Update app.py

app.py

@@ -498,7 +498,7 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
                 print("HF Anfrage.......................")
                 model_kwargs={"temperature": 0.5, "max_length": 512, "num_return_sequences": 1, "top_k": top_k, "top_p": top_p, "repetition_penalty": repetition_penalty}
                 llm = HuggingFaceHub(repo_id=repo_id, model_kwargs=model_kwargs) 
-                #llm = HuggingFaceChain(model=MODEL_NAME_HF, model_kwargs={"temperature": 0.5, "max_length": 128}) 
+                llm = HuggingFaceChain(model=MODEL_NAME_HF, model_kwargs={"temperature": 0.5, "max_length": 128}) 
                 #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="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,)
                 #llm via HuggingChat
@@ -522,9 +522,10 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
             else:
                 #splittet = False
                 print("LLM aufrufen ohne RAG: ...........")
-                #resulti = llm_chain(llm, history_text_und_prompt)
-                #result = resulti.strip()
+                resulti = llm_chain(llm, history_text_und_prompt)
+                result = resulti.strip()
                 #Alternativ mit API_URL - aber das model braucht 93 B Space!!!
+                """
                 data = {
                     "inputs": prompt,
                     "parameters": {"temperature": 0.2, "max_length": 64},
@@ -538,7 +539,7 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
                     print("Fehler:", response.text)
                 result = response.json()
 
-                """
+                
                 chatbot_response = result[0]['generated_text']
                 print("anzahl tokens gesamt antwort:------------------")
                 print (len(chatbot_response.split()))