diff --git a/README.md b/README.md
index 46ee119d..11cb2632 100644
--- a/README.md
+++ b/README.md
@@ -81,6 +81,11 @@ Note: you could turn off your internet connection, and the script inference woul
 
 Type `exit` to finish the script.
 
+
+### Script Arguments
+The script also supports optional command-line arguments to modify its behavior. You can see a full list of these arguments by running the command ```python privateGPT.py --help``` in your terminal
+
+
 # How does it work?
 Selecting the right local models and the power of `LangChain` you can run the entire pipeline locally, without any data leaving your environment, and with reasonable performance.
 
diff --git a/privateGPT.py b/privateGPT.py
index d4545ce8..7adab52d 100755
--- a/privateGPT.py
+++ b/privateGPT.py
@@ -6,6 +6,7 @@ from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.vectorstores import Chroma
 from langchain.llms import GPT4All, LlamaCpp
 import os
+import argparse
 
 load_dotenv()
 
@@ -19,11 +20,14 @@ model_n_ctx = os.environ.get('MODEL_N_CTX')
 from constants import CHROMA_SETTINGS
 
 def main():
+    # Parse the command line arguments
+    args = parse_arguments()
     embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
     db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
     retriever = db.as_retriever()
+    # activate/deactivate the streaming StdOut callback for LLMs
+    callbacks = [] if args.mute_stream else [StreamingStdOutCallbackHandler()]
     # Prepare the LLM
-    callbacks = [StreamingStdOutCallbackHandler()]
     match model_type:
         case "LlamaCpp":
             llm = LlamaCpp(model_path=model_path, n_ctx=model_n_ctx, callbacks=callbacks, verbose=False)
@@ -32,7 +36,7 @@ def main():
         case _default:
             print(f"Model {model_type} not supported!")
             exit;
-    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
+    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents= not args.hide_source)
     # Interactive questions and answers
     while True:
         query = input("\nEnter a query: ")
@@ -41,7 +45,7 @@ def main():
 
         # Get the answer from the chain
         res = qa(query)
-        answer, docs = res['result'], res['source_documents']
+        answer, docs = res['result'], [] if args.hide_source else res['source_documents']
 
         # Print the result
         print("\n\n> Question:")
@@ -54,5 +58,18 @@ def main():
             print("\n> " + document.metadata["source"] + ":")
             print(document.page_content)
 
+def parse_arguments():
+    parser = argparse.ArgumentParser(description='privateGPT: Ask questions to your documents without an internet connection, '
+                                                 'using the power of LLMs.')
+    parser.add_argument("--hide-source", "-S", action='store_true',
+                        help='Use this flag to disable printing of source documents used for answers.')
+
+    parser.add_argument("--mute-stream", "-M",
+                        action='store_true',
+                        help='Use this flag to disable the streaming StdOut callback for LLMs.')
+
+    return parser.parse_args()
+
+
 if __name__ == "__main__":
     main()