app.py

from time import perf_counter

import gradio as gr
from jinja2 import Environment, FileSystemLoader

from backend.query_llm import generate
from backend.semantic_search import qd_retriever
from pathlib import Path

proj_dir = Path(__file__).parent


# Set up the template environment with the templates directory
env = Environment(loader=FileSystemLoader(proj_dir/'templates'))

# Load the templates directly from the environment
template = env.get_template('template.j2')
template_html = env.get_template('template_html.j2')


def add_text(history, text):
    history = [] if history is None else history
    history = history + [(text, None)]
    return history, gr.Textbox(value="", interactive=False)


def bot(history, system_prompt=""):
    top_k = 5
    query = history[-1][0]

    # Retrieve documents relevant to query
    document_start = perf_counter()
    documents = qd_retriever.retrieve(query, top_k=top_k)
    document_time = document_start - perf_counter()

    # Create Prompt
    prompt = template.render(documents=documents, query=query)
    prompt_html = template_html.render(documents=documents, query=query)

    history[-1][1] = ""
    for character in generate(prompt, history[:-1]):
        history[-1][1] = character
        yield history, prompt_html


with gr.Blocks() as demo:
    with gr.Tab("Application"):
        chatbot = gr.Chatbot(
                [],
                elem_id="chatbot",
                avatar_images=('examples/lama.jpeg', 'examples/lama2.jpeg'),
                bubble_full_width=False,
                show_copy_button=True,
                show_share_button=True,
                )

        with gr.Row():
            txt = gr.Textbox(
                    scale=3,
                    show_label=False,
                    placeholder="Enter text and press enter",
                    container=False,
                    )
            txt_btn = gr.Button(value="Submit text", scale=1)

        prompt_html = gr.HTML()
        # Turn off interactivity while generating if you hit enter
        txt_msg = txt_btn.click(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(
                bot, chatbot, [chatbot, prompt_html])

        # Turn it back on
        txt_msg.then(lambda: gr.Textbox(interactive=True), None, [txt], queue=False)

        # Turn off interactivity while generating if you hit enter
        txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(
                bot, chatbot, [chatbot, prompt_html])

        # Turn it back on
        txt_msg.then(lambda: gr.Textbox(interactive=True), None, [txt], queue=False)

    gr.Examples(['What is the largest city on earth?', 'Who has the record for the fastest mile?'], txt)

demo.queue()
demo.launch(debug=True)