Update app.py

app.py

@@ -160,15 +160,25 @@ class ExtendedQuantumDocumentManager(QuantumDocumentManager):
     """Extended with multi-modal document handling."""
     def create_image_collection(self, image_paths: List[str]):
         embeddings = []
+        valid_images = []
         for img_path in image_paths:
-            image = Image.open(img_path)
-            inputs = clip_processor(images=image, return_tensors="pt")
-            with torch.no_grad():
-                emb = clip_model.get_image_features(**inputs)
-            embeddings.append(emb.numpy())
+            try:
+                image = Image.open(img_path)
+                inputs = clip_processor(images=image, return_tensors="pt")
+                with torch.no_grad():
+                    emb = clip_model.get_image_features(**inputs)
+                embeddings.append(emb.numpy())
+                valid_images.append(img_path)
+            except FileNotFoundError as fe:
+                logger.warning(f"Image file not found: {img_path}. Skipping this file.")
+            except Exception as e:
+                logger.exception(f"Error processing image {img_path}: {str(e)}")
+        if not embeddings:
+            logger.error("No valid images found for image collection.")
+            return None
         return Chroma.from_embeddings(
             embeddings=embeddings,
-            documents=image_paths,
+            documents=valid_images,
             collection_name="neuro_images"
         )
 
@@ -793,32 +803,6 @@ clip_model = CLIPModel.from_pretrained(ResearchConfig.CLIP_SETTINGS["model"])
 clip_processor = CLIPProcessor.from_pretrained(ResearchConfig.CLIP_SETTINGS["model"])
 multi_retriever = MultiModalRetriever(retriever.research_retriever, clip_model, clip_processor)
 
-# ------------------------------
-# Updated Document Processing for Multi-Modal Documents
-# ------------------------------
-class ExtendedQuantumDocumentManager(ExtendedQuantumDocumentManager):
-    """Extended with multi-modal document handling."""
-    def create_image_collection(self, image_paths: List[str]):
-        embeddings = []
-        for img_path in image_paths:
-            image = Image.open(img_path)
-            inputs = clip_processor(images=image, return_tensors="pt")
-            with torch.no_grad():
-                emb = clip_model.get_image_features(**inputs)
-            embeddings.append(emb.numpy())
-        return Chroma.from_embeddings(
-            embeddings=embeddings,
-            documents=image_paths,
-            collection_name="neuro_images"
-        )
-
-# Initialize image collection using the extended manager
-qdm = ExtendedQuantumDocumentManager()
-qdm.create_image_collection([
-    "data/images/quantum_computing.png",
-    "data/images/neural_arch.png"
-])
-
 # ------------------------------
 # Execute the Application
 # ------------------------------