|
import streamlit as st
|
|
import sparknlp
|
|
|
|
from sparknlp.base import *
|
|
from sparknlp.annotator import *
|
|
from pyspark.ml import Pipeline
|
|
|
|
|
|
st.set_page_config(
|
|
layout="wide",
|
|
initial_sidebar_state="auto"
|
|
)
|
|
|
|
|
|
st.markdown("""
|
|
<style>
|
|
.main-title {
|
|
font-size: 36px;
|
|
color: #4A90E2;
|
|
font-weight: bold;
|
|
text-align: center;
|
|
}
|
|
.section {
|
|
background-color: #f9f9f9;
|
|
padding: 10px;
|
|
border-radius: 10px;
|
|
margin-top: 10px;
|
|
}
|
|
.section p, .section ul {
|
|
color: #666666;
|
|
}
|
|
</style>
|
|
""", unsafe_allow_html=True)
|
|
|
|
@st.cache_resource
|
|
def init_spark():
|
|
return sparknlp.start()
|
|
|
|
@st.cache_resource
|
|
def create_pipeline(model):
|
|
document_assembler = DocumentAssembler() \
|
|
.setInputCol("text") \
|
|
.setOutputCol("documents")
|
|
|
|
sentence_detector = SentenceDetectorDLModel\
|
|
.pretrained()\
|
|
.setInputCols(["documents"])\
|
|
.setOutputCol("questions")
|
|
|
|
t5 = T5Transformer()\
|
|
.pretrained("google_t5_small_ssm_nq")\
|
|
.setInputCols(["questions"])\
|
|
.setOutputCol("answers")\
|
|
|
|
pipeline = Pipeline().setStages([document_assembler, sentence_detector, t5])
|
|
return pipeline
|
|
|
|
def fit_data(pipeline, data):
|
|
df = spark.createDataFrame([[data]]).toDF("text")
|
|
result = pipeline.fit(df).transform(df)
|
|
return result.select('answers.result').collect()
|
|
|
|
|
|
model = st.sidebar.selectbox(
|
|
"Choose the pretrained model",
|
|
['google_t5_small_ssm_nq'],
|
|
help="For more info about the models visit: https://sparknlp.org/models"
|
|
)
|
|
|
|
|
|
title, sub_title = (
|
|
'Automatically Answer Questions (CLOSED BOOK)',
|
|
'Automatically generate answers to questions without context.'
|
|
)
|
|
|
|
st.markdown(f'<div class="main-title">{title}</div>', unsafe_allow_html=True)
|
|
st.write(sub_title)
|
|
|
|
|
|
link = """
|
|
<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/public/QUESTION_ANSWERING_CLOSED_BOOK.ipynb#scrollTo=LEW2ZjZj7T1Q">
|
|
<img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/>
|
|
</a>
|
|
"""
|
|
st.sidebar.markdown('Reference notebook:')
|
|
st.sidebar.markdown(link, unsafe_allow_html=True)
|
|
|
|
|
|
examples = [
|
|
"Who is Clark Kent?",
|
|
"Which is the capital of Bulgaria ?",
|
|
"Which country tops the annual global democracy index compiled by the economist intelligence unit?",
|
|
"In which city is the Eiffel Tower located?",
|
|
"Who is the founder of Microsoft?"
|
|
]
|
|
|
|
selected_text = st.selectbox("Select an example", examples)
|
|
custom_input = st.text_input("Try it with your own Sentence!")
|
|
|
|
text_to_analyze = custom_input if custom_input else selected_text
|
|
|
|
st.write('Question:')
|
|
HTML_WRAPPER = """<div class="scroll entities" style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem; white-space:pre-wrap">{}</div>"""
|
|
st.markdown(HTML_WRAPPER.format(text_to_analyze), unsafe_allow_html=True)
|
|
|
|
|
|
spark = init_spark()
|
|
pipeline = create_pipeline(model)
|
|
output = fit_data(pipeline, text_to_analyze)
|
|
|
|
|
|
st.write("Answer:")
|
|
|
|
output_text = "".join(output[0][0])
|
|
st.markdown(HTML_WRAPPER.format(output_text.title()), unsafe_allow_html=True)
|
|
|
|
|