Update app.py

app.py

@@ -566,34 +566,68 @@ async def chat_endpoint(chat_query: ChatQuery):
 
 @app.post("/api/resources")
 async def resources_endpoint(profile: MedicalProfile):
-        query_text = profile.conditions + profile.daily_symptoms
-        query_embedding = embed_query_text(query_text)  # Embed the query text
-        embeddings_data = load_embeddings ()
+    try:
+        # Build the query text
+        query_text = profile.conditions + " " + profile.daily_symptoms
+
+        # Generate the query embedding
+        query_embedding = embed_query_text(query_text)
+        if query_embedding is None:
+            raise ValueError("Failed to generate query embedding.")
+
+        # Load embeddings and retrieve initial results
+        embeddings_data = load_embeddings()
         folder_path = 'downloaded_articles/downloaded_articles'
         initial_results = query_embeddings(query_embedding, embeddings_data, n_results=6)
+        if not initial_results:
+            raise ValueError("No relevant documents found.")
+
+        # Extract document IDs
         document_ids = [doc_id for doc_id, _ in initial_results]
+
+        # Load document metadata (URL mappings)
         file_path = 'finalcleaned_excel_file.xlsx'
         df = pd.read_excel(file_path)
         file_name_to_url = {f"article_{index}.html": url for index, url in enumerate(df['Unnamed: 0'])}
-        file_names = document_ids
-    
-            # Retrieve original URLs
-        for file_name in file_names:
+
+        # Map file names to original URLs
+        resources = []
+        for file_name in document_ids:
             original_url = file_name_to_url.get(file_name, None)
             if original_url:
-                title = get_page_title(original_url)
-                if title:
-                    print(f"Title: {title},URL: {original_url}")
-                else:
-                    print(f"Name: {file_name}")
+                title = get_page_title(original_url) or "Unknown Title"
+                resources.append({"file_name": file_name, "title": title, "url": original_url})
             else:
-                print(f"Name: {file_name}")
+                resources.append({"file_name": file_name, "title": "Unknown", "url": None})
+
+        # Retrieve document texts
         document_texts = retrieve_document_texts(document_ids, folder_path)
+        if not document_texts:
+            raise ValueError("Failed to retrieve document texts.")
+
+        # Perform re-ranking
         cross_encoder = models['cross_encoder']
         scores = cross_encoder.predict([(query_text, doc) for doc in document_texts])
-        scored_documents = list(zip(scores, document_ids, document_texts))
-        scored_documents.sort(key=lambda x: x[0], reverse=True)
-        return {"resources": scored_documents, "success": True}
+        scores = [float(score) for score in scores]  # Convert to native Python float
+
+        # Combine scores with resources
+        for i, resource in enumerate(resources):
+            resource["score"] = scores[i] if i < len(scores) else 0.0
+
+        # Sort resources by score
+        resources.sort(key=lambda x: x["score"], reverse=True)
+
+        # Limit response to top 5 resources
+        return {"resources": resources[:5], "success": True}
+
+    except ValueError as ve:
+        # Handle expected errors
+        raise HTTPException(status_code=400, detail=str(ve))
+    except Exception as e:
+        # Handle unexpected errors
+        print(f"Unexpected error: {e}")
+        raise HTTPException(status_code=500, detail="An unexpected error occurred.")
+
  
 
 @app.post("/api/recipes")