Skip to main content

Gen AI can be utilized to build useful things. In this post, you will build an e-commerce product description generator using Google’s Gemini Pro vision LLM over Vertex AI on the Google Cloud Platform (GCP). Let’s get started!

How to create an e-commerce product description generator using Gemini and Vertex AI with Python code example

Table of contents #

Process of writing product descriptions for e-commerce websites #

Before you get your hands dirty with Vertex AI and some code, let’s understand the process of wiring product descriptions for any product shown on an e-commerce website. Models are scheduled to take photographs wearing the products, every product is photographed in a photo studio.

Then a copywriter has a look at the retouched photographs possibly with the product by the side and writes a product description that you see on the website. It is a long process and if the website has hundreds of products going online each day it can be a labor-intensive, time-consuming, and error-prone process as it is mostly manual. It can be summed up visually as:

The general process of writing product descripitons

Now, imagine you have a system where you can upload pictures and prompt the system to get the product description for that particular product. The generated product descriptions will not be perfect but it will get you (or the copywriter) 80% of the way. That is what you are doing to build in this tutorial.

To do this you will use the Gemini Pro LLM over Vertex AI, you will also get the basic code that can be deployed as a service. You can find some more context in these slides. In the next section, you will learn about the prerequisites to build the e-commerce product description generator.

Prerequisites #

To begin, you will need to have the following pre-requisites sorted:

  • Have a working Google Cloud account (with some credit)
  • Download this zip file on your machine, for the product images. Please decompress it after downloading.

Also, be aware of the Vertex AI and Gemini Pricing as well.

Next, you will create a GCP project to build your e-commerce product description generator. You might need 20-30 minutes to create the basic product description generator and have a proof of concept code for it as shown below.

Vertex AI on GCP #

Below are the steps to create a new GCP project (if you have an existing one you can use that too).

  1. Go to your Google Cloud Console and Create a new project called gemini-ecomm or anything relevant as seen below:
Create a new GCP Project
  1. Make sure you have selected the project created in Step 1 if you have multiple projects.

  2. Go to Vertex AI from your Google Cloud Console, the easiest way to do it would be to search for vertex on the search bar as seen below:

Search vertex on GCP console
  1. Click on Vertex AI

  2. On the Vertex AI page, then "Enable all recommended APIs" as seen below (it will take some time):

Enable all related Vertex AI APIs
  1. After the APIs are enabled, click on Multimodal found on the left menu
Click on Multimodal on Vertex AI page
  1. On the Multimodal page, click Open on the "Prompt design (single turn)" box as follows:
Click on Open for Prompt design (Single Turn)

Prompting #

  1. On the Prompt experiment page, please make sure you have the gemini-1.0-pro-vision-001 model selected. Then, paste the following prompt in the Prompt text box:
As an expert e-commerce copywriter, analyze the uploaded images of
women's jeans and write a product description for a low to mid-end 
fashion e-commerce website. Please include the details about the 
comfortable to wear jeans and do not include any details about the 
price. Make sure that the copy is written in an engaging and friendly tone.
  1. Then upload the images you find in the repository or the images folder of the unzipped file. Navigate to womens-jeans-photos folder after clicking the Insert Media option on the right side of the Prompt textbox. Then upload all Once all the 8 images, it will look something like the below:
The prompt with the images upload
  1. After that hit the Submit button to test out the prompt with the uploaded images, you should get a response similar to the following:
The response to the prompt with product description

Name and save the prompt #

  1. At this point, it would be a good idea to save your prompt (with images). To do this, click the pen icon beside Untitled prompt above the prompt text box, then type e-commerce-product-desc-generator the click anywhere, it will look like the below while editing:
Name the prompt
  1. As you have named the prompt, you can save it. To save the prompt click Save on the top left part of the right sidebar as shown below:
Save button for the prompt
  1. Then, select the region (it is ok to choose us-central1) on the overlay window and save the prompt.
Save the prompt selecting a region

All saved prompts will be accessible in your My Prompts page.

Save the prompt selecting a region
  1. Hurray! The basic e-commerce product description generator is working. Now, you will change some settings to make it better. You can go back to the prompt editing page by clicking the Prompt Name if you are on the My Prompts page.

Gemini configurations #

  1. In terms of configurations, for Gemini 1.0 pro vision there are 4 options you can configure. Those four are explained in plain words below:
  • Temperature (Randomness/Creativity/Spice): Imagine a roulette wheel (randomness). A high temperature increases the spin's randomness, affecting the chosen word (output).

  • Output Token Limit (Length): This is like a set word limit (length) for your text. It controls how many words the LLM generates in total.

  • Top K (Choice): Think of this as picking from a shortlist (choice) of the most likely words. A lower K restricts the options for the next word.

  • Top P (Probability): This is like a probability wheel (probability). It influences the LLM to pick the next word based on its likelihood (probability), not just being the most likely.

Below is a configuration you can try out, the right settings for this configuration depend on how you want the output to be shaped by Gemini:

4 configs for the Gemini pro vision LLM
  1. It is also important to set up the Safety Settings correctly as per your use case, for now, we will set it at maximum safety (Responsible AI). As seen below, the safety settings (found on the right sidebar are self-explanatory)
Gemini safety settings
  1. You can also tweak the prompt text to make it better, below is another version of the prompt:
As an expert e-commerce copywriter, analyze the uploaded images of women's
jeans and write a product description for a low to mid-end fashion e-commerce
website. Please include the details about the comfortable to wear clothing and
do not include any details about the price. Make sure that the copy is written
in an engaging and direct tone.

You can play around with the prompt and make it more flexible or more specific as per your goals.

The next step will involve some code.

Run generated Python Code #

  1. If you want to create an API for the e-commerce description generator or want to have more control over what the LLM is called, you can generate code and run it on a Google Cloud Platform service like Google Cloud Run. To generate code, click the <> Get Code link which shows a slider on the right side as follows:
Get code for your Gemini experiment

For this workshop, you will use the Node.js code and try it out. For that, you will use Cloud Shell and Cloud Shell Editor.

  1. Click Activate Cloud Shell toward the top right corner of the screen as seen below:
Activate Cloud Shell
  1. In the Cloud shell window, click Open Editor:
Open editor
  1. This will take some time and open up the Google Cloud Shell Editor which looks very similar to VS Code. In the Editor click Hamburger Menu > Terminal > New Terminal as follows:
Open terminal in editor
  1. In the editor's terminal, execute mkdir projects && cd projects && mkdir gemini-workshop && cd gemini-workshop and then pip3 install --upgrade google-cloud-aiplatform :
Commands executed
  1. After the vertex AI Python package is installed it will look like the below:
Install Vertex AI Python package
  1. After that you will load the folder in the project, go to Hamburger Menu > File > Open Folder:
Load project to Cloud shell editor
  1. Then type in projects/gem and select the gemini-workshop option and click OK:
Select the right folder
  1. It will load the folder on the Cloud Shell editor, after that, to add a new file click the file+ icon beside GEMINI-WORKSHOP and name it
Create the file
  1. For the contents of the, click <>GET CODE on the Vertex AI Editor screen, while on the Python option copy the code into a file called
Get Python code for e-commerce descripiton generator
  1. Paste the code in the empty file and save it:
Paste copied code
  1. To run the code and test it out, again open the terminal from Hamburger Menu > Terminal > New Terminal and type in python then hit enter. It will ask you to Authorise:
Authorize the execution

After authorisation, the code will run and give an output like the below:

See the generated product description

Congrats! You are a Gemini and Vertex AI novice now :). You can close the Cloud Shell Editor. Even shut down/delete the project if you like.

What's next #

  1. Further steps

The generated code is more like a proof of concept. You can add an API layer and UI on top of it to make it more useful. You can deploy that API on Google Cloud Run as serverless containers.

For instance below is a basic UI generated with v0 with the prompt:

An internal tool for e-commerce websites to generate product descriptions,
it will have a product name text box, multi-file upload field, category
select box with clothes, shoes, accessory options, gender select box
with male, female, and unisex options and age select box with infants,
kids, teens, and adults options. Then a button that says Generate.

The UI is below:

Example UI generated by V0 for the product description generator
  1. It would be good idea to read more about LLMs in general and also about Gemini. You can also do courses or code labs about Gemini on Cloud Skills boost platform.

Congrats! You have successfully built and tested a general purpose e-commrece product description generator. You can also crate a text or URL's text summarizer using Gemini over Vertex AI.

Conclusion #

In this blog post, you embarked on a journey to build a basic e-commerce product description generator using Google's Gemini API over Vertex AI on GCP.

You started by creating a prompt that captures the essence of what we wanted the generator to achieve. Towards the end you create a proof of concept script with Python that can be converted into a standalone internal application.

Whether you're an e-commerce entrepreneur, a content creator, or simply someone interested in the future of AI, LLMs have the potential to revolutionize the way we work and create.

So, embrace the excitement, experiment with different prompts and configurations, and see what amazing results you can achieve with the help of Google's Gemini API.

The future of better productivity is here, and it's powered by AI!


Latest Posts

Side Projects


Join the Newsletter

Receive exclusive content and links about software engineering and web development every month.

    We hate spam as much as you do. Unsubscribe at any time.