removed some comments

app/main.py

@@ -42,9 +42,9 @@ class PromptRequest(BaseModel):
 
 class ContentRequest(BaseModel):
     grade: int
-    subject: str  # "math" or "science"
+    subject: str
     topic: str
-    style: str = "normal"  # "normal", "simple", or "creative"
+    style: str = "normal"  
 
 TOPIC_KEYWORDS = {
     # Grade 3 Science
@@ -208,13 +208,13 @@ def retrieve_documents(query, index, embedding_model, documents, top_k=5):
 
     # Simple direct keyword matching since we only have one keyword per topic
     for filename, keywords in TOPIC_KEYWORDS.items():
-        if keywords[0] == query_lower:  # Exact match with the single keyword
+        if keywords[0] == query_lower:  
             target_topic = filename
             break
         
     # Get embeddings and search
     query_embedding = embedding_model.encode([query])
-    distances, indices = index.search(query_embedding, top_k * 3)  # Get more candidates
+    distances, indices = index.search(query_embedding, top_k * 3)  
 
     # Filter and organize retrieved documents
     topic_docs = []
@@ -393,7 +393,7 @@ async def load_or_create_index():
                 files_found = True
                 chunks = split_text_into_chunks(text, filename)
                 documents.extend(chunks)
-            await asyncio.sleep(0)  # Allow other async operations to proceed
+            await asyncio.sleep(0)  
         
         if not files_found:
             raise Exception(f"No valid text or PDF files found in the specified paths")
@@ -497,7 +497,7 @@ async def generate_content(request: ContentRequest):
         }
             
         response = generate_response_with_rag(
-            request.topic,  # Use topic as the prompt
+            request.topic,  
             app.state.faiss_index,
             app.state.embedding_model,
             app.state.documents,