How To Build and Deploy an NLP Model with FastAPI: Part 2

This is the second and final part of the series on How to build and deploy an NLP model with FastAPI. In , we looked at how to build an NLP model that can classify movie reviews into different sentiments. the first part In this second and final part, you will learn What is FastAPI and how to install it. How to deploy your model with FastAPI. How to use your deployed NLP model in any Python application. So let’s get started.🚀 What is FastAPI? FastAPI is the fast and modern python web framework for building different . It provides higher performance, easier to code, and comes up with automatic & interactive documentation. FastAPI is built upon two major python libraries – (for web handling) and (for data handling & validation). FastAPI is very fast compared to Flask because it brings asynchronous function handlers to the table. APIs Starlette Pydantic If you want to know more about FastAPI, I recommend you read this by Sebastián Ramírez. article In this article, we will try to use some of the features presented in FastAPI to serve our NLP model. How To Install FastAPI Firstly, make sure you install the latest version (with pip): pip install fastapi You will also need an ASGI server for production such as . uvicorn pip install uvicorn Deploy NLP Model with FastAPI In this section, we are going to deploy our trained model as a REST API with FastAPI. The code for our API will be saved in a python file called , this file will be responsible for running our FastAPI app. NLP main.py Import packages The first step is to import packages that will help us to build the FastAPI app and run the NLP model. string punctuation nltk.tokenize word_tokenize nltk nltk.corpus stopwords nltk.stem WordNetLemmatizer re os os.path dirname, join, realpath joblib uvicorn fastapi FastAPI # text preprocessing modules from import # text preprocessing modules from import import from import from import import # regular expression import from import import import from import Initializing a FastAPI App Instance We can use the following code to initialize the FastAPI app. app = FastAPI( title= , description= , version= , ) "Sentiment Model API" "A simple API that use NLP model to predict the sentiment of the movie's reviews" "0.1" As you can see we have customized the configuration of our FastAPI application by including: Title of the API Description of the API. The version of the API. Load the NLP model To load the model we use method and add the path to the model directory. The name of the NLP model is . joblib.load() sentiment_model_pipeline.pkl open( join(dirname(realpath(__file__)), ), ) f: model = joblib.load(f) # load the sentiment model with "models/sentiment_model_pipeline.pkl" "rb" as Define a Function to Clean the Data We will use the same function called from Part 1 that cleans the review data by removing stopwords, numbers, and punctuation, and finally, convert each word into its base form by using the lemmatization process in the NLTK package. text_cleaning() text = re.sub( , , text) text = re.sub( , , text) text = re.sub( , , text) text = re.sub( , , text) text = .join([c c text c punctuation]) remove_stop_words: stop_words = stopwords.words( ) text = text.split() text = [w w text w stop_words] text = .join(text) lemmatize_words: text = text.split() lemmatizer = WordNetLemmatizer() lemmatized_words = [lemmatizer.lemmatize(word) word text] text = .join(lemmatized_words) text : def text_cleaning (text, remove_stop_words=True, lemmatize_words=True) # Clean the text, with the option to remove stop_words and to lemmatize word # Clean the text r"[^A-Za-z0-9]" " " r"\'s" " " r"http\S+" " link " r"\b\d+(?:\.\d+)?\s+" "" # remove numbers # Remove punctuation from text "" for in if not in # Optionally, remove stop words if # load stopwords "english" for in if not in " " # Optionally, shorten words to their stems if for in " " # Return a list of words return Create Prediction Endpoint The next step is to add our prediction endpoint called " " with the GET request method. /predict-review @app.get("/predict-review") “An API endpoint is the point of entry in a communication channel when two systems are interacting. It refers to touchpoints of the communication between an API and a server.” Then we define a prediction function for this endpoint. The name of the function is called with a review parameter. predict_sentiment() The predict_sentiment() function will do the following tasks. Receive the movie review. Clean the movie review by using the function. text_cleaning() Make a prediction by using our NLP model. Save the prediction result in the variable (either 0 or 1). output Save the probability of the prediction in the variable and format it into 2 decimal places. probas Finally, return prediction and probability result. cleaned_review = text_cleaning(review) prediction = model.predict([cleaned_review]) output = int(prediction[ ]) probas = model.predict_proba([cleaned_review]) output_probability = .format(float(probas[:, output])) sentiments = { : , : } result = { : sentiments[output], : output_probability} result @app.get("/predict-review") : def predict_sentiment (review: str) """ A simple function that receive a review content and predict the sentiment of the content. :param review: :return: prediction, probabilities """ # clean the review # perform prediction 0 "{:.2f}" # output dictionary 0 "Negative" 1 "Positive" # show results "prediction" "Probability" return Here are all blocks of codes in the file. main.py string punctuation nltk.tokenize word_tokenize nltk nltk.corpus stopwords nltk.stem WordNetLemmatizer re os os.path dirname, join, realpath joblib uvicorn fastapi FastAPI app = FastAPI( title= , description= , version= , ) open( join(dirname(realpath(__file__)), ), ) f: model = joblib.load(f) text = re.sub( , , text) text = re.sub( , , text) text = re.sub( , , text) text = re.sub( , , text) text = .join([c c text c punctuation]) remove_stop_words: stop_words = stopwords.words( ) text = text.split() text = [w w text w stop_words] text = .join(text) lemmatize_words: text = text.split() lemmatizer = WordNetLemmatizer() lemmatized_words = [lemmatizer.lemmatize(word) word text] text = .join(lemmatized_words) text cleaned_review = text_cleaning(review) prediction = model.predict([cleaned_review]) output = int(prediction[ ]) probas = model.predict_proba([cleaned_review]) output_probability = .format(float(probas[:, output])) sentiments = { : , : } result = { : sentiments[output], : output_probability} result # text preprocessing modules from import # text preprocessing modules from import import from import from import import # regular expression import from import import import from import "Sentiment Model API" "A simple API that use NLP model to predict the sentiment of the movie's reviews" "0.1" # load the sentiment model with "models/sentiment_model_pipeline.pkl" "rb" as # cleaning the data : def text_cleaning (text, remove_stop_words=True, lemmatize_words=True) # Clean the text, with the option to remove stop_words and to lemmatize word # Clean the text r"[^A-Za-z0-9]" " " r"\'s" " " r"http\S+" " link " r"\b\d+(?:\.\d+)?\s+" "" # remove numbers # Remove punctuation from text "" for in if not in # Optionally, remove stop words if # load stopwords "english" for in if not in " " # Optionally, shorten words to their stems if for in " " # Return a list of words return @app.get("/predict-review") : def predict_sentiment (review: str) """ A simple function that receive a review content and predict the sentiment of the content. :param review: :return: prediction, probabilities """ # clean the review # perform prediction 0 "{:.2f}" # output dictionary 0 "Negative" 1 "Positive" # show results "prediction" "Probability" return Run the API The following command will help us to run the FastAPI app we have created. uvicorn main:app --reload Here are the settings we have defined for uvicorn to run our FastAPI app. the file main.py that has the FastAPI app. main: the object created inside of main.py with the line app = FastAPI(). app: : Enables the server to automatically restart whenever we make changes in the code. --reload FastAPI provides an Automatic Interactive API documentation page. To access it navigate to in your browser and then you will see the documentation page created automatically by FastAPI. http://127.0.0.1:8000/docs The documentation page shows the name of our API, the description, and its version. It also shows a list of available routes in our API that you can interact with. To make a prediction first click the " " route and then click on the button " , it allows you to fill the review parameter and directly interact with the API. predict-review Try it out" Fill the review field by adding a movie review of your choice. I added the following movie review about movie released in 2021. Zack Snyder's Justice League "I loved the movie from the beginning to the end. Just like Ray fisher said, I was hoping that the movie doesn't end. The begging scene was mind blowing, liked that scene very much. Unlike 'the Justice League' the movie show every hero is best at their own thing, make us love every character. Thanks, Zack and the whole team." Then click the execute button to make a prediction and get the result. Finally, the result from the API shows that our NLP model predicts the review provided has sentiment with the probability of . Positive 0.70 Use NLP model in any Python Applications To use our NLP API in any python application, we need to install the requests python package. This python package will help us to send HTTP requests to the FastAPI app we have developed. To install the requests package run the following command. pip install requests Then create a simple python file called . This file will be responsible to send our HTTP requests. python_app.py We first import requests package. requests r import as Add a movie review about Movie. Godzilla vs Kong (2021) review = # add review "This movie was exactly what I wanted in a Godzilla vs Kong movie. It's big loud, brash and dumb, in the best ways possible. It also has a heart in a the form of Jia (Kaylee Hottle) and a superbly expressionful Kong. The scenes of him in the hollow world are especially impactful and beautifully shot/animated. Kong really is the emotional core of the film (with Godzilla more of an indifferent force of nature), and is done so well he may even convert a few members of Team Godzilla." Then add the review in a key parameter to pass to the HTTP request. keys = { : review} "review" Finally, we send a request to our API to make a prediction of the review. prediction = r.get( , params=keys) "http://127.0.0.1:8000/predict-review/" Then we can see the prediction results. results = prediction.json() print(results[ ]) print(results[ ]) "prediction" "Probability" This will show the prediction and its probability. Here are the results. Positive 0.54 Wrapping Up Congratulations 👏👏, you have made it to the end of this part 2. I hope you have learned something new on how to deploy your NLP model with FastAPI. If you want to learn more about FastAPI, I recommend taking this created by . full FastAPI course Bitfumes You can download the project source code used in this article here: https://github.com/Davisy/Deploy-NLP-Model-with-FastAPI If you learned something new or enjoyed reading this article, please share it so that others can see it. Until then, see you in the next article!. You can also find me on Twitter and you can read more articles like this . @Davis_McDavid here Want to keep up to date with all the latest in machine learning? Subscribe to our newsletter in the footer below!