Update app.py

app.py

@@ -276,9 +276,15 @@ def generate(text, history, rag_option, model_option,  temperature=0.5, max_new_
             db = document_retrieval_chroma()
             #mit RAG:
             neu_text_mit_chunks = rag_chain(text, db)
-            prompt = generate_prompt_with_history_openai(neu_text_mit_chunks, history)
+            #für Chat LLM:
+            #prompt = generate_prompt_with_history_openai(neu_text_mit_chunks, history)
+            #als reiner prompt:
+            prompt = generate_prompt_with_history(neu_text_mit_chunks, history)
         else:
-            prompt = generate_prompt_with_history_openai(text, history)
+            #für Chat LLM:
+            #prompt = generate_prompt_with_history_openai(text, history)
+            #als reiner prompt:
+            prompt = generate_prompt_with_history(text, history)
             
         #Anfrage an Modell (mit RAG: mit chunks aus Vektorstore, ohne: nur promt und history)
         #payload = tokenizer.apply_chat_template([{"role":"user","content":prompt}],tokenize=False)