Artificial Intelligence and Machine Learning Blogs
Explore AI and ML blogs. Discover use cases, advancements, and the transformative potential of AI for businesses. Stay informed of trends and applications.
cancel
Showing results for 
Search instead for 
Did you mean: 
Sergiu
Contributor
The blog State of GenAI in the SAP Community 09/2023 is a great analysis of the applicability of GenAI. I had the following conversation, which you can find in the comments:

Sergiu: How did you collect statistics for Overview SAP Community Insights from 82 blogs?
Peter: I would love to say I used a sophisticated method like accessing an API or at least did web scraping. But I simply invested one evening to search for the right keywords and another one to manually collect the numbers (likes/views).
Sergiu: I thought you succeeded in giving a set of prompt instructions to ChatGPT Plus to access the web and return the results in CSV or JSON. One day we will get that without coding. 🙂

Open the online application SAP AI Blog Statistics I developed for collecting statistics on the SAP AI Blog. Challenge yourself to achieve the same results with Generative AI without coding or web scraping apps.

Table of content


Web scraping with Generative AI
Online app SAP AI Blog Statistics
Conclusions

Web scraping with Generative AI


Large Language Models (LLM) are an impressive piece of technology. Generative AI applications like ChatOpenAI and MONICA are great copilots for coding. ChatGPT Plus and MONICA Pro have a web access option which is great at summarizing; however, they can’t perform specific tasks like web scraping of statistics.

With the prompt instruction “Collect the number of views,” I received the answer, “As an AI language model, I don’t have access to the exact number of views mentioned in the blog post.”

Have you engineered a prompt to extract statistics of SAP blogs?

Is it possible?

Share the solution in the comments.

Online app SAP AI Blog Statistics


For now, you can collect statistics with Python code. 🐍 😊'

Open the  SAP AI Blog Statistics online application and select one of the options:

Select the list of blogs or upload a list of blogs and press the button extract.

You can download the results in CSV or JSON formats.

Screenshots:


Select an option.




Press Extract and wait for results.
URLs are clickable, and columns are sortable.
Press Download CSV or Download JSON to save Blog Statistics to a local file.

In the GitHub repository LLM-Challenge, you can find the Jupyter Notebook for a playground and the class SapBlogStatistics. This allows you to integrate them into other applications.

Conclusions


Humans designed computer formats and languages to store, process, and transmit the information we perceive naturally. Somehow, we think that from now on,  we can rely on LLMs to achieve any past and future tasks with computers using prompt instructions with texts or images so we never have to type keyboards thousands of line codes, test and debug hundreds of times. How will computer formats and languages evolve without further human contribution?

Have you engineered a prompt to extract statistics of SAP blogs?

Is it possible?

Share the solution in the comments.

What would you prefer for web scraping in terms of efficiency: LLM or apps and code?

 

Why is the web scraping with generative AI important?

I think achieving the extraction of data from specific elements of a web page leads to the next step of inserting data into web forms, which brings us into the territory of web automation with natural language instructions. With one more step of deploying generative AI into an application that interacts with other desktop applications, we can automate the entire workspace with natural language instructions. Discovering the capability of LLMs to work with specific elements could enhance user interaction from multi-screen apps operated by keyboard and mouse to the interaction of apps orchestrated by natural language.

Update on November 09, 2023

Guess what, Bill Gates envisions the following "In the next five years, this will change completely. You won’t have to use different apps for different tasks. You’ll simply tell your device, in everyday language, what you want to do". 🙂

Read the article by Bill Gates  "AI is about to completely change how you use computers".

Enjoy! 🎈🎈🎈

 

Blog series


SAP HANA Cloud Machine Learning Challenge “I quit!” – Understanding metrics

Could machine learning build a model for prime numbers?

“Hello, world!” your crafted chat GPT bot!

SAP Machine Learning Embedding in OpenAI

Building Trust in AI: YouTube Transcript OpenAI Assistant

AI Challenge | Web scraping with Generative AI

 

 

 
3 Comments
pbaumann
Active Contributor
Hi iatco.sergiu ! Nice Idea. Happy that you build on my collection and our talk!

I remember to find the right blogs was a higher effort as you can't rely on tags or key words. Additionally some blogs are... maybe not so useful, depending on what you are looking for. So taking a curated list is still an effort, even if it helps e. g. to collect statistics easily in a regular intervall for looking for developments among other possible usaged.

So or so, cool to see that!
Sergiu
Contributor
Hi Peter,

The list of blogs is continually expanding and time scarcity challenges us humans to find ways to extract what is essential. Tags are also expanding and are assigned subjectively. The ranking reveals where attention is focused and a curated list helps with focusing on what is essential.

Regards,

Sergiu
Sergiu
Contributor

After moving the content from blogs.sap.com to community.sap.com the app is no longer working because the elements for views, likes and comments are unavailable.

Regards,
Sergiu