pages/Workflow & Model Overview.py

import streamlit as st

# Page configuration
st.set_page_config(
    layout="wide", 
    initial_sidebar_state="auto"
)

# Custom CSS for better styling
st.markdown("""
    <style>
        .main-title {
            font-size: 36px;
            color: #4A90E2;
            font-weight: bold;
            text-align: center;
        }
        .sub-title {
            font-size: 24px;
            color: #4A90E2;
            margin-top: 20px;
        }
        .section {
            background-color: #f9f9f9;
            padding: 15px;
            border-radius: 10px;
            margin-top: 20px;
        }
        .section h2 {
            font-size: 22px;
            color: #4A90E2;
        }
        .section p, .section ul {
            color: #666666;
        }
        .link {
            color: #4A90E2;
            text-decoration: none;
        }
    </style>
""", unsafe_allow_html=True)

# Title
st.markdown('<div class="main-title">SQL Query Generation</div>', unsafe_allow_html=True)

# Introduction Section
st.markdown("""
<div class="section">
    <p>SQL Query Generation is a process that involves translating natural language queries into SQL statements. This allows non-technical users to interact with databases by simply asking questions in plain English, making it easier to retrieve specific data without needing to write complex SQL code.</p>
    <p>In this page, we explore how to implement SQL Query Generation using the T5 model in a Spark NLP pipeline. The T5 model is trained to perform various text-to-text transformations, including translating English queries into SQL commands.</p>
</div>
""", unsafe_allow_html=True)

# T5 Transformer Overview
st.markdown('<div class="sub-title">T5: The Transformer Architecture</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <p>The T5 (Text-To-Text Transfer Transformer) model is designed to handle a wide variety of NLP tasks by treating them as text-to-text problems. In the context of SQL Query Generation, T5 takes a natural language input and translates it into an appropriate SQL query.</p>
    <p>This model is built on the transformer architecture, which uses self-attention mechanisms to process input text, making it highly effective for understanding and generating text. The T5 model is particularly well-suited for tasks where the goal is to generate text that corresponds to a specific function, like generating SQL queries from plain English questions.</p>
</div>
""", unsafe_allow_html=True)

# Performance Section
st.markdown('<div class="sub-title">Performance and Benchmarks</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <p>T5 models, including the one used for SQL Query Generation, have been tested on various benchmarks that measure their ability to accurately translate natural language into SQL queries. These models have consistently demonstrated strong performance, accurately generating SQL queries that retrieve the correct data from databases.</p>
    <p>Performance metrics for T5 in this domain show that it can handle a wide range of query types, from simple lookups to more complex queries involving multiple conditions and joins.</p>
</div>
""", unsafe_allow_html=True)

# Implementation Section
st.markdown('<div class="sub-title">Implementing SQL Query Generation</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <p>Below is an example of how to implement SQL Query Generation using a T5 model in a Spark NLP pipeline. This example demonstrates how a natural language query can be transformed into an SQL query that can be executed on a database.</p>
</div>
""", unsafe_allow_html=True)

st.code('''
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
from pyspark.sql.functions import col, expr

documentAssembler = DocumentAssembler() \\
    .setInputCol("text") \\
    .setOutputCol("documents")

t5 = T5Transformer.pretrained("t5_small_wikiSQL") \\
    .setTask("translate English to SQL:") \\
    .setInputCols(["documents"]) \\
    .setMaxOutputLength(200) \\
    .setOutputCol("sql")

pipeline = Pipeline().setStages([documentAssembler, t5])

data = spark.createDataFrame([["How many customers have ordered more than 2 items?"]]).toDF("text")
result = pipeline.fit(data).transform(data)
result.select("sql.result").show(truncate=False)
''', language='python')

# Example Output
st.text("""
+----------------------------------------------------+
|result                                              |
+----------------------------------------------------+
|[SELECT COUNT Customers FROM table WHERE Orders > 2]|
+----------------------------------------------------+
""")

# Model Info Section
st.markdown('<div class="sub-title">Choosing the Right SQL Model</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <p>The T5 model used in the example, "t5_small_wikiSQL," is optimized for SQL query generation from English language input. Depending on the complexity of the queries you need to generate, you may choose a larger or more specialized version of the T5 model.</p>
    <p>For more complex queries or larger datasets, consider using a model with more parameters, such as T5-base or T5-large, which offer improved performance and accuracy. You can explore different models and find the one that best suits your needs on the <a class="link" href="https://sparknlp.org/models?annotator=T5Transformer" target="_blank">Spark NLP Models Hub</a>.</p>
</div>
""", unsafe_allow_html=True)

# Footer
# References Section
st.markdown('<div class="sub-title">References</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <ul>
        <li><a class="link" href="https://ai.googleblog.com/2019/10/exploring-transfer-learning-with-t5.html" target="_blank">Google AI Blog on T5</a>: Learn more about the T5 model</li>
        <li><a class="link" href="https://sparknlp.org/models?annotator=T5Transformer" target="_blank">Spark NLP Model Hub</a>: Explore T5 models</li>
        <li><a class="link" href="https://github.com/google-research/text-to-text-transfer-transformer" target="_blank">GitHub</a>: Access the T5 repository and contribute</li>
        <li><a class="link" href="https://arxiv.org/abs/1910.10683" target="_blank">T5 Paper</a>: Detailed insights from the developers</li>
    </ul>
</div>
""", unsafe_allow_html=True)

st.markdown('<div class="sub-title">Community & Support</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <ul>
        <li><a class="link" href="https://sparknlp.org/" target="_blank">Official Website</a>: Documentation and examples</li>
        <li><a class="link" href="https://join.slack.com/t/spark-nlp/shared_invite/zt-198dipu77-L3UWNe_AJ8xqDk0ivmih5Q" target="_blank">Slack</a>: Live discussion with the community and team</li>
        <li><a class="link" href="https://github.com/JohnSnowLabs/spark-nlp" target="_blank">GitHub</a>: Bug reports, feature requests, and contributions</li>
        <li><a class="link" href="https://medium.com/spark-nlp" target="_blank">Medium</a>: Spark NLP articles</li>
        <li><a class="link" href="https://www.youtube.com/channel/UCmFOjlpYEhxf_wJUDuz6xxQ/videos" target="_blank">YouTube</a>: Video tutorials</li>
    </ul>
</div>
""", unsafe_allow_html=True)

st.markdown('<div class="sub-title">Quick Links</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <ul>
        <li><a class="link" href="https://sparknlp.org/docs/en/quickstart" target="_blank">Getting Started</a></li>
        <li><a class="link" href="https://nlp.johnsnowlabs.com/models" target="_blank">Pretrained Models</a></li>
        <li><a class="link" href="https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples/python/annotation/text/english" target="_blank">Example Notebooks</a></li>
        <li><a class="link" href="https://sparknlp.org/docs/en/install" target="_blank">Installation Guide</a></li>
    </ul>
</div>
""", unsafe_allow_html=True)