DEV Community: Nupoor Shetye

Lingo: Learn English With AI✨

Nupoor Shetye — Sun, 14 Apr 2024 23:21:46 +0000

This is a submission for the Cloudflare AI Challenge.

What I Built

English has become the universal language of communication, yet many struggle to learn it, especially non-native speakers. This inspired me to create Lingo, an AI-powered English language learning app. Lingo offers basic English lessons and advanced features to help users refine their language skills.

Features

Learn: Lingo's Learn feature offers a curated selection of bite-sized English concepts, carefully crafted to help new learners grasp the basics quickly and effectively. Whether you're just starting your journey or looking to brush up on your skills, our Learn feature provides a solid foundation to build upon.
Objects: There have been countless times when I've struggled to find the right word in English for something. With Lingo's Objects feature, describing unfamiliar objects in English becomes a breeze. Simply upload an image, and the resnet-50 image classification model, will detect and identify objects, helping users learn their English names effortlessly.
Summarize: Reading lengthy texts can be daunting, especially for English learners. Lingo's Summarize feature streamlines this process by offering a quick and efficient way to summarize complex texts. Powered by the state-of-the-art bart-large-cnn model, users can easily get key information from long passages either by entering the text directly or even by uploading an image.
Grammar: Good grammar is essential for effective communication, and Lingo's Grammar feature ensures that users can polish their writing skills with ease. Our AI-powered grammar checker, leveraging the cutting-edge llama-2-7b-chat-fp16 model, provides instant feedback on grammar and spelling mistakes, helping users refine their language proficiency.
Concepts: Understanding complex concepts is made simpler with Lingo's Concepts feature. Users can explore a wide range of topics, from science to literature, with simplified explanations and visually engaging content generated by AI. Whether you're struggling with static electricity or photosynthesis, our Concept feature has you covered. For this, I have used the llama-2-7b-chat-fp16 and stable-diffusion-xl-lightning models.
Translate: For efficient language learning, nothing beats comparing sentences in your native language to English. Lingo's Translate feature allows users to do just that, utilizing the powerful m2m100-1.2b model for accurate translation. Whether you're practicing conversation or expanding your vocabulary, our Translate feature is your go-to tool.

Demo

Home Page of the website

Features section listing all features of the website

Learn Page showing bite-sized concepts for new learners

English Tenses lesson teaching tenses by examples

Object Detection page that returns the object detected from the image upload
Summarize Page allows user to either enter text or upload an image for summarization

Grammar Page checks for spelling and grammar mistakes in the text

Concepts Page explains difficult concepts in simple words and visualizations

Translate Page translates various languages into English

You can find link to the website here

NOTE : If the AI tasks do not return a result please wait for some time and try again.

My Code

For creating Lingo, I went with a web application since it can be easily accessed on all devices. I used React as the frontend framework and Cloudflare Pages to create as well as deploy my project. Pages Functions also allows you to add bindings for Workers AI allowing you to seamlessly use AI in your applications.

Technology Stack:

Frontend: React
Deployment: Cloudflare Pages
AI Integration: Cloudflare Workers AI

You can find the link to the Github repo here

Journey

I had never used Cloudflare before, so getting started with it took some time as well as experimentation, but I am glad I was able to deliver a functioning website that utilizes a large variety of task types. Moving ahead I wish to integrate database storage and expand the website functionality for users.

Here are all the models I used:

Text Generation: For the Text Generation feature, I used the llama-2-7b-chat-fp16 model.

Image Classification: Initially I tried experimenting with the Object Detection model but the Image classification model give me better results so I finally decided to go with the resnet-50 model.

Text Summarization: For the Text Summarization feature, I used the bart-large-cnn model.

Text-to-Image Generation: For the Text-to-Image Generation feature, I used the stable-diffusion-xl-lightning model.

Translation: For the Translation feature, I used the m2m100-1.2b model.

Multiple Models and/or Triple Task Types

My project utilizes more than three task types

Text Generation: llama-2-7b-chat-fp16 model.

Image Classification: resnet-50 model.

Text Summarization: bart-large-cnn model.

Text-to-Image Generation: stable-diffusion-xl-lightning model.

Translation: m2m100-1.2b model.

Tutorial to Predict Amsterdam Housing Prices Using MindsDB and MongoDB

Nupoor Shetye — Tue, 01 Nov 2022 03:28:03 +0000

☑️ What is MindsDB?

Most businesses today utilize machine learning to power their decisions. From recommendation systems, to optimized shipping routes to customer sentiment analysis, companies have now incorporated machine learning and artificial intelligence into all aspects of business. And the data generated by the companies serves as the backbone of all these ML algorithms and models. Handling and processing data for preparing machine learning models can be expensive and cumbersome. This is where MindsDB comes into the picture. MindsDB brings machine learning to your database allowing you to leverage machine learning techniques on the data stored inside your database. With the help of MindsDB, you can create, train and optimize ML models right in your database without requiring additional platforms making machine learning more accessible and efficient.

☑️ What will we be learning in this tutorial?

📚 Part 1 : Setting up the requirements

First and foremost, we will prepare our setup that is essential to start forecasting with MindsDB and MongoAPI.

Download MongoDB and MongoDB Compass
Getting started with MindsDB
Integrating MindsDB with MongoDB

📚 Part 2 : Generating ML Models

We will see how to create and train ML models in our database. In this tutorial, we will be predicting the Housing Prices of Amsterdam using this dataset.

Preparing the database
Understanding our Problem Statement
Creating the Predictor Model
Querying the Predictor Model

☑️ Part 1 : Setting up the requirements

We will be explaining this section briefly, so that we can move on to our predictions. For a more detailed explanation please refer to this article.

📌 Download MongoDB and MongoDB Compass

To get started we must have both MongoDB Community Edition and MongoDB Compass installed and working in our systems.

Once you are done with the installation of both MongoDB and MongoDB Compass we can get going with our tutorial.

📌 Getting started with MindsDB

MindsDB provides all users with a free MindsDB Cloud version that they can access to generate predictions on their database. You can sign up for the free MindsDB Cloud Version by following the setup guide. Verify your email and log into your account and you are ready to go. Once done, you should be seeing a page like this :

If you wish, you can choose to install MindsDB on your local system using docker image or by using PyPI. However, we will be working with Minds DB Cloud in this tutorial.

📌 Integrating MindsDB with MongoDB

MindsDB provides us the ability to integrate with MongoDB using the MongoAPI. We can do so by following the given steps.

Open your MongoDB Compass. On the left navigation panel, You will have an option for a New Connection. Click on that Option and you will be provided with the details of your connection.

In the URI Section enter the following :

mongodb://cloud.mindsdb.com/

Click on the Advanced Connection Options dropdown. Here your host will be detected as MindsDB Cloud.

In the Authentication option enter your MindsDB Username and Password. Then click on Save and Connect, give your connection a name and select and color.

If you successfully create a connection you will be displayed a page similar to this :

In the bottom panel of this page, you will see the the Mongo Shell bar, enlarge it and type the following queries and click Enter.

> use mindsdb
> show collections

If you get a result like this, it means that we have succeeded in integrating MindsDB with MongoDB. Now let us move to the second part of our tutorial where we will be generating an ML model.

☑️ Part 2 : Generating ML Models

📌 Preparing the database

We will be preparing our database on which we can run our queries and perform our forecasts. On the MindsDB Cloud console, click on the last icon in the left navigation bar. You will see a 'Select Your Data Sources' page. We can add a variety of data sources, however, for this tutorial we will be working with .csv files.

Go to the files section and click on Import File. Import your csv file and provide a name for your database table in which the contents of the .csv file will be stored. Click on Save and Continue.

Now we have to save this database that we have just created in our MongoDB database. We can use the databases.insertOne() command for this purpose.

To do so, go to the Mongo Shell and type the following command :

db.databases.insertOne({
    name: "HousePricingDB", // database name
    engine: "mongodb", // database engine 
    connection_args: {
        "port": 27017, // default connection port
        "host": "mongodb://cloud.mindsdb.com:27017", // connection host
        "database": "files" // database connection          
    }
});

On clicking Enter, you must receive the following response :

If you get such a response, that means your database is successfully created!

📌 Understanding our Problem Statement

We saw earlier that we will be predicting the housing prices of Amsterdam using this Kaggle dataset. Let us take a closer look into our database that we have set up. Our database consists of the following fields :

Id : Gives the serial number of the data entry

Address : Gives the address of the particular property/house

Zip : Gives the Zip Code of the house

Price : Gives the total cost of the house

Area : Gives the total area of the house we are looking into

Room : Gives the number of rooms in the house

Lon : Gives the exact longitudinal co-ordinates of the property

Lat : Gives the exact latitudinal co-ordinates of the property

We can run the following query in our MindsDB Console to see our database where we can see all our fields :

SELECT * FROM files.housepricing LIMIT 10;

This is what will be displayed :

Now let us understand what we are trying to predict. We have been given a database consisting of various fields and we want to predict the Price of a particular plot or house according to its features like the address, zip code, number of rooms, area, etc. We are going to train an ML model that learns how the Price of a house varies according to the features mentioned above. And once we have trained our model, we can input the details of a house or property and our ML Model will predict what its estimated Price will be.

Sounds like a difficult task? Let us see how MindsDB can do that for us in a simple query!

📌 Creating the Predictor Model

Now that our database is ready, we can go ahead and create our ML Model. As we have seen, The Predictor Model is basically a trained Machine Learning Model that can be used to predict or forecast a particular value known as the target variable or target value.

We use the CREATE PREDICTOR command to create and train a ML model. Enter the following command in your MindsDB console :

CREATE PREDICTOR mindsdb.house_pricing_predictor
FROM files
(SELECT * FROM housepricing)
PREDICT Price;

Here house_pricing_predictor is the name of our Predictor Model and Price is our target value that we want to predict. We want to predict the housing prices taking into account all the other attributes. Click on Run or press Shift+Enter to run our query. If there are no hiccups, we will get a Query Successfully Completed message.

And that’s it! We have created and trained a Machine Learning model by a single query! That is the magic of MindsDB!

📌 Querying the Predictor Model

We can see our machine learning model specifications by typing the following command in our Mongo Shell :

 db.predictors.find({name:"house_pricing_predictor"})

When we press Enter we get all the details of our Predictor Model like its status, accuracy, target value and errors.

To see the same in our MindsDB Console, enter the following query :

SELECT *
FROM mindsdb.predictors
WHERE name='house_pricing_predictor';

Now finally we can query our ML model to predict the target value of a particular entry.

The query for the same is :

SELECT Price, Price_explain
FROM mindsdb.house_pricing_predictor
WHERE Id = 8
AND Address = "Da Costakade 32 II, Amsterdam"
AND Zip = "1053 WL"
AND Area = 80
AND Room = 2
AND Lon = 4.871555
AND Lat = 52.371041;

And lo and behold! Our model predicts the Price of the house according to its attributes entered by us :

We can also query our ML model through the Mongo Shell and start generating predictions.

Use the following command to do so :

db.house_pricing_predictor.find({
Id:"8", 
Address:"Da Costakade 32 II, Amsterdam", 
Zip:"1053 WL", 
Area:"80", Room:"2", 
Lon:"4.871555",
Lat:"52.371041"})

And this is our output :

☑️ Conclusion :

Using MindsDB we have successfully created and trained a Machine Learning model in our database and unlocked the ability to generate in-database forecasts. You can visit the MindsDB Documentation to know the various features of MindsDB.

☑️ What’s Next?

If you enjoyed following along to this tutorial, make sure to Sign Up for a free MindsDB Cloud account and continue exploring! Kaggle is a great resource to find similar datasets and you can create and train an ML model of your own with the help of MindsDB. You can also check them out on GitHub.

Tutorial to Predict the Weather Using MindsDB and MongoDB

Nupoor Shetye — Tue, 01 Nov 2022 03:24:23 +0000

☑️ What is MindsDB?

MindsDB is a tool that helps you to leverage machine learning techniques on the data stored inside your database. MindsDB brings machine learning into the database reducing complex workflows and extended durations of processing, creation and deployment. With MindsDB, you can build, train, optimize, and deploy your ML models without the need for other platforms. MindsDB helps you generate forecasts and predictions from your database which can be accessed with the help of a simple query. The revolutionary model of MindsDB helps businesses make decisions faster and more efficiently providing real-time value to the company.

☑️ What will the tutorial entail?

📝 Part 1 : Setting up the requirements

Firstly, we will set up all the tools we will be needing to utilize the functionalities of MindsDB using MongoAPI and get the dice rolling.

Download MongoDB and MongoDB Compass
Getting started with MindsDB
Integrating MindsDB with MongoDB

📝 Part 2 : Generating ML Models

We will see how we can generate ML models in our database itself and go over the queries required to do so. In today's tutorial, we will be generating an ML Model to predict the weather using this dataset.

Preparing the database
Understanding our Problem Statement
Creating the Predictor Model
Querying the Predictor Model

☑️ Part 1 : Setting up the requirements

👉 Download MongoDB and MongoDB Compass

In this tutorial, we will be using MongoDB as our database and MongoDB Compass to interact with our database and with MindsDB as well. For anyone who is a complete newbie, MongoDB is a cross-platform NoSQL database that is used to store high volumes of data. MongoDB does not use tables and rows like a traditional relational database, instead, the data is organized as collections of documents containing key:value pairs. MongoDB Compass is the GUI for MongoDB so it provides an interface for the user to interact with the database, greatly simplifying things for beginners.

We won’t be diving too deep into the installation of MongoDB. There are two versions of MongoDB available, a free Community Edition and a paid Enterprise Edition. We will be working with the Community Edition as it is more than enough to test out the features of the database. Download the Community Edition of MongoDB and follow the installation steps to ensure correct installation. During the installation you will be provided with an option to download the MongoDB Compass as well. Make sure to select the checkbox or else you can download the MongoDB Compass separately as well and install it.

Once you have downloaded both MongoDB and MongoDB Compass successfully, we can move on to the next step.

NOTE : Previously the Mongo Shell was bundled together with the MongoDB and didn’t need separate installation. However, now, one must download and install the Mongo Shell separately.
You can download the Mongo Shell and follow the installation guide. Make sure you add the MongoDB and Mongo Shell binary files to your environment variables so that you can access them from your command prompt or terminal directly.

👉 Getting started with MindsDB

If you wish, you can choose to install MindsDB on your local system using docker image or by using PyPI. However, we will be working with Minds DB Cloud in this tutorial.

👉 Integrating MindsDB with MongoDB

MindsDB provides us the ability to integrate with MongoDB using the MongoAPI. We can do so by following the given steps.

Open your MongoDB Compass. On the left navigation panel, You will have an option for a New Connection. Click on that Option and you will be provided with the details of your connection.

In the URI Section enter the following :

mongodb://cloud.mindsdb.com/

Click on the Advanced Connection Options dropdown. Here your host will be detected as MindsDB Cloud.

In the Authentication option enter your MindsDB Username and Password. Then click on Save and Connect, give your connection a name and select and color.

If you successfully create a connection you will be displayed a page similar to this :

In the bottom panel of this page, you will see the the Mongo Shell bar, enlarge it and type the following queries and click Enter.

> use mindsdb
> show collections

If you get a result like this, it indicates that you have successfully integrated MindsDB with MongoDB. Whew..!! That was quite a task. But don’t worry, the exciting part is yet to come.

☑️ Part 2 : Generating ML Models

👉 Preparing the database

Go to the files section and click on Import File. Import your csv file and provide a name for your database table in which the contents of the .csv file will be stored. Click on Save and Continue.

Now we have to save this database that we have just created in our MongoDB database. We will be using the databases.insertOne() command to do so

To do so, go to the Mongo Shell and type the following command :

db.databases.insertOne({
    name: "WeatherDB", // database name
    engine: "mongodb", // database engine 
    connection_args: {
        "port": 27017, // default connection port
        "host": "mongodb://cloud.mindsdb.com:27017", // connection host
        "database": "files" // database connection          
    }
});

On clicking Enter, you must receive the following response :

If you get such a response, that means your database is all prepped to explore!

📌 Understanding our Problem Statement

Our main goal is to predict the weather and we are going to be using this Kaggle dataset that we saw earlier. Our database consists of various parameters or fields as seen below :

date : The dates at which the weather was recorded

precipitation : All forms of precipitation such as rain or snow that was recorded during the day

temp_max : The maximum temperature recorded on the day

temp_min : The minimum temperature recorded on the day

wind : The wind speed on the particular date

weather : The weather that was finally recorded on that day

To have a glimpse at all our database fields we can run the following query in the MindsDB Console :

SELECT * FROM files.weather LIMIT 10;

We will be given the following output :

Now let us get familiar with our problem statement and what exactly are we trying to predict. As we can see our database contains several fields such as the date, precipitation, temperature and wind speed. And our final field is the weather that was recorded and that we wish to predict. What we want to do is to create an ML model to tell us what the weather on a particular day will be if we provide the remaining details like the date, precipitation, temperature and wind speed. But how will our ML model be able to achieve this task? That is where the training phase kicks in. On the basis of our given database, we will train our ML Model to learn how the final output of the weather varies according to the values of the remaining fields. And once we have trained our model, we can input the fields in our database and our ML Model will predict what the estimated weather would be in accordance to those parameters.

Sounds overwhelming? Let us see how MindsDB can do that for us in just a few seconds!

👉 Creating the Predictor Model

Now that our database is ready, we can go ahead and create our very first Predictor Model. The Predictor Model is basically a trained Machine Learning Model that can be used to predict or forecast a particular value known as the target variable or target value.

We use the CREATE PREDICTOR command to create and train a ML model. Enter the following command in your MindsDB console :

CREATE PREDICTOR mindsdb.weather_predictor
FROM files
(SELECT * FROM weather)
PREDICT weather;

Here weather_predictor is the name of our Predictor Model and weather is our target value that we want to predict. Click on Run or press Shift+Enter to run our query. If we don't encounter any issues, we will get a Query Successfully Completed message.

And that’s it! We have created and trained a Machine Learning model in just a few lines of code! That is the magic of MindsDB!

👉 Querying the Predictor Model

We can see the details of our machine learning model by typing the following command in our Mongo Shell :

 db.predictors.find({name:"weather_predictor"})

When we press Enter we get all the details of our Predictor Model like its status, accuracy, target value and errors.

To see the same in our MindsDB Console, enter the following query :

SELECT *
FROM mindsdb.predictors
WHERE name='weather_predictor';

Now finally we can query our ML model to predict the target value of a particular entry.

The syntax for the same is :

SELECT weather, weather_explain
FROM mindsdb.weather_predictor
WHERE precipitation = 0.8
AND date = "2012-01-03"
AND temp_max = 11.7
AND temp_min = 7.2
AND wind = 2.3;

We will obtain the following prediction for the weather according to our parameters entered :

We can also query our ML model through the Mongo Shell and start generating predictions.

Use the following command :

db.weather_predictor.find({
date:"2012-01-03", 
precipitation:"0.8", 
temp_max:"11.7", 
temp_min:"7.2", 
wind:"2.3"})

We are displayed this output:

☑️ Conclusion :

☑️ What’s Next?

If you enjoyed following along to this tutorial, make sure to Sign Up for a free MindsDB Cloud account and continue exploring! Kaggle is a great resource for you to find similar datasets and you can create and train an ML model of your own with the help of MindsDB. You can also check them out on GitHub.