Update app.py

app.py

@@ -286,10 +286,19 @@ def invoke (prompt, history, rag_option, openai_api_key,  temperature=0.9, max_n
         #LLM auswählen (OpenAI oder HF)
         ###########################
         #Anfrage an OpenAI
-        llm = ChatOpenAI(model_name = MODEL_NAME,  openai_api_key = openai_api_key, temperature=temperature)#, top_p = top_p)
+        #llm = ChatOpenAI(model_name = MODEL_NAME,  openai_api_key = openai_api_key, temperature=temperature)#, top_p = top_p)
         #oder an Hugging Face
         #llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature": 0.5, "max_length": 64}) 
         #llm = HuggingFaceHub(url_??? = "https://wdgsjd6zf201mufn.us-east-1.aws.endpoints.huggingface.cloud", model_kwargs={"temperature": 0.5, "max_length": 64}) 
+        llm = HuggingFaceTextGenInference(
+                inference_server_url="https://wdgsjd6zf201mufn.us-east-1.aws.endpoints.huggingface.cloud", #"http://localhost:8010/",
+                max_new_tokens=max_new_tokens,
+                top_k=10,
+                top_p=top_p,
+                typical_p=0.95,
+                temperature=temperature,
+                repetition_penalty=repetition_penalty,
+            )
         
         #zusätzliche Dokumenten Splits aus DB zum Prompt hinzufügen (aus VektorDB - Chroma oder Mongo DB)
         if (rag_option == "An"):