What is a vector database and how it works
Powered by embedding models and vector embeddings, Vector databases let you search by meaning and "exact match" keywords. It is the best of both worlds.
Project: Getting website performance score automatically
The problem I have a client who runs a digital marketing agency and works with over 45 doctors. Each doctor has their own website, and the agency is responsible for keeping these websites SEO-friendly and running smoothly. Part of their job is to send each doctor a monthly performance report.
How to create credentials for commonly used Google APIs
Google lets you access all its powerful services by providing an API for each one: 1. Places API (Premium)- Provides detailed information about places (e.g., businesses, landmarks). 2. Custom Search API — Enables developers to add web search and site search capabilities to their websites or create SEO tools
The core components of an API-based HTTP request
Now that you understand how websites, URLs, and APIs work, let's go a level deeper and see what makes up an HTTP request. As I mentioned in the last lesson, every HTTP request consists of six parts: 1. The API endpoint– Where the request is sent 2. The
The purpose of the HTTP protocol
Understanding URLs and Websites We use websites every day and access them using unique URLs, right? For example, we type in the URL https://www.google.com to access Google's website. Similarly, we type in the URL https://www.instagram.com to access Instagram's website. Just
Manually crafting APIs requests using HTTP modules
As you already know, the official apps on Make.com makes it really easy to work with popular services like Google Sheets, Convertio, Airtable, and a ton of other services. But sometimes, you need to work with APIs that don’t have an official app on Make.com. For example,
Delay the next step of the automation using the Sleep module
Sometimes, it's best to delay the next step of an automation rather than executing it immediately. For example, if ChatGPT's analysis determines that an applicant is “Not Recommended,” we should send them a rejection email. But instead of sending the rejection email immediately, we can send
Challenge: Notify HR When an Applicant is a Strong Hire
So far, we’ve built a solid automation: It works well, but we can make it even better! Right now, ChatGPT evaluates resumes and gives a Final Recommendation with one of these four options: 1. Strong Hire 2. Potential Hire 3. Need More Information 4. Not Recommended Now, let’s
Solution: Requesting ChatGPT to respond in JSON Format
The solution to our problem is two-folds: 1. First, Instead of receiving a long text response from ChatGPT, we need ChatGPT to output its analysis in JSON format. 2. Next, we need to force Make.com to parse the structured JSON data produced by ChatGPT and convert that data into
The Problem: Extracting key details from ChatGPT response
In order to understand the problem, we should try to map the key details from ChatGPT’s verdict to the corresponding columns in the Airtable base. But before that, we need to implement the following steps: 1. Add the “Create a Record” module from Airtable at the end of the
Using the capabilities of AI and ChatGPT inside Make.com scenarios
The Agenda Here is the automation we have built so far: 1. Using Tally’s module, we’ve set up a webhook to detect resume submissions. 2. When a resume is submitted, the automation instantly gets triggered and sends the resume file to the Convertio API. 3. Finally, Convertio converts
How to perform file conversion on the fly during an automation run
In the last lesson: 1. With the help of Tally's “Watch New Responses” module, we set up a webhook that listens for form submission events. 2. Once the form is submitted, we receive its details in a bundle, including the file URL of the uploaded resume. If you