Code Update

backend/src/__init__.py

@@ -5,9 +5,8 @@ from .routes.rag import rag_bp
 
 def create_app():
     app = Flask(__name__)
-    CORS(app) # Enable CORS for all routes
+    CORS(app)
     
-    # Register Blueprints
     app.register_blueprint(main_bp)
     app.register_blueprint(rag_bp, url_prefix='/api/rag')
     

backend/src/gemini/client.py

@@ -2,10 +2,6 @@ from google import genai
 import os
 
 def generate_content(prompt, model_name="gemini-2.0-flash-exp"):
-    """
-    Generates content using the Google GenAI SDK.
-    Defaults to gemini-2.0-flash-exp as per request (or similar).
-    """
     api_key = os.environ.get("GOOGLE_API_KEY")
     if not api_key:
         return "Error: GOOGLE_API_KEY not found."

backend/src/rag/embeddings.py

@@ -2,9 +2,6 @@ from google import genai
 import os
 
 def get_embedding(text, model="gemini-embedding-001"):
-    """
-    Generates an embedding for the given text using the Gemini API.
-    """
     api_key = os.environ.get("GOOGLE_API_KEY")
     if not api_key:
         raise ValueError("GOOGLE_API_KEY environment variable not set")
@@ -17,9 +14,6 @@ def get_embedding(text, model="gemini-embedding-001"):
     return result.embeddings[0].values
 
 def get_embeddings_batch(texts, model="gemini-embedding-001"):
-    """
-    Generates embeddings for a list of texts.
-    """
     api_key = os.environ.get("GOOGLE_API_KEY")
     if not api_key:
         raise ValueError("GOOGLE_API_KEY environment variable not set")
@@ -29,5 +23,4 @@ def get_embeddings_batch(texts, model="gemini-embedding-001"):
         model=model,
         contents=texts
     )
-    # The SDK returns a list of embedding objects
     return [emb.values for emb in result.embeddings]

backend/src/rag/ingest.py

@@ -4,18 +4,10 @@ import io
 import os
 
 def load_csv(file_path):
-    """
-    Loads a CSV file and returns a list of strings (one per row).
-    This is a simplistic implementation - in production you might want specific columns.
-    """
     df = pd.read_csv(file_path)
-    # Convert each row to a string representation
     return df.apply(lambda x: ' | '.join(x.astype(str)), axis=1).tolist()
 
 def load_pdf(file_path):
-    """
-    Loads a PDF file and returns a list of strings (one per page).
-    """
     reader = PdfReader(file_path)
     text_chunks = []
     for page in reader.pages:
@@ -25,9 +17,6 @@ def load_pdf(file_path):
     return text_chunks
 
 def process_file(file_path):
-    """
-    Determines file type and returns text chunks.
-    """
     ext = os.path.splitext(file_path)[1].lower()
     if ext == '.csv':
         return load_csv(file_path)

backend/src/rag/store.py

@@ -9,14 +9,10 @@ def get_mongo_client():
     return MongoClient(uri)
 
 def ingest_documents(text_chunks, collection_name="rag_documents"):
-    """
-    Generates embeddings for text chunks and stores them in MongoDB.
-    """
     client = get_mongo_client()
-    db = client.get_database("vectors_db") # Default DB name
+    db = client.get_database("vectors_db")
     collection = db[collection_name]
     
-    # Generate embeddings in batches (handling API limits might be needed for large sets)
     embeddings = get_embeddings_batch(text_chunks)
     
     documents = []
@@ -32,10 +28,6 @@ def ingest_documents(text_chunks, collection_name="rag_documents"):
     return 0
 
 def vector_search(query_text, collection_name="rag_documents", num_results=5):
-    """
-    Performs a vector search in MongoDB.
-    """
-    # 1. Get embedding for the query
     from .embeddings import get_embedding
     query_embedding = get_embedding(query_text)
     
@@ -43,7 +35,6 @@ def vector_search(query_text, collection_name="rag_documents", num_results=5):
     db = client.get_database("vectors_db")
     collection = db[collection_name]
     
-    # Note: You must have a vector search index defined in MongoDB Atlas for this to work.
     pipeline = [
         {
             "$vectorSearch": {