Update app.py

app.py

@@ -154,7 +154,7 @@ def rag_chain(llm, prompt, db):
 
 ###################################################
 #Funktion von Gradio aus, die den dort eingegebenen Prompt annimmt und weiterverarbeitet
-def invoke(openai_api_key, rag_option, prompt):
+def invoke (prompt, chatbot, openai_api_key, rag_option, temperature=0.9, max_new_tokens=512, top_p=0.6, repetition_penalty=1.3,);
     global splittet
     
     if (openai_api_key == "" or openai_api_key == "sk-"):
@@ -241,6 +241,9 @@ def vote(data: gr.LikeData):
     else: print("You downvoted this response: " + data.value)
 
 additional_inputs = [
+    gr.Textbox(label = "OpenAI API Key", value = "sk-", lines = 1), 
+    #gr.Radio(["Off", "Chroma", "MongoDB"], label="Retrieval Augmented Generation", value = "Off"),
+    gr.Radio(["Off", "Chroma"], label="Retrieval Augmented Generation", value = "Off"),
     gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Höhere Werte erzeugen diversere Antworten"),
     gr.Slider(label="Max new tokens", value=256, minimum=0, maximum=4096, step=64, interactive=True, info="Maximale Anzahl neuer Tokens"),
     gr.Slider(label="Top-p (nucleus sampling)", value=0.6, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Höhere Werte verwenden auch Tokens mit niedrigerer Wahrscheinlichkeit."),
@@ -252,17 +255,19 @@ chatbot_stream = gr.Chatbot(avatar_images=(
     "https://drive.google.com/uc?id=1tfELAQW_VbPCy6QTRbexRlwAEYo8rSSv"
     ), bubble_full_width = False)
 
-chat_interface_stream = gr.ChatInterface(
-                invoke,
-                title=title, 
-                description=description, 
-                chatbot=chatbot_stream,
-                css=css, 
-                examples=examples, 
-                inputs = [gr.Textbox(label = "OpenAI API Key", value = "sk-", lines = 1), 
-                              #gr.Radio(["Off", "Chroma", "MongoDB"], label="Retrieval Augmented Generation", value = "Off"),
-                              gr.Radio(["Off", "Chroma"], label="Retrieval Augmented Generation", value = "Off"),
-                 ) 
+chat_interface_stream = gr.Interface(fn=invoke, 
+                           inputs = [gr.Textbox(label = "OpenAI API Key", value = "sk-", lines = 1), 
+                                      #gr.Radio(["Off", "Chroma", "MongoDB"], label="Retrieval Augmented Generation", value = "Off"),
+                                      gr.Radio(["Off", "Chroma"], label="Retrieval Augmented Generation", value = "Off"),
+                                      gr.Textbox(label = "Prompt", value = "What is GPT-4?", lines = 1),
+                                      gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Höhere Werte erzeugen diversere Antworten"),
+                                      gr.Slider(label="Max new tokens", value=256, minimum=0, maximum=4096, step=64, interactive=True, info="Maximale Anzahl neuer Tokens"),
+                                      gr.Slider(label="Top-p (nucleus sampling)", value=0.6, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Höhere Werte verwenden auch Tokens mit niedrigerer Wahrscheinlichkeit."),
+                                      gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Strafe für wiederholte Tokens")
+                                    ],
+                           outputs = [chatbot_stream],
+                           title = "Generative AI - LLM & RAG",
+                           description = description)
 
 with gr.Blocks() as demo:
     with gr.Tab("General LLM"):