Update app.py

app.py

@@ -507,12 +507,13 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
         ###########################
         if (model_option == "OpenAI"):
             #Anfrage an OpenAI ----------------------------
-            print("OpenAI normal.......................")
+            print("OpenAI Anfrage.......................")
             llm = ChatOpenAI(model_name = MODEL_NAME,  openai_api_key = openai_api_key, temperature=temperature)#, top_p = top_p) 
             #Prompt an history anhängen und einen Text daraus machen
             history_text_und_prompt = generate_prompt_with_history_openai(prompt, history)
         else:
             #oder an Hugging Face --------------------------
+            print("HF Anfrage.......................")
             llm = HuggingFaceHub(repo_id=repo_id, 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}) 
@@ -523,6 +524,7 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
     
         #zusätzliche Dokumenten Splits aus DB zum Prompt hinzufügen (aus VektorDB - Chroma oder Mongo DB)
         if (rag_option == "An"):
+            print("RAG aktiviert.......................")
             #muss nur einmal ausgeführt werden... 
             if not splittet:
                 splits = document_loading_splitting()
@@ -530,11 +532,11 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
             db = document_retrieval_chroma(llm, history_text_und_prompt)
             print("LLM aufrufen mit RAG: ...........")
             result = rag_chain(llm, history_text_und_prompt, db)
-        elif (rag_option == "MongoDB"):
+        #elif (rag_option == "MongoDB"):
             #splits = document_loading_splitting()
             #document_storage_mongodb(splits)
-            db = document_retrieval_mongodb(llm, history_text_und_prompt)
-            result = rag_chain(llm, history_text_und_prompt, db)
+            #db = document_retrieval_mongodb(llm, history_text_und_prompt)
+            #result = rag_chain(llm, history_text_und_prompt, db)
         else:
             print("LLM aufrufen ohne RAG: ...........")
             result = llm_chain(llm, history_text_und_prompt)