Update app.py

app.py

@@ -82,7 +82,7 @@ MODEL_NAME  = "gpt-3.5-turbo-16k"
 repo_id = "meta-llama/Llama-2-13b-chat-hf"   
 #repo_id = "HuggingFaceH4/zephyr-7b-alpha"
 #repo_id = "meta-llama/Llama-2-70b-chat-hf"    
-#repo_id = "tiiuae/falcon-180B-chat"  
+#repo_id = "tiiuae/falcon-180B-chat"   
 #repo_id = "Vicuna-33b"
 
 
@@ -258,9 +258,10 @@ def invoke (prompt, history, openai_api_key, rag_option, temperature=0.9, max_ne
         #LLM auswählen (OpenAI oder HF)
         ###########################
         #Anfrage an OpenAI
-        llm = ChatOpenAI(model_name = MODEL_NAME,  openai_api_key = openai_api_key, temperature = 0)
+        #llm = ChatOpenAI(model_name = MODEL_NAME,  openai_api_key = openai_api_key, temperature = 0)
         #oder an Hugging Face
-        #llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature": 0.5, "max_length": 64})
+        #llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature": 0.5, "max_length": 64}) 
+        llm = HuggingFaceHub(API_URL = "https://wdgsjd6zf201mufn.us-east-1.aws.endpoints.huggingface.cloud", model_kwargs={"temperature": 0.5, "max_length": 64}) 
         
         #zusätzliche Dokumenten Splits aus DB zum Prompt hinzufügen (aus VektorDB - Chroma oder Mongo DB)
         if (rag_option == "Chroma"):