Update run.py

run.py

@@ -21,9 +21,11 @@ CACHING_PARAMETERS.do_caching = False  # Set to True in order to disable caching
 
 logging.set_verbosity_debug()
 # Comment out if using huggingface backend
+# The set_verbose() method is used for debugging and logging the outputs and drop_params() method automatically drops the parameters which are not set my litellm (since the response format of OpenAI and huggingface is different we require this to translate Huggingface to OpenAI response format).
 # import litellm
 # litellm.set_verbose=True
 # litellm.drop_params=True
+
 dependencies = [
     {"url": "aiflows/ChatFlowModule", "revision": os.getcwd()},
 ]
@@ -48,6 +50,7 @@ if __name__ == "__main__":
     api_information = [ApiInfo(backend_used="openai",
                               api_key = os.getenv("OPENAI_API_KEY"))]
     #Huggingface backend
+    # Here the API_BASE is the api link to your hosted server. By this way, you can run any flows on your own server.
     # api_information = [ApiInfo(backend_used="huggingface",
     #                           api_key = os.getenv("HUGGINGFACE_API_KEY"), api_base="http://0.0.0.0:5000/v1/completions")]
     # # Azure backend