Updated run.py to support Huggingface backend

run.py

@@ -20,7 +20,10 @@ CACHING_PARAMETERS.do_caching = False  # Set to True in order to disable caching
 # clear_cache() # Uncomment this line to clear the cache
 
 logging.set_verbosity_debug()
-
+# Comment out if using huggingface backend
+# import litellm
+# litellm.set_verbose=True
+# litellm.drop_params=True
 dependencies = [
     {"url": "aiflows/ChatFlowModule", "revision": os.getcwd()},
 ]
@@ -44,6 +47,9 @@ if __name__ == "__main__":
     # OpenAI backend
     api_information = [ApiInfo(backend_used="openai",
                               api_key = os.getenv("OPENAI_API_KEY"))]
+    #Huggingface backend
+    # 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
     # api_information = ApiInfo(backend_used = "azure",
     #                           api_base = os.getenv("AZURE_API_BASE"),
@@ -100,6 +106,6 @@ if __name__ == "__main__":
     
     
     #9. ~~~~~Optional: Unserve Flow~~~~~~
-    # serving.delete_served_flow(cl, "ReverseNumberAtomicFlow_served")
+    # serve_utils.delete_served_flow(cl, "ReverseNumberAtomicFlow_served")