Upload 8 files

.dockerignore

@@ -0,0 +1,34 @@
+# Include any files or directories that you don't want to be copied to your
+# container here (e.g., local build artifacts, temporary files, etc.).
+#
+# For more help, visit the .dockerignore file reference guide at
+# https://docs.docker.com/go/build-context-dockerignore/
+
+**/.DS_Store
+**/__pycache__
+**/.venv
+**/.classpath
+**/.dockerignore
+**/.env
+**/.git
+**/.gitignore
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/bin
+**/charts
+**/docker-compose*
+**/compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+LICENSE
+README.md

Dockerfile

@@ -1,101 +1,63 @@
-FROM nvidia/cuda:11.3.1-base-ubuntu20.04
-
-ENV DEBIAN_FRONTEND=noninteractive \
-	TZ=Europe/Paris
-
-# Remove any third-party apt sources to avoid issues with expiring keys.
-# Install some basic utilities
-RUN rm -f /etc/apt/sources.list.d/*.list && \
-    apt-get update && apt-get install -y --no-install-recommends \
-    curl \
-    ca-certificates \
-    sudo \
-    git \
-    git-lfs \
-    zip \
-    unzip \
-    htop \
-    bzip2 \
-    libx11-6 \
-    build-essential \
-    libsndfile-dev \
-    software-properties-common \
- && rm -rf /var/lib/apt/lists/*
-
-RUN add-apt-repository ppa:flexiondotorg/nvtop && \
-    apt-get upgrade -y && \
-    apt-get install -y --no-install-recommends nvtop
-
-RUN curl -sL https://deb.nodesource.com/setup_14.x  | bash - && \
-    apt-get install -y nodejs && \
-    npm install -g configurable-http-proxy
-
-# Create a working directory
-WORKDIR /app
-
-# Create a non-root user and switch to it
-RUN adduser --disabled-password --gecos '' --shell /bin/bash user \
- && chown -R user:user /app
-RUN echo "user ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/90-user
-USER user
-
-# All users can use /home/user as their home directory
-ENV HOME=/home/user
-RUN mkdir $HOME/.cache $HOME/.config \
- && chmod -R 777 $HOME
-
-# Set up the Conda environment
-ENV CONDA_AUTO_UPDATE_CONDA=false \
-    PATH=$HOME/miniconda/bin:$PATH
-RUN curl -sLo ~/miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-py39_4.10.3-Linux-x86_64.sh \
- && chmod +x ~/miniconda.sh \
- && ~/miniconda.sh -b -p ~/miniconda \
- && rm ~/miniconda.sh \
- && conda clean -ya
-
-WORKDIR $HOME/app
-
-#######################################
-# Start root user section
-#######################################
+# syntax=docker/dockerfile:1
 
-USER root
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Dockerfile reference guide at
+# https://docs.docker.com/go/dockerfile-reference/
 
-# User Debian packages
-## Security warning : Potential user code executed as root (build time)
-RUN --mount=target=/root/packages.txt,source=packages.txt \
-    apt-get update && \
-    xargs -r -a /root/packages.txt apt-get install -y --no-install-recommends \
-    && rm -rf /var/lib/apt/lists/*
+# Want to help us make this template better? Share your feedback here: https://forms.gle/ybq9Krt8jtBL3iCk7
 
-RUN --mount=target=/root/on_startup.sh,source=on_startup.sh,readwrite \
-	bash /root/on_startup.sh
+ARG PYTHON_VERSION=3.11.9
+FROM python:${PYTHON_VERSION}-slim as base
 
-RUN mkdir /data && chown user:user /data
+# Prevents Python from writing pyc files.
+ENV PYTHONDONTWRITEBYTECODE=1
 
-#######################################
-# End root user section
-#######################################
+# Keeps Python from buffering stdout and stderr to avoid situations where
+# the application crashes without emitting any logs due to buffering.
+ENV PYTHONUNBUFFERED=1
 
-USER user
-
-# Python packages
-RUN --mount=target=requirements.txt,source=requirements.txt \
-    pip install --no-cache-dir --upgrade -r requirements.txt
-
-# Copy the current directory contents into the container at $HOME/app setting the owner to the user
-COPY --chown=user . $HOME/app
-
-RUN chmod +x start_server.sh
-
-COPY --chown=user login.html /home/user/miniconda/lib/python3.9/site-packages/jupyter_server/templates/login.html
-
-ENV PYTHONUNBUFFERED=1 \
-	GRADIO_ALLOW_FLAGGING=never \
-	GRADIO_NUM_PORTS=1 \
-	GRADIO_SERVER_NAME=0.0.0.0 \
-	GRADIO_THEME=huggingface \
-	SYSTEM=spaces \
-	SHELL=/bin/bash
+WORKDIR /app
 
-CMD ["./start_server.sh"]
+# Create a non-privileged user that the app will run under.
+# See https://docs.docker.com/go/dockerfile-user-best-practices/
+ARG UID=10001
+RUN adduser \
+    --disabled-password \
+    --gecos "" \
+    --home "/nonexistent" \
+    --shell "/sbin/nologin" \
+    --no-create-home \
+    --uid "${UID}" \
+    appuser
+
+# Download dependencies as a separate step to take advantage of Docker's caching.
+# Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
+# Leverage a bind mount to requirements.txt to avoid having to copy them into
+# into this layer.
+RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=bind,source=requirements.txt,target=requirements.txt \
+    python -m pip install -r requirements.txt
+
+# Switch to the non-privileged user to run the application.
+USER appuser
+
+# Set the TRANSFORMERS_CACHE environment variable
+ENV TRANSFORMERS_CACHE=/tmp/.cache/huggingface
+
+# Create the cache folder with appropriate permissions
+RUN mkdir -p $TRANSFORMERS_CACHE && chmod -R 777 $TRANSFORMERS_CACHE
+
+# Set NLTK data directory
+ENV NLTK_DATA=/tmp/nltk_data
+
+# Create the NLTK data directory with appropriate permissions
+RUN mkdir -p $NLTK_DATA && chmod -R 777 $NLTK_DATA
+
+# Copy the source code into the container.
+COPY . .
+
+# Expose the port that the application listens on.
+EXPOSE 8000
+
+# Run the application.
+CMD uvicorn 'main:app' --host=0.0.0.0 --port=7860 

README.Docker.md

@@ -0,0 +1,22 @@
+### Building and running your application
+
+When you're ready, start your application by running:
+`docker compose up --build`.
+
+Your application will be available at http://localhost:7860 .
+
+### Deploying your application to the cloud
+
+First, build your image, e.g.: `docker build -t myapp .`.
+If your cloud uses a different CPU architecture than your development
+machine (e.g., you are on a Mac M1 and your cloud provider is amd64),
+you'll want to build the image for that platform, e.g.:
+`docker build --platform=linux/amd64 -t myapp .`.
+
+Then, push it to your registry, e.g. `docker push myregistry.com/myapp`.
+
+Consult Docker's [getting started](https://docs.docker.com/go/get-started-sharing/)
+docs for more detail on building and pushing.
+
+### References
+* [Docker's Python guide](https://docs.docker.com/language/python/)

compose.yaml

@@ -0,0 +1,49 @@
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Docker Compose reference guide at
+# https://docs.docker.com/go/compose-spec-reference/
+
+# Here the instructions define your application as a service called "server".
+# This service is built from the Dockerfile in the current directory.
+# You can add other services your application may depend on here, such as a
+# database or a cache. For examples, see the Awesome Compose repository:
+# https://github.com/docker/awesome-compose
+services:
+  server:
+    build:
+      context: .
+    ports:
+      - 8000:8000
+
+# The commented out section below is an example of how to define a PostgreSQL
+# database that your application can use. `depends_on` tells Docker Compose to
+# start the database before your application. The `db-data` volume persists the
+# database data between container restarts. The `db-password` secret is used
+# to set the database password. You must create `db/password.txt` and add
+# a password of your choosing to it before running `docker compose up`.
+#     depends_on:
+#       db:
+#         condition: service_healthy
+#   db:
+#     image: postgres
+#     restart: always
+#     user: postgres
+#     secrets:
+#       - db-password
+#     volumes:
+#       - db-data:/var/lib/postgresql/data
+#     environment:
+#       - POSTGRES_DB=example
+#       - POSTGRES_PASSWORD_FILE=/run/secrets/db-password
+#     expose:
+#       - 5432
+#     healthcheck:
+#       test: [ "CMD", "pg_isready" ]
+#       interval: 10s
+#       timeout: 5s
+#       retries: 5
+# volumes:
+#   db-data:
+# secrets:
+#   db-password:
+#     file: db/password.txt
+

main.py

@@ -0,0 +1,100 @@
+from contextlib import asynccontextmanager
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel, ValidationError
+from fastapi.encoders import jsonable_encoder
+
+# TEXT PREPROCESSING
+# --------------------------------------------------------------------
+import re
+import string
+import nltk
+nltk.download('punkt')
+nltk.download('wordnet')
+nltk.download('omw-1.4')
+from nltk.stem import WordNetLemmatizer
+
+# Function to remove URLs from text
+def remove_urls(text):
+    return re.sub(r'http[s]?://\S+', '', text)
+
+# Function to remove punctuations from text
+def remove_punctuation(text):
+    regular_punct = string.punctuation
+    return str(re.sub(r'['+regular_punct+']', '', str(text)))
+
+# Function to convert the text into lower case
+def lower_case(text):
+    return text.lower()
+
+# Function to lemmatize text
+def lemmatize(text):
+    wordnet_lemmatizer = WordNetLemmatizer()
+
+    tokens = nltk.word_tokenize(text)
+    lemma_txt = ''
+    for w in tokens:
+        lemma_txt = lemma_txt + wordnet_lemmatizer.lemmatize(w) + ' '
+
+    return lemma_txt
+
+def preprocess_text(text):
+    # Preprocess the input text
+    text = remove_urls(text)
+    text = remove_punctuation(text)
+    text = lower_case(text)
+    text = lemmatize(text)
+    return text
+
+# Load the model using FastAPI lifespan event so that the model is loaded at the beginning for efficiency
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # Load the model from HuggingFace transformers library
+    from transformers import pipeline
+    global sentiment_task
+    sentiment_task = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment-latest", tokenizer="cardiffnlp/twitter-roberta-base-sentiment-latest")
+    yield
+    # Clean up the model and release the resources
+    del sentiment_task
+
+# Initialize the FastAPI app
+app = FastAPI(lifespan=lifespan)
+
+# Define the input data model
+class TextInput(BaseModel):
+    text: str
+
+# Define the welcome endpoint
+@app.get('/')
+async def welcome():
+    return "Welcome to our Text Classification API"
+
+# Validate input text length
+MAX_TEXT_LENGTH = 1000
+
+# Define the sentiment analysis endpoint 
+@app.post('/analyze/{text}')
+async def classify_text(text_input:TextInput):    
+    try:
+        # Convert input data to JSON serializable dictionary
+        text_input_dict = jsonable_encoder(text_input)
+        # Validate input data using Pydantic model
+        text_data = TextInput(**text_input_dict)  # Convert to Pydantic model
+
+        # Validate input text length
+        if len(text_input.text) > MAX_TEXT_LENGTH:
+            raise HTTPException(status_code=400, detail="Text length exceeds maximum allowed length")
+        elif len(text_input.text) == 0:
+            raise HTTPException(status_code=400, detail="Text cannot be empty")
+    except ValidationError as e:
+        # Handle validation error
+        raise HTTPException(status_code=422, detail=str(e))
+
+    try:
+        # Perform text classification
+        return sentiment_task(preprocess_text(text_input.text))
+    except ValueError as ve:
+        # Handle value error
+        raise HTTPException(status_code=400, detail=str(ve))
+    except Exception as e:
+        # Handle other server errors
+        raise HTTPException(status_code=500, detail=str(e))

requirements.txt

@@ -1,4 +1,7 @@
-jupyterlab==3.6.1
-jupyter-server==2.3.0
-tornado==6.2
-ipywidgets
+fastapi==0.110.1
+nest_asyncio==1.6.0
+nltk==3.8.1
+pydantic==2.7.0
+transformers==4.38.2
+uvicorn==0.29.0
+torch==2.2.2

test_main.py

@@ -0,0 +1,70 @@
+from fastapi.testclient import TestClient
+from main import app
+from main import TextInput
+from fastapi.encoders import jsonable_encoder
+
+client = TestClient(app)
+
+# Test the welcome endpoint
+def test_welcome():
+    # Test the welcome endpoint
+    response = client.get("/")
+    assert response.status_code == 200
+    assert response.json() == "Welcome to our Text Classification API"
+
+# Test the sentiment analysis endpoint for positive sentiment
+def test_positive_sentiment():
+    with client:
+        # Define the request payload 
+        # Initialize payload as a TextInput object
+        payload = TextInput(text="I love this product! It's amazing!")
+
+        # Convert TextInput object to JSON-serializable dictionary
+        payload_dict = jsonable_encoder(payload)
+        
+        # Send a POST request to the sentiment analysis endpoint
+        response = client.post("/analyze/{text}", json=payload_dict)
+
+        # Assert that the response status code is 200 OK
+        assert response.status_code == 200
+        
+        # Assert that the sentiment returned is positive
+        assert response.json()[0]['label'] == "positive"
+
+# Test the sentiment analysis endpoint for negative sentiment
+def test_negative_sentiment():
+    with client:
+        # Define the request payload 
+        # Initialize payload as a TextInput object
+        payload = TextInput(text="I'm really disappointed with this service. It's terrible.")
+
+        # Convert TextInput object to JSON-serializable dictionary
+        payload_dict = jsonable_encoder(payload)
+        
+        # Send a POST request to the sentiment analysis endpoint
+        response = client.post("/analyze/{text}", json=payload_dict)
+
+        # Assert that the response status code is 200 OK
+        assert response.status_code == 200
+        
+        # Assert that the sentiment returned is positive
+        assert response.json()[0]['label'] == "negative"
+
+# Test the sentiment analysis endpoint for neutral sentiment
+def test_neutral_sentiment():
+    with client:
+        # Define the request payload 
+        # Initialize payload as a TextInput object
+        payload = TextInput(text="This is a neutral statement.")
+
+        # Convert TextInput object to JSON-serializable dictionary
+        payload_dict = jsonable_encoder(payload)
+        
+        # Send a POST request to the sentiment analysis endpoint
+        response = client.post("/analyze/{text}", json=payload_dict)
+
+        # Assert that the response status code is 200 OK
+        assert response.status_code == 200
+        
+        # Assert that the sentiment returned is positive
+        assert response.json()[0]['label'] == "neutral"