|
import gradio as gr |
|
from transformers import pipeline |
|
import numpy as np |
|
import pandas as pd |
|
from sentence_transformers import SentenceTransformer, util |
|
import nltk |
|
from nltk import sent_tokenize |
|
nltk.download("punkt") |
|
|
|
|
|
df = pd.read_json("krishnamurti_df.json") |
|
|
|
|
|
model = SentenceTransformer("msmarco-roberta-base-v3") |
|
|
|
krishnamurti_generator = pipeline("text-generation", model="distilgpt2") |
|
|
|
|
|
|
|
def ask_krishnamurti(question): |
|
answer = krishnamurti_generator(question, min_length=100, max_length=120)[0]['generated_text'] |
|
answer = " ".join(sent_tokenize(answer)[:6]) |
|
return answer |
|
|
|
def get_similar_quotes(question): |
|
question_embedding = model.encode(question) |
|
sims = [util.dot_score(question_embedding, quote_embedding) for quote_embedding in df['Embedding']] |
|
ind = np.argpartition(sims, -5)[-5:] |
|
similar_sentences = [df['Quotes'][i] for i in ind] |
|
top5quotes = pd.DataFrame(data = similar_sentences, columns=["Quotes"], index=range(1,6)) |
|
top5quotes['Quotes'] = top5quotes['Quotes'].str[:-1].str[:250] + "..." |
|
return top5quotes |
|
|
|
def main(question): |
|
return ask_krishnamurti(question), get_similar_quotes(question) |
|
|
|
with gr.Blocks() as demo: |
|
gr.Markdown(""" |
|
# Ask Krishanmurti |
|
""" |
|
) |
|
with gr.Row(): |
|
inp = gr.Textbox(placeholder="Place your question here...") |
|
with gr.Column(): |
|
out1 = gr.Textbox( |
|
lines=3, |
|
max_lines=10, |
|
label="Answer" |
|
) |
|
out2 = gr.DataFrame( |
|
headers=["Quotes"], |
|
max_rows=5, |
|
interactive=False, |
|
wrap=True) |
|
btn = gr.Button("Run") |
|
btn.click(fn=main, inputs=inp, outputs=[out1,out2]) |
|
|
|
demo.launch() |
