Upload 5 files

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[theme]
+base="light"
+primaryColor="#29B4E8"

Demo.py

@@ -0,0 +1,116 @@
+import streamlit as st
+import sparknlp
+
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+# Page configuration
+st.set_page_config(
+    layout="wide", 
+    initial_sidebar_state="auto"
+)
+
+# CSS for styling
+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()
+
+# Sidebar content
+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"
+)
+
+# Set up the page layout
+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)
+
+# Reference notebook link in sidebar
+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)
+
+# Load examples
+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)
+
+# Initialize Spark and create pipeline
+spark = init_spark()
+pipeline = create_pipeline(model)
+output = fit_data(pipeline, text_to_analyze)
+
+# Display matched sentence
+st.write("Answer:")
+
+output_text = "".join(output[0][0])
+st.markdown(HTML_WRAPPER.format(output_text.title()), unsafe_allow_html=True)
+

Dockerfile

@@ -0,0 +1,72 @@
+# Download base image ubuntu 18.04
+FROM ubuntu:18.04
+
+# Set environment variables
+ENV NB_USER jovyan
+ENV NB_UID 1000
+ENV HOME /home/${NB_USER}
+ENV JAVA_HOME /usr/lib/jvm/java-8-openjdk-amd64/
+
+# Install required packages
+RUN apt-get update && apt-get install -y \
+    tar \
+    wget \
+    bash \
+    rsync \
+    gcc \
+    libfreetype6-dev \
+    libhdf5-serial-dev \
+    libpng-dev \
+    libzmq3-dev \
+    python3 \
+    python3-dev \
+    python3-pip \
+    unzip \
+    pkg-config \
+    software-properties-common \
+    graphviz \
+    openjdk-8-jdk \
+    ant \
+    ca-certificates-java \
+    && apt-get clean \
+    && update-ca-certificates -f
+
+# Install Python 3.8 and pip
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y python3.8 python3-pip \
+    && apt-get clean
+
+# Set up JAVA_HOME
+RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> /etc/profile \
+    && echo "export PATH=\$JAVA_HOME/bin:\$PATH" >> /etc/profile
+# Create a new user named "jovyan" with user ID 1000
+RUN useradd -m -u ${NB_UID} ${NB_USER}
+
+# Switch to the "jovyan" user
+USER ${NB_USER}
+
+# Set home and path variables for the user
+ENV HOME=/home/${NB_USER} \
+    PATH=/home/${NB_USER}/.local/bin:$PATH
+
+# Set up PySpark to use Python 3.8 for both driver and workers
+ENV PYSPARK_PYTHON=/usr/bin/python3.8
+ENV PYSPARK_DRIVER_PYTHON=/usr/bin/python3.8
+
+# Set the working directory to the user's home directory
+WORKDIR ${HOME}
+
+# Upgrade pip and install Python dependencies
+RUN python3.8 -m pip install --upgrade pip
+COPY requirements.txt /tmp/requirements.txt
+RUN python3.8 -m pip install -r /tmp/requirements.txt
+
+# Copy the application code into the container at /home/jovyan
+COPY --chown=${NB_USER}:${NB_USER} . ${HOME}
+
+# Expose port for Streamlit
+EXPOSE 7860
+
+# Define the entry point for the container
+ENTRYPOINT ["streamlit", "run", "Demo.py", "--server.port=7860", "--server.address=0.0.0.0"]

pages/Workflow & Model Overview.py

@@ -0,0 +1,171 @@
+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">Automatically Answer Questions (CLOSED BOOK)</div>', unsafe_allow_html=True)
+
+# Introduction Section
+st.markdown("""
+<div class="section">
+    <p>Closed-book question answering is a challenging task where a model is expected to generate accurate answers to questions without access to external information or documents during inference. This approach relies solely on the pre-trained knowledge embedded within the model, making it ideal for scenarios where retrieval-based methods are not feasible.</p>
+    <p>In this page, we will explore how to implement a pipeline that can automatically answer questions in a closed-book setting using state-of-the-art NLP techniques. We utilize a T5 Transformer model fine-tuned for closed-book question answering, providing accurate and contextually relevant answers to a variety of trivia questions.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# T5 Transformer Overview
+st.markdown('<div class="sub-title">Understanding the T5 Transformer for Closed-Book QA</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>The T5 (Text-To-Text Transfer Transformer) model by Google is a versatile transformer-based model designed to handle a wide range of NLP tasks in a unified text-to-text format. For closed-book question answering, T5 is fine-tuned to generate answers directly from its internal knowledge without relying on external sources.</p>
+    <p>The model processes input questions and, based on its training, generates a text response that is both relevant and accurate. This makes it particularly effective in applications where access to external data sources is limited or impractical.</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>The T5 model has been extensively benchmarked on various question-answering datasets, including natural questions and trivia challenges. In these evaluations, the closed-book variant of T5 has shown strong performance, often producing answers that are correct and contextually appropriate, even when the model is not allowed to reference any external data.</p>
+    <p>This makes the T5 model a powerful tool for generating answers in applications such as virtual assistants, educational tools, and any scenario where pre-trained knowledge is sufficient to provide responses.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Implementation Section
+st.markdown('<div class="sub-title">Implementing Closed-Book Question Answering</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>The following example demonstrates how to implement a closed-book question answering pipeline using Spark NLP. The pipeline includes a document assembler, a sentence detector to identify questions, and the T5 model to generate answers.</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
+
+document_assembler = DocumentAssembler()\\
+    .setInputCol("text")\\
+    .setOutputCol("documents")
+
+sentence_detector = SentenceDetectorDLModel\\
+    .pretrained("sentence_detector_dl", "en")\\
+    .setInputCols(["documents"])\\
+    .setOutputCol("questions")
+    
+t5 = T5Transformer()\\
+    .pretrained("google_t5_small_ssm_nq")\\
+    .setTask('trivia question:')\\
+    .setInputCols(["questions"])\\
+    .setOutputCol("answers")
+    
+pipeline = Pipeline().setStages([document_assembler, sentence_detector, t5])
+
+data = spark.createDataFrame([["What is the capital of France?"]]).toDF("text")
+result = pipeline.fit(data).transform(data)
+result.select("answers.result").show(truncate=False)
+''', language='python')
+
+# Example Output
+st.text("""
++---------------------------+
+|answers.result              |
++---------------------------+
+|[Paris]                    |
++---------------------------+
+""")
+
+# Model Info Section
+st.markdown('<div class="sub-title">Choosing the Right T5 Model</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>Several T5 models are available, each pre-trained on different datasets and tasks. For closed-book question answering, it's important to select a model that has been fine-tuned specifically for this task. The model used in the example, "google_t5_small_ssm_nq," is optimized for answering trivia questions in a closed-book setting.</p>
+    <p>For more complex or varied question-answering tasks, consider using larger T5 models like T5-Base or T5-Large, which may offer improved accuracy and context comprehension. Explore the available models on the <a class="link" href="https://sparknlp.org/models?annotator=T5Transformer" target="_blank">Spark NLP Models Hub</a> to find the best fit for your application.</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/2020/02/exploring-transfer-learning-with-t5.html" target="_blank">Google AI Blog</a>: Exploring Transfer Learning with T5</li>
+        <li><a class="link" href="https://sparknlp.org/models?annotator=T5Transformer" target="_blank">Spark NLP Model Hub</a>: Explore T5 models</li>
+        <li>Model used: <a class="link" href="https://sparknlp.org/2022/05/31/google_t5_small_ssm_nq_en_3_0.html" target="_blank">google_t5_small_ssm_nq</a></li>
+        <li><a class="link" href="https://github.com/google-research/text-to-text-transfer-transformer" target="_blank">GitHub</a>: T5 Transformer repository</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)

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+st-annotated-text
+streamlit-tags
+pandas
+numpy
+spark-nlp
+pyspark