Update app.py

app.py

@@ -153,8 +153,27 @@ class QuantumDocumentManager:
         """
         return f"{hashlib.sha256(content.encode()).hexdigest()[:16]}-{int(time.time())}"
 
+# ------------------------------
+# Extended Quantum Document Manager for Multi-Modal Documents
+# ------------------------------
+class ExtendedQuantumDocumentManager(QuantumDocumentManager):
+    """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 document collections
-qdm = QuantumDocumentManager()
+qdm = ExtendedQuantumDocumentManager()
 research_docs = qdm.create_collection([
     "Research Report: Results of a New AI Model Improving Image Recognition Accuracy to 98%",
     "Academic Paper Summary: Why Transformers Became the Mainstream Architecture in Natural Language Processing",
@@ -192,7 +211,6 @@ class ResearchRetriever:
     def retrieve(self, query: str, domain: str) -> List[Any]:
         """
         Retrieves documents based on the query and domain.
-        For now, domain differentiation is minimal; however, you can extend this method to use domain-specific collections.
         """
         try:
             return self.research_retriever.invoke(query)
@@ -386,7 +404,6 @@ class MultiModalRetriever:
         self.text_retriever = text_retriever
         self.clip_model = clip_model
         self.clip_processor = clip_processor
-        # Provide required positional arguments: name and description
         self.code_retriever = create_retriever_tool([], "Code Retriever", "Retriever for code snippets")
         
     def retrieve(self, query: str, domain: str) -> Dict[str, List]:
@@ -779,7 +796,7 @@ multi_retriever = MultiModalRetriever(retriever.research_retriever, clip_model,
 # ------------------------------
 # Updated Document Processing for Multi-Modal Documents
 # ------------------------------
-class QuantumDocumentManager(QuantumDocumentManager):
+class ExtendedQuantumDocumentManager(ExtendedQuantumDocumentManager):
     """Extended with multi-modal document handling."""
     def create_image_collection(self, image_paths: List[str]):
         embeddings = []
@@ -795,7 +812,8 @@ class QuantumDocumentManager(QuantumDocumentManager):
             collection_name="neuro_images"
         )
 
-# Initialize image collection
+# Initialize image collection using the extended manager
+qdm = ExtendedQuantumDocumentManager()
 qdm.create_image_collection([
     "data/images/quantum_computing.png",
     "data/images/neural_arch.png"