Connect with us


Build Your Own SEO AnswerBox With GPT-3 Codex & Streamlit



Build Your Own SEO AnswerBox With GPT-3 Codex & Streamlit

Google has integrated a new method of querying data in GA4 whereby you simply type a question or a phrase, and it creates the dashboard.

Imagine if you could do the same with your own SEO data – what would that do for your productivity?

In this article, you’ll learn how to configure your own dashboards using phrases and questions, creating an AnswerBox of your own with GPT-3 Codex and Streamlit.

Google’s Answer Box

In Google Analytics v4, you’ve probably noticed a clever search bar that allows you to get:

  • Instant answers.
  • Reports.
  • Answers on configuration.
  • Help.

Instant answers are particularly useful. By asking questions about your data, you get answers and – most importantly – ready-to-use reports.

There’s nothing magical about it. This technology relies on natural language processing (NLP), so you have to be precise about metrics, dimensions, and timing when asking for an answer.

For example, you can search for [conversions last week from the United States] and see the results in the search panel that appears on the right.

Screenshot from Google Analytics v4, February 2022

This new way of using a data visualization tool is incredibly powerful and will surely be integrated into all solutions of this type.

The time savings for the user are impressive, as users don’t have to search through all the views of the tool and no longer have to configure the view.


Everything is done automatically based on the instructions provided in the search box.

Can we easily do the same thing? And which data should we use?

Smart SEO Dashboard

Before requesting a report, you need to think about the important data to be taken into account.

I suggest you look into the concept of the Smart SEO Dashboard.

  • The first requirement is to keep the graphs simple and specific. Less is always more.
  • Next, the abscissa or ordinates must refer to measurable data. Otherwise, it is impossible to see the evolution.
  • In addition, graphs must focus on meaningful parameters. It is useless to monitor parameters that will have no influence on your activity. Weather is an excellent example: it plays a crucial role on some sites and none on others.
  • Dashboards should always include relevant summaries in order to be quickly read and understood. Generally speaking, if it takes more than three seconds to understand a dashboard, it can definitely be improved.
  • Finally, the most important data is time. It is imperative to track time data by comparing each day, month, year, etc.

Now, you need to identify the best technology to generate this type of dashboard.

GPT-3 Codex

GPT-3 Codex is a computer code generator that was created in August 2021.

Access to GPT-3 Codex was given much faster than access to GPT-3.

Not surprisingly, GPT-3 Codex has been fed millions of quality source codes available on GitHub – that is, more than 54 million GitHub repositories.

Like GPT-3, it is a sophisticated neural network that is capable of self-learning.


GPT-3 Codex does not only work in Python. You can also generate code in Go, Javascript, Perl, and PHP.

On the other hand, GPT-3 Codex has only 12 billion parameters, unlike its big brother GPT-3 Da Vinci which has 175 billion.

Let’s take a closer look at this size-versus-cost ratio.

OpenAI’s experiments show that the size-versus-performance ratio of Codex follows a logarithmic scale.

This means that the performance gains gradually decrease as the size of the model increases.

Therefore, the additional costs of collecting data, training, and running a larger model are not at all worth the slight increase in performance.

All of these reasons explain why the model has only 12 billion parameters for its first version.

We’ve found an AI to generate the code.


Now let’s look for the best framework available at the moment to execute it all in a friendly interface with clicks and drag-and-drop.


Streamlit is an open source technology that allows you to quickly build very advanced user interfaces.

Streamlit also includes many very useful components to have even more interactions like:

  • Session management.
  • Password management.
  • User management.

The community is particularly active and shares many handy custom modules for SEO.

To start, we’ll use GPT-3 Codex to generate graphs with Streamlit, and then attempt to produce a Streamlit app that generates the code and runs it automatically.

Two Excellent Examples For Querying The Data

First, we need to generate an app for Streamlit and run it.

1. With OpenAI (Semi-Automatic)

The first thing to generate is a Streamlit web app that retrieves all the logs from the month of May 1995 from NASA and displays the number of URLs crawled per day.

First of all, we need to retrieve the CSV file by specifying the name of the columns and the format if necessary.


For our example, it is important that the date is in UTC format.

Then you can ask OpenAI to display the graph of your choice, once it has understood your data.

how to configure using OpenAIScreenshot from OpenAI, February 2022

From these instructions, you will have a working code.

Remember that we don’t want to copy and paste code, but drive everything through English instructions with a no-code approach.

2. With Streamlit (Full Automatic)

Here is an open source example based on one of Streamlit’s applications.

It is an app directly connected to GPT-3 Codex that generates computer code and allows you to execute it.

With Charly Wargnier, we did the same thing but for SEO use cases in an app called “Codex for SEO”.

In one click, you can import your data.


Then, you can describe the content of the imported file: What are the columns? What are the data types?

data analysis script in codex for seoScreenshot from Codex For SEO, February 2022

Then you specify your instructions.

In our example, we ask it to group the queries together and to sum the clicks and impressions.

We’ll tell it to keep only the columns we’re interested in (the Queries and Clicks columns), and then click the Execute button.

No line of code is needed to get the results, and everything is generated by the OpenAI Codex and executed by Streamlit.

Our proof of concept is therefore validated with many different use cases.

Moreover, if you need assistance, everything you need for this is accessible via a training program with 150 minutes of video.

results from codex for seo scriptScreenshot from Codex For SEO, February 2022

For educational and transparency reasons, we have provided the generated code as well as the results.

And with that, the SEO AnswerBox is now available for everyone to create!

More resources:


Featured Image: NicoElNino/Shutterstock

Source link



Link relevancy trumps volume for SEO



Data speaks Link relevancy trumps volume for SEO

30-second summary:

  • Earned media coverage is more valuable than ever for your website
  • Digital PR is just as important as technical SEO
  • A large volume of links is the goal, what’s stopping someone from picking the most newsworthy idea, even if it has nothing to do with your client?

In 2022, it’s impossible to deny the benefit that digital PR as a tactic has on an organic growth strategy. Earned media coverage is more valuable than ever for your website. You could be doing everything right for SEO, but if you’re not building links, you’re still missing out on the increased search visibility, organic traffic, and brand awareness that backlinks bring to your business.

Last year, Google’s John Mueller finally weighed in on digital PR as a tactic and confirmed what we’ve all known for a while now: that it’s just as important — if not more — as technical SEO.

As digital PR is still a relatively “young industry” that’s only just sprouted up in the past 10 years, many PR pros have relied on “viral” campaigns to boost the backlink portfolio of their clients. These viral campaigns are often celebrated but are often created with little regard to how relevant, or “on-brand” those ideas really are.

After all, if a large volume of links is the goal, what’s stopping someone from picking the most newsworthy idea, even if it has nothing to do with your client?

In 2022, link volume is no longer the goal (or shouldn’t be)

While many PR pros’ were evaluating their success around this one key metric (link volume) others in the industry have suspected for a while now that the relevance of linking coverage is a key factor Google looks at when assigning “value” to links.

Once again, John Mueller has settled the debate about link volume vs link relevance,  coming out in 2021 and saying that ‘the total number of links’ doesn’t matter at all.


This clarity has helped refocus the digital PR industry and forced PR pros to re-evaluate what metrics and KPIs we need to be focusing on to drive true organic growth.

It’s no longer enough to be ‘popular’ you also need to be relevant. Not just in terms of the publications you are targeting, but the keywords you want to rank for,  audience interest, and most importantly, brand alignment to the story you are pitching in.

Google is continuously looking to become more intelligent through its use of machine learning and artificial intelligence. It wants to understand web content as a human, and therefore through its use of natural language understanding, it is likely to not just be looking at the anchor text of links in third-party articles, but it is also wanting to understand the wider context of the article that a brand is placed in.

How to ensure your link-building activity is relevant to your brand

The first steps to coming up with relevant content ideas for your digital PR campaign are to:

  1.  understand your client, and
  2.  understand your client’s audience and their needs.

Every good idea will flow from these two pillars.

If Google’s main objective is to show the best content to users through search, then your job is to create content that either supports your client’s product or service or supports their customers.

It is more important than ever to not only create relevant and on-brand content in the written form but also ensure that any supporting assets created (video, images, audio) are also relevant to the target keywords and services or products that the brand sells.


In addition, it’s important to create content that engages people, to drive further buzz and positive sentiment around the brand, all of which contribute to greater brand awareness and affinity among your potential customers.

How to measure the relevancy of your backlink profile

We now have the technology available to us to be able to understand and assign quantifiable metrics to the relevance of linking coverage (or indeed the relevance of any text-based content) – which allows us to be much more data-driven and targeted when developing digital PR, link creation activity and competitor and marketplace analysis.

For example, natural language understanding tools like Salient, measure the relevancy of both off-page and on-page content. Tools like this help to understand how a search engine is viewing a brand’s content, it not only enables us to identify the gaps in our client’s backlink profile.

At Journey Further, we use this proprietary tool to measure the relevancy of both off-page and on-page content for our clients.

Measuring the relevancy of your backlink profile

We can use this tool to understand how a search engine is viewing a brand’s content, it not only enables us to identify the gaps in our client’s backlink profile but also aids us in optimizing its content on-site. The outcome of which – is a much more focused, effective, and measurable digital PR activity that is better aligned to SEO objectives and that delivers better ROI for clients.

Looking ahead to 2023

Looking ahead to 2023 and beyond, it’s likely that Google will only continue to develop better technology to understand web content.

All digital PR campaigns should reflect this, and where possible, be multi-faceted, not just relying on a single press release to get cut through. We need to be thinking as marketers, not just SEO practitioners, and ensure we are driving as much ROI as possible. Taking a brand plus performance approach to SEO and digital PR will therefore be key.

Beth Nunnington is the VP of Digital PR and Content Marketing at Journey Further, leading Digital PR strategy for the world’s leading brands. Her work has been featured in The Drum, PR Moment, and Prolific North. Find Beth on Twitter @BethNunnington.


Subscribe to the Search Engine Watch newsletter for insights on SEO, the search landscape, search marketing, digital marketing, leadership, podcasts, and more.

Join the conversation with us on LinkedIn and Twitter.

Source link

Continue Reading

Subscribe To our Newsletter
We promise not to spam you. Unsubscribe at any time.
Invalid email address