes)
-        
-        img_bytes.seek(0)
-        payload["image_b64"] = base64.b64encode(img_bytes.read()).decode("utf-8")
+        payload["image_b64"] = base64.b64encode(img_bytes.getvalue()).decode("utf-8")
     else:
         vec = embed_text(text_description).tolist()
         payload["has_image"] = False
-        payload["tags"] = ""
-    
-    point = PointStruct(id=item_id, vector=vec, payload=payload)
-    qclient.upsert(collection_name=COLLECTION, points=[point], wait=True)
+        if genai_client:
+            try:
+                resp = genai_client.models.generate_content(
+                    model="gemini-2.5-flash",
+                    contents=f"Give 4 short, comma-separated tags for this item described as: {text_description}. Reply only with tags."
+                )
+                payload["tags"] = resp.text.strip()
+            except Exception:
+                payload["tags"] = ""
+        else:
+            payload["tags"] = ""
+
+    try:
+        point = PointStruct(id=item_id, vector=vec, payload=payload)
+        qclient.upsert(collection_name=COLLECTION, points=[point], wait=True)
+    except Exception as e:
+        return f"Error saving to Qdrant: {e}"
 
     return f"Saved item id: {item_id}\nTags: {payload.get('tags','')}"
 
-def search_items(query_image: Image.Image, query_text: str, limit: int = 5):
-    """Searches for similar items in the database."""
-    if query_image:
+# -------------------------
+# App logic: search
+# -------------------------
+def search_items(query_image, query_text, limit: int = 5):
+    if query_image is not None:
         qvec = embed_image_pil(query_image).tolist()
-    elif query_text:
+    elif query_text and len(query_text.strip()) > 0:
         qvec = embed_text(query_text).tolist()
     else:
-        return "Provide a query image or text to search."
+        return "Please provide a query image or some query text."
+
+    try:
+        hits = qclient.search(collection_name=COLLECTION, query_vector=qvec, limit=limit)
+    except Exception as e:
+        return f"Error querying Qdrant: {e}"
 
-    hits = qclient.search(collection_name=COLLECTION, query_vector=qvec, limit=limit)
     if not hits:
-        return "No results found."
+        return "No results."
 
     results = []
     for h in hits:
         payload = h.payload or {}
-        score = getattr(h, "score", 0)
+        score = getattr(h, "score", None)
         results.append(
-            f"ID: {h.id}\nScore: {float(score):.4f}\nMode: {payload.get('mode','')}\n"
-            f"Tags: {payload.get('tags','')}\nText: {payload.get('text','')}\n"
+            f"id:{h.id} score:{float(score) if score else None} mode:{payload.get('mode','')} tags:{payload.get('tags','')} text:{payload.get('text','')}"
         )
-
     return "\n\n".join(results)
 
-# --- Gradio UI ---
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("## Lost & Found Helper")
-    gr.Markdown("Add items that were lost or found, and search for them using a photo or description.")
-    
+# -------------------------
+# 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.")
     with gr.Row():
-        with gr.Column(scale=1):
-            gr.Markdown("### Add an Item")
-            mode = gr.Radio(["lost", "found"], value="lost", label="I have...")
-            upload_img = gr.Image(type="pil", label="Item Photo (optional)")
-            text_desc = gr.Textbox(lines=2, placeholder="e.g., 'red backpack with a keychain'", label="Description")
-            add_btn = gr.Button("Add Item", variant="primary")
-            add_out = gr.Textbox(interactive=False, label="Result", lines=3)
-        
-        with gr.Column(scale=2):
-            gr.Markdown("### Search for an Item")
-            query_img = gr.Image(type="pil", label="Search by Image (optional)")
-            query_text = gr.Textbox(lines=2, placeholder="e.g., 'blue water bottle'", label="Search by Text (optional)")
-            search_btn = gr.Button("Search", variant="primary")
-            search_out = gr.Textbox(interactive=False, label="Search Results", lines=10)
+        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)")
+            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")
+            search_out = gr.Textbox(label="Search results", interactive=False)
 
     add_btn.click(add_item, inputs=[mode, upload_img, text_desc], outputs=[add_out])
     search_btn.click(search_items, inputs=[query_img, query_text], outputs=[search_out])