General

AI Leadership: Data-Driven Decision Making & Avoiding "Analysis Paralysis" with Jerry Reghunadh

Published Nov 18, 2024

Updated Dec 11, 2024

1 min read

In this episode of Leadership Exchange, host Rob Ocel chats with Jerry Reghunadh, Senior Director of Enterprise Architecture at Data Nimbus, about leadership, AI adoption, and data-driven decision-making. Jerry shares his career journey, insights on leveraging tools like ChatGPT and Copilot, and strategies for building effective data pipelines. They explore how companies can avoid "analysis paralysis," adopt AI strategically, and evaluate new technologies to solve real-world problems. Tune in for practical advice on aligning innovation with business goals and staying competitive in a rapidly evolving tech landscape.

Chapters 00:00 – Introduction
00:31 – Jerry’s Leadership Journey
02:01 – Discussing AI in Leadership
03:59 – Experimenting with AI Tools
06:24 – Overcoming Analysis Paralysis
09:18 – Importance of Early AI Adoption
13:12 – AI’s Impact on Efficiency
14:30 – Sponsor Message
16:26 – Setting Realistic Goals for AI
19:41 – Data Management and AI
23:09 – Is AI Just a Fad?
27:22 – Testing New Technologies
29:56 – Final Thoughts on AI
30:25 – Connect with Jerry
30:44 – Closing Remarks
31:20 – Outro

Follow Jerry on Social Media Linkedin: https://www.linkedin.com/in/jerrymannel/

How to build an AI assistant with OpenAI, Vercel AI SDK, and Ollama with Next.js

In today’s blog post, we’ll build an AI Assistant using three different AI models: Whisper and TTS from OpenAI and Llama 3.1 from Meta. While exploring AI, I wanted to try different things and create an AI assistant that works by voice. This curiosity led me to combine OpenAI’s Whisper and TTS models with Meta’s Llama 3.1 to build a voice-activated assistant. Here’s how these models will work together: * First, we’ll send our audio to the Whisper model, which will convert it from speech to text. * Next, we’ll pass that text to the Llama 3.1 model. Llama will understand the text and generate a response. * Finally, we’ll take Llama’s response and send it to the TTS model, turning the text back into speech. We’ll then stream that audio back to the client. Let’s dive in and start building this excellent AI Assistant! Getting started We will use different tools to build our assistant. To build our client side, we will use Next.js. However, you could choose whichever framework you prefer. To use our OpenAI models, we will use their TypeScript / JavaScript SDK. To use this API, we require the following environmental variable: OPENAI_API_KEY— To get this key, we need to log in to the OpenAI dashboard and find the API keys section. Here, we can generate a new key. Awesome. Now, to use our Llama 3.1 model, we will use Ollama and the Vercel AI SDK, utilizing a provider called ollama-ai-provider. Ollama will allow us to download our preferred model (we could even use a different one, like Phi) and run it locally. The Vercel SDK will facilitate its use in our Next.js project. To use Ollama, we just need to download it and choose our preferred model. For this blog post, we are going to select Llama 3.1. After installing Ollama, we can verify if it is working by opening our terminal and writing the following command: Notice that I wrote “llama3.1” because that’s my chosen model, but you should use the one you downloaded. Kicking things off It's time to kick things off by setting up our Next.js app. Let's start with this command: ` After running the command, you’ll see a few prompts to set the app's details. Let's go step by step: * Name your app. * Enable app router. The other steps are optional and entirely up to you. In my case, I also chose to use TypeScript and Tailwind CSS. Now that’s done, let’s go into our project and install the dependencies that we need to run our models: ` Building our client logic Now, our goal is to record our voice, send it to the backend, and then receive a voice response from it. To record our audio, we need to use client-side functions, which means we need to use client components. In our case, we don’t want to transform our whole page to use client capabilities and have the whole tree in the client bundle; instead, we would prefer to use Server components and import our client components to progressively enhance our application. So, let’s create a separate component that will handle the client-side logic. Inside our app folder, let's create a components folder, and here, we will be creating our component: ` Let’s go ahead and initialize our component. I went ahead and added a button with some styles in it: ` And then import it into our Page Server component: ` Now, if we run our app, we should see the following: Awesome! Now, our button doesn’t do anything, but our goal is to record our audio and send it to someplace; for that, let us create a hook that will contain our logic: ` We will use two APIs to record our voice: navigator and MediaRecorder. The navigator API will give us information about the user’s media devices like the user media audio, and the MediaRecorder will help us record the audio from it. This is how they’re going to play out together: ` Let’s explain this code step by step. First, we create two new states. The first one is for keeping track of when we are recording, and the second one stores the instance of our MediaRecorder. ` Then, we’ll create our first method, startRecording. Here, we are going to have the logic to start recording our audio. We first check if the user has media devices available thanks to the navigator API that gives us information about the browser environment of our user: If we don’t have media devices to record our audio, we just return. If they do, then let us create a stream using their audio media device. ` Finally, we go ahead and create an instance of a MediaRecorder to record this audio: ` Then we need a method to stop our recording, which will be our stopRecording. Here, we will just stop our recording in case a media recorder exists. ` We are recording our audio, but we are not storing it anywhere. Let’s add a new useEffect and ref to accomplish this. We would need a new ref, and this is where our chunks of audio data will be stored. ` In our useEffect we are going to do two main things: store those chunks in our ref, and when it stops, we are going to create a new Blob of type audio/mp3: ` It is time to wire this hook with our AudioRecorder component: ` Let’s go to the other side of the coin, the backend! Setting up our Server side We want to use our models on the server to keep things safe and run faster. Let’s create a new route and add a handler for it using route handlers from Next.js. In our App folder, let’s make an “Api” folder with the following route in it: We want to use our models on the server to keep things safe and run faster. Let’s create a new route and add a handler for it using route handlers from Next.js. In our App folder, let’s make an “Api” folder with the following route in it: ` Our route is called ‘chat’. In the route.ts file, we’ll set up our handler. Let’s start by setting up our OpenAI SDK. ` In this route, we’ll send the audio from the front end as a base64 string. Then, we’ll receive it and turn it into a Buffer object. ` It’s time to use our first model. We want to turn this audio into text and use OpenAI’s Whisper Speech-To-Text model. Whisper needs an audio file to create the text. Since we have a Buffer instead of a file, we’ll use their ‘toFile’ method to convert our audio Buffer into an audio file like this: ` Notice that we specified “mp3”. This is one of the many extensions that the Whisper model can use. You can see the full list of supported extensions here: https://platform.openai.com/docs/api-reference/audio/createTranscription#audio-createtranscription-file Now that our file is ready, let’s pass it to Whisper! Using our OpenAI instance, this is how we will invoke our model: ` That’s it! Now, we can move on to the next step: using Llama 3.1 to interpret this text and give us an answer. We’ll use two methods for this. First, we’ll use ‘ollama’ from the ‘ollama-ai-provider’ package, which lets us use this model with our locally running Ollama. Then, we’ll use ‘generateText’ from the Vercel AI SDK to generate the text. Side note: To make our Ollama run locally, we need to write the following command in the terminal: ` ` Finally, we have our last model: TTS from OpenAI. We want to reply to our user with audio, so this model will be really helpful. It will turn our text into speech: ` The TTS model will turn our response into an audio file. We want to stream this audio back to the user like this: ` And that’s all the whole backend code! Now, back to the frontend to finish wiring everything up. Putting It All Together In our useRecordVoice.tsx hook, let's create a new method that will call our API endpoint. This method will also take the response back and play to the user the audio that we are streaming from the backend. ` Great! Now that we’re getting our streamed response, we need to handle it and play the audio back to the user. We’ll use the AudioContext API for this. This API allows us to store the audio, decode it and play it to the user once it’s ready: ` And that's it! Now the user should hear the audio response on their device. To wrap things up, let's make our app a bit nicer by adding a little loading indicator: ` Conclusion In this blog post, we saw how combining multiple AI models can help us achieve our goals. We learned to run AI models like Llama 3.1 locally and use them in our Next.js app. We also discovered how to send audio to these models and stream back a response, playing the audio back to the user. This is just one of many ways you can use AI—the possibilities are endless. AI models are amazing tools that let us create things that were once hard to achieve with such quality. Thanks for reading; now, it’s your turn to build something amazing with AI! You can find the complete demo on GitHub: AI Assistant with Whisper TTS and Ollama using Next.js...

Sep 27, 2024

8 mins

AINextJSJavaScript

Psychologically Safe Workplaces with Krystal Smith-Moore

Krystal Smith-Moore, Engineering Manager at Spotify, shares her journey from a non-traditional background to management, and how it informs her empathetic leadership approach. Krystal emphasizes the significance of self-awareness, seeking support, and aligning personal values with management roles. By ensuring our values align with the company's mission and culture, we can create a more fulfilling leadership experience. Krystal stresses the need for self-care, setting boundaries to prevent burnout, and recognizing when it's time to recharge. By prioritizing self-care, leaders can maintain their energy and enthusiasm, leading to better decision-making and a more positive work environment. She also discusses the importance of empathy, continuous learning, and creating psychologically safe workplaces where employees feel comfortable expressing their ideas and concerns. By aligning personal values with management roles, prioritizing self-care, and fostering a psychologically safe workplace, leaders can create a positive and impactful experience for themselves and their teams. Download this episode here....

Jun 13, 2024

1 min

Engineering Leadership

Introduction to Zod for Data Validation

As web developers, we're often working with data from external sources like APIs we don't control or user inputs submitted to our backends. We can't always rely on this data to take the form we expect, and we can encounter unexpected errors when it deviates from expectations. But with the Zod library, we can define what our data ought to look like and parse the incoming data against those defined schemas. This lets us work with that data confidently, or to quickly throw an error when it isn't correct. Why use Zod? TypeScript is great for letting us define the shape of our data in our code. It helps us write more correct code the first time around by warning us if we are doing something we shouldn't. But TypeScript can't do everything for us. For example, we can define a variable as a string or a number, but we can't say "a string that starts with user_id_ and is 20 characters long" or "an integer between 1 and 5". There are limits to how much TypeScript can narrow down our data for us. Also, TypeScript is a tool for us developers. When we compile our code, our types are not available to the vanilla JavaScript. JavaScript can't validate that the data we actually use in our code matches what we thought we'd get when we wrote our TypeScript types unless you're willing to manually write code to perform those checks. This is where we can reach for a tool like Zod. With Zod, we can write data schemas. These schemas, in the simplest scenarios, look very much like TypeScript types. But we can do more with Zod than we can with TypeScript alone. Zod schemas let us create additional rules for data parsing and validation. A 20-character string that starts with user_id_? It's z.string().startsWith('user_id_').length(20). An integer between 1 and 5 inclusive? It's z.number().int().gte(1).lte(5). Zod's primitives give us many extra functions to be more specific about *exactly* what data we expect. Unlike TypeScript, Zod schemas aren't removed on compilation to JavaScript—we still have access to them! If our app receives some data, we can verify that it matches the expected shape by passing it to your Zod schema's parse function. You'll either get back your data in exactly the shape you defined in your schema, or Zod will give you an error to tell you what was wrong. Zod schemas aren't a replacement for TypeScript; rather, they are an excellent complement. Once we've defined our Zod schema, it's simple to derive a TypeScript type from it and to use that type as we normally would. But when we really need to be sure our data conforms to the schema, we can always parse the data with our schema for that extra confidence. Defining Data Schemas Zod schemas are the variables that define our expectations for the shape of our data, validate those expectations, and transform the data if necessary to match our desired shape. It's easy to start with simple schemas, and to add complexity as required. Zod provides different functions that represent data structures and related validation options, which can be combined to create larger schemas. In many cases, you'll probably be building a schema for a data object with properties of some primitive type. For example, here's a schema that would validate a JavaScript object representing an order for a pizza: ` Zod provides a number of primitives for defining schemas that line up with JavaScript primitives: string, number, bigint, boolean, date, symbol, undefined, and null. It also includes primitives void, any, unknown, and never for additional typing information. In addition to basic primitives, Zod can define object, array, and other native data structure schemas, as well as schemas for data structures not natively part of JavaScript like tuple and enum. The documentation contains considerable detail on the available data structures and how to use them. Parsing and Validating Data with Schemas With Zod schemas, you're not only telling your program what data should look like; you're also creating the tools to easily verify that the incoming data matches the schema definitions. This is where Zod really shines, as it greatly simplifies the process of validating data like user inputs or third party API responses. Let's say you're writing a website form to register new users. At a minimum, you'll need to make sure the new user's email address is a valid email address. For a password, we'll ask for something at least 8 characters long and including one letter, one number, and one special character. (Yes, this is not really the best way to write strong passwords; but for the sake of showing off how Zod works, we're going with it.) We'll also ask the user to confirm their password by typing it twice. First, let's create a Zod schema to model these inputs: ` So far, this schema is pretty basic. It's only making sure that whatever the user types as an email is an email, and it's checking that the password is at least 8 characters long. But it is *not* checking if password and confirmPassword match, nor checking for the complexity requirements. Let's enhance our schema to fix that! ` By adding refine with a custom validation function, we have been able to verify that the passwords match. If they don't, parsing will give us an error to let us know that the data was invalid. We can also chain refine functions to add checks for our password complexity rules: ` Here we've chained multiple refine functions. You could alternatively use superRefine, which gives you even more fine grained control. Now that we've built out our schema and added refinements for extra validation, we can parse some user inputs. Let's see two test cases: one that's bound to fail, and one that will succeed. ` There are two main ways we can use our schema to validate our data: parse and safeParse. The main difference is that parse will throw an error if validation fails, while safeParse will return an object with a success property of either true or false, and either a data property with your parsed data or an error property with the details of a ZodError explaining why the parsing failed. In the case of our example data, userInput2 will parse just fine and return the data for you to use. But userInput1 will create a ZodError listing all of the ways it has failed validation. ` ` We can use these error messages to communicate to the user how they need to fix their form inputs if validation fails. Each error in the list describes the validation failure and gives us a human readable message to go with it. You'll notice that the validation errors for checking for a valid email and for checking password length have a lot of details, but we've got three items at the end of the error list that don't really tell us anything useful: just a custom error of Invalid input. The first is from our refine checking if the passwords match, and the second two are from our refine functions checking for password complexity (numbers and special characters). Let's modify our refine functions so that these errors are useful! We'll add our own error parameters to customize the message we get back and the path to the data that failed validation. ` Now, our error messages from failures in refine are informative! You can figure out which form fields aren't validating from the path, and then display the messages next to form fields to let the user know how to remedy the error. ` By giving our refine checks a custom path and message, we can make better use of the returned errors. In this case, we can highlight specific problem form fields for the user and give them the message about what is wrong. Integrating with TypeScript Integrating Zod with TypeScript is very easy. Using z.infer<typeof YourSchema> will allow you to avoid writing extra TypeScript types that merely reflect the intent of your Zod schemas. You can create a type from any Zod schema like so: ` Using a TypeScript type derived from a Zod schema does *not* give you any extra level of data validation at the type level beyond what TypeScript is capable of. If you create a type from z.string.min(3).max(20), the TypeScript type will still just be string. And when compiled to JavaScript, even that will be gone! That's why you still need to use parse/safeParse on incoming data to validate it before proceeding as if it really does match your requirements. A common pattern with inferring types from Zod schemas is to use the same name for both. Because the schema is a variable, there's no name conflict if the type uses the same name. However, I find that this can lead to confusing situations when trying to import one or the other—my personal preference is to name the Zod schema with Schema at the end to make it clear which is which. Conclusion Zod is an excellent tool for easily and confidently asserting that the data you're working with is exactly the sort of data you were expecting. It gives us the ability to assert at runtime that we've got what we wanted, and allows us to then craft strategies to handle what happens if that data is wrong. Combined with the ability to infer TypeScript types from Zod schemas, it lets us write and run more reliable code with greater confidence....

Nov 15, 2024

7 mins

JavaScriptZod

D1 SQLite: Writing queries with the D1 Client API

Writing queries with the D1 Client API In the previous post we defined our database schema, got up and running with migrations, and loaded some seed data into our database. In this post we will be working with our new database and seed data. If you want to participate, make sure to follow the steps in the first post. We’ve been taking a minimal approach so far by using only wrangler and sql scripts for our workflow. The D1 Client API has a small surface area. Thanks to the power of SQL, we will have everything we need to construct all types of queries. Before we start writing our queries, let's touch on some important concepts. Prepared statements and parameter binding This is the first section of the docs and it highlights two different ways to write our SQL statements using the client API: prepared and static statements. Best practice is to use prepared statements because they are more performant and prevent SQL injection attacks. So we will write our queries using prepared statements. We need to use parameter binding to build our queries with prepared statements. This is pretty straightforward and there are two variations. By default we add ? ’s to our statement to represent a value to be filled in. The bind method will bind the parameters to each question mark by their index. The first ? is tied to the first parameter in bind, 2nd, etc. I would stick with this most of the time to avoid any confusion. ` I like this second method less as it feels like something I can imagine messing up very innocently. You can add a number directly after a question mark to indicate which number parameter it should be bound to. In this exampl, we reverse the previous binding. ` Reusing prepared statements If we take the first example above and not bind any values we have a statement that can be reused: ` Querying For the purposes of this post we will just build example queries by writing them out directly in our Worker fetch handler. If you are building an app I would recommend building functions or some other abstraction around your queries. select queries Let's write our first query against our data set to get our feet wet. Here’s the initial worker code and a query for all authors: ` We pass our SQL statement into prepare and use the all method to get all the rows. Notice that we are able to pass our types to a generic parameter in all. This allows us to get a fully typed response from our query. We can run our worker with npm run dev and access it at http://localhost:8787 by default. We’ll keep this simple workflow of writing queries and passing them as a json response for inspection in the browser. Opening the page we get our author results. joins Not using an ORM means we have full control over our own destiny. Like anything else though, this has tradeoffs. Let’s look at a query to fetch the list of posts that includes author and tags information. ` Let’s walk through each part of the query and highlight some pros and cons. ` * The query selects all columns from the posts table. * It also selects the name column from the authors table and renames it to author_name. * It aggregates the name column from the tags table into a JSON array. If there are no tags, it returns an empty JSON array. This aggregated result is renamed to tags. ` * The query starts by selecting data from the posts table. * It then joins the authors table to include author information for each post, matching posts to authors using the author_id column in posts and the id column in authors. * Next, it left joins the posts_tags table to include tag associations for each post, ensuring that all posts are included even if they have no tags. * Next, it left joins the tags table to include tag names, matching tags to posts using the tag_id column in posts_tags and the id column in tags. * Finally, group the results by the post id so that all rows with the same post id are combined in a single row SQL provides a lot of power to query our data in interesting ways. JOIN ’s will typically be more performant than performing additional queries.You could just as easily write a simpler version of this query that uses subqueries to fetch post tags and join all the data by hand with JavaScript. This is the nice thing about writing SQL, you’re free to fetch and handle your data how you please. Our results should look similar to this: ` This brings us to our next topic. Marshaling / coercing result data A couple of things we notice about the format of the result data our query provides: Rows are flat. We join the author directly onto the post and prefix its column names with author. ` Using an ORM we might get the data back as a child object: ` Another thing is that our tags data is a JSON string and not a JavaScript array. This means that we will need to parse it ourselves. ` This isn’t the end of the world but it is some more work on our end to coerce the result data into the format that we actually want. This problem is handled in most ORM’s and is their main selling point in my opinion. insert / update / delete Next, let’s write a function that will add a new post to our database. ` There’s a few queries involved in our create post function: * first we create the new post * next we run through the tags and either create or return an existing tag * finally, we add entries to our post_tags join table to associate our new post with the tags assigned We can test our new function by providing post content in query params on our index page and formatting them for our function. ` I gave it a run like this: http://localhost:8787authorId=1&tags=Food%2CReview&title=A+review+of+my+favorite+Italian+restaurant&content=I+got+the+sausage+orchette+and+it+was+amazing.+I+wish+that+instead+of+baby+broccoli+they+used+rapini.+Otherwise+it+was+a+perfect+dish+and+the+vibes+were+great And got a new post with the id 11. UPDATE and DELETE operations are pretty similar to what we’ve seen so far. Most complexity in your queries will be similar to what we’ve seen in the posts query where we want to JOIN or GROUP BY data in various ways. To update the post we can write a query that looks like this: ` COALESCE acts similarly to if we had written a ?? b in JavaScript. If the binded value that we provide is null it will fall back to the default. We can delete our new post with a simple DELETE query: ` Transactions / Batching One thing to note with D1 is that I don’t think the traditional style of SQLite transactions are supported. You can use the db.batch API to achieve similar functionality though. According to the docs: Batched statements are SQL transactions ↗. If a statement in the sequence fails, then an error is returned for that specific statement, and it aborts or rolls back the entire sequence. ` Summary In this post, we've taken a hands-on approach to exploring the D1 Client API, starting with defining our database schema and loading seed data. We then dove into writing queries, covering the basics of prepared statements and parameter binding, before moving on to more complex topics like joins and transactions. We saw how to construct and execute queries to fetch data from our database, including how to handle relationships between tables and marshal result data into a usable format. We also touched on inserting, updating, and deleting data, and how to use transactions to ensure data consistency. By working through these examples, we've gained a solid understanding of how to use the D1 Client API to interact with our database and build robust, data-driven applications....

Dec 23, 2024

6 mins

JavaScript

Let's innovate together!

We're ready to be your trusted technical partners in your digital innovation journey.

Whether it's modernization or custom software solutions, our team of experts can guide you through best practices and how to build scalable, performant software that lasts.

AI Leadership: Data-Driven Decision Making & Avoiding "Analysis Paralysis" with Jerry Reghunadh

You might also like

How to build an AI assistant with OpenAI, Vercel AI SDK, and Ollama with Next.js

Psychologically Safe Workplaces with Krystal Smith-Moore

Introduction to Zod for Data Validation

D1 SQLite: Writing queries with the D1 Client API

Let's innovate together!

You might also like

How to build an AI assistant with OpenAI, Vercel AI SDK, and Ollama with Next.js

Psychologically Safe Workplaces with Krystal Smith-Moore

Introduction to Zod for Data Validation

D1 SQLite: Writing queries with the D1 Client API