from omegaconf import OmegaConf from query import VectaraQuery import os import gradio as gr def isTrue(x) -> bool: if isinstance(x, bool): return x return x.strip().lower() == 'true' corpus_ids = str(os.environ['corpus_ids']).split(',') cfg = OmegaConf.create({ 'customer_id': str(os.environ['customer_id']), 'corpus_ids': corpus_ids, 'api_key': str(os.environ['api_key']), 'title': os.environ['title'], 'description': os.environ['description'], 'source_data_desc': os.environ['source_data_desc'], 'streaming': isTrue(os.environ.get('streaming', False)), 'prompt_name': os.environ.get('prompt_name', None) }) vq = VectaraQuery(cfg.api_key, cfg.customer_id, cfg.corpus_ids, cfg.prompt_name) def respond(message, history): if cfg.streaming: # Call stream response and stream output stream = vq.submit_query_streaming(message) outputs = "" for output in stream: outputs += output yield outputs else: # Call non-stream response and return message output response = vq.submit_query(message) yield response cfg.title = f'''

{cfg.title}

''' cfg.description = f'''

{cfg.description}


This demo uses Retrieval Augmented Generation to ask questions about {cfg.source_data_desc}
''' image_html = ''' ''' # with gr.Blocks() as demo: # gr.HTML() # gr.ChatInterface(respond, title = cfg.title, description = cfg.description, # chatbot = gr.Chatbot(value = [[None, "How may I help you?"]], scale=3)) with gr.Blocks() as demo: with gr.Row(): gr.HTML(image_html) gr.HTML(cfg.title) gr.HTML(cfg.description) gr.ChatInterface(respond, chatbot=gr.Chatbot(value=[[None, "How may I help you?"]], scale=3)) if __name__ == "__main__": demo.launch()