File size: 882 Bytes
f40f6ca e81731d 7d25ed6 e81731d 7d25ed6 e81731d 7d25ed6 e81731d 7d25ed6 e81731d 7d25ed6 e81731d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 |
import gradio as gr
from rag import respond_rag_ollama # Your custom RAG function using Ollama
history = []
def respond(message, chat_history, temperature=0.5, max_tokens=512 ):
response = respond_rag_ollama(message, temperature=temperature,num_predict=max_tokens) # send only message & temperature
chat_history.append((message, response))
return "", chat_history
with gr.Blocks() as demo:
gr.Markdown("# Game of Thrones Q&A bot")
chatbot = gr.Chatbot()
msg = gr.Textbox(label="Tell me something about 7 kingdoms")
temp = gr.Slider(0.0, 1.0, value=0.5, label="Temperature")
max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
clear = gr.Button("Clear")
msg.submit(respond, [msg, chatbot, temp, max_tokens], [msg, chatbot])
clear.click(lambda: ([], ""), None, [chatbot, msg])
demo.launch()
|