app.py

#import json
import os
import pprint
#import shutil
#import requests

import gradio as gr

from transformers.utils import logging
from langchain.embeddings import HuggingFaceInstructEmbeddings, GooglePalmEmbeddings
import pinecone
from langchain.vectorstores import Pinecone

logging.set_verbosity_debug()

instructor_embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl", model_kwargs={"device": "cpu"})

HF_TOKEN = os.environ.get("HF_TOKEN", None)
PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY", None)
PINECONE_ENV = os.environ.get("PINECONE_ENV", None)
GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY", None)

pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_ENV)

from langchain.llms import GooglePalm
from langchain.chains import RetrievalQAWithSourcesChain
llm=GooglePalm(google_api_key=GOOGLE_API_KEY, temperature=0.1, max_output_tokens=2048)
vectorStore = Pinecone.from_existing_index('tennis', instructor_embeddings)
retriever = vectorStore.as_retriever(search_kwargs={"k": 3})
qa_chain_instrucEmbed = RetrievalQAWithSourcesChain.from_chain_type(llm=llm,
                                  chain_type="stuff",
                                  retriever=retriever,
                                  return_source_documents=True,
                                  verbose=True
                                  )

theme = gr.themes.Monochrome(
    primary_hue="indigo",
    secondary_hue="blue",
    neutral_hue="slate",
    radius_size=gr.themes.sizes.radius_sm,
    font=[
        gr.themes.GoogleFont("Open Sans"),
        "ui-sans-serif",
        "system-ui",
        "sans-serif",
    ],
)

def generate(question):
    ret = qa_chain_instrucEmbed(question)
    pprint.pprint(ret)
    answer = ret['answer']
    sources = ret['sources']
    embed_video_html = '<div>'
    if sources is not None and len(sources) > 0:
        sources = [s.strip() for s in sources.split(',')]
        for source in sources:
            embed_video_html += f'''
                <iframe width="560" height="315" src="https://www.youtube.com/embed/{source}"
                title="YouTube video player" frameborder="0" allow="accelerometer; autoplay;
                clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
                '''
    return answer, embed_video_html+'</div>'

examples = [
    "Tell me step by step how to find out my dominant eye when I play tennis.",
    "What do we look for in a great tennis player? Write out the essential attributes.",
    "Who has the best tennis serve? Explain in details.",
    "Compare Novak and Nadal gamestyle in details. Who is better?",
    "Who is the tennis GOAT?"
]

def process_example(args):
    for x in generate(args):
        pass
    return x


css = ".generating {visibility: hidden}"

monospace_css = """
#q-input textarea {
    font-family: monospace, 'Consolas', Courier, monospace;
}
"""

css += monospace_css + ".gradio-container {color: black}"

description = """
<div style="text-align: center;">
    <h1>Ask Tennis Coach Patrick Mouratoglou</h1>
</div>
<div style="text-align: left;">
    <p>This is a demo to answer some popular questions from tennis fans to Coach Patrick. The information is being extracted from his official <a href="https://www.youtube.com/@patrickmouratoglou_official" style='color: #e6b800;'>Youtube channel</a>. It's using the following technologies:</p>
    <ul>
        <li>Google PALM</li>
        <li>Gradio</li>
        <li>hkunlp/instructor-xl</li>
        <li>HuggingFace</li>
        <li>Langchain</li>
        <li>Pinecone</li>
    </ul>
</div>
"""
disclaimer = """⚠️<b>This is an unofficial website.</b>\
 <br>**Intended Use**: this app for demonstration purposes; not to serve as replacement for Coach Patrick official media channels or personal expertise."""

with gr.Blocks(theme=theme, analytics_enabled=False, css=css) as demo:
    with gr.Column():
        gr.Markdown(description)
        gr.Markdown(disclaimer)
        with gr.Row():
            with gr.Column():
                question = gr.Textbox(
                    placeholder="Enter your question here",
                    lines=5,
                    label="Question"
                )
                submit = gr.Button("Ask", variant="primary")
                output = gr.Textbox(elem_id="q-output", lines=10, label="Answer")
                video = gr.HTML('')
                gr.Examples(
                    examples=examples,
                    inputs=[question],
                    cache_examples=False,
                    fn=process_example,
                    outputs=[output, video],
                )

    submit.click(
        generate,
        inputs=[question],
        outputs=[output, video],
    )
demo.queue(concurrency_count=16).launch(debug=True)