Workshop Announcement: Using LLMs with ellmer by Hadley Wickham

[This article was first published on R-posts.com, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)


Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.

Join our workshop on Using LLMs with ellmer, which is a part of our workshops for Ukraine series! 

Here’s some more info:

Title: Using LLMs with ellmer

Date: Friday, June 13th, 18:00 – 20:00 CEST (Rome, Berlin, Paris timezone)

Speaker: Hadley Wickham is Chief Scientist at Posit PBC, winner of the 2019 COPSS award, and a member of the R Foundation. He builds tools (both computational and cognitive) to make data science easier, faster, and more fun. His work includes packages for data science (like the tidyverse, which includes ggplot2, dplyr, and tidyr)and principled software development (e.g. roxygen2, testthat, and pkgdown). He is also a writer, educator, and speaker promoting the use of R for data science. Learn more on his website, <http://hadley.nz>.

Description: Join us for an engaging, hands-on hackathon workshop where you’ll learn to use large language models (LLMs) from R with the ellmer (https://ellmer.tidyverse.org) package. In this 2-hour session, we’ll combine theory with practical exercises to help you create AI-driven solutions—no extensive preparation needed!

## What you’ll learn:

– A quick intro to LLMs: what they’re good at and where they struggle

– How to use ellmer with different model providers (OpenAI, Anthropic, Google Gemini, and others)

– Effective prompt design strategies and practical applications for your work

– Function calling: how to let LLMs use R functions for tasks they can’t handle well

– Extracting structured data from text, images, and video using LLMs

## What you’ll need:

– A laptop with R installed

– The development version of ellmer (`pak::pak(“tidyverse/ellmer”))`

– An account with either Claude (cheap) or Google Gemini (free).

Follow the instructions at <github.com/hadley/workshop-llm-hackathon> to get setup.

Minimal registration fee: 20 euro (or 20 USD or 800 UAH)

Please note that the registration confirmation is sent 1 day before the workshop to all registered participants rather than immediately after registration

How can I register?

  • Save your donation receipt (after the donation is processed, there is an option to enter your email address on the website to which the donation receipt is sent)

  • Fill in the registration form, attaching a screenshot of a donation receipt (please attach the screenshot of the donation receipt that was emailed to you rather than the page you see after donation).

If you are not personally interested in attending, you can also contribute by sponsoring a participation of a student, who will then be able to participate for free. If you choose to sponsor a student, all proceeds will also go directly to organisations working in Ukraine. You can either sponsor a particular student or you can leave it up to us so that we can allocate the sponsored place to students who have signed up for the waiting list.

How can I sponsor a student?

  • Save your donation receipt (after the donation is processed, there is an option to enter your email address on the website to which the donation receipt is sent)

  • Fill in the sponsorship form, attaching the screenshot of the donation receipt (please attach the screenshot of the donation receipt that was emailed to you rather than the page you see after the donation). You can indicate whether you want to sponsor a particular student or we can allocate this spot ourselves to the students from the waiting list. You can also indicate whether you prefer us to prioritize students from developing countries when assigning place(s) that you sponsored.

If you are a university student and cannot afford the registration fee, you can also sign up for the waiting list here. (Note that you are not guaranteed to participate by signing up for the waiting list).

You can also find more information about this workshop series,  a schedule of our future workshops as well as a list of our past workshops which you can get the recordings & materials here.

Looking forward to seeing you during the workshop!

 


Using LLMs with ellmer workshop by Hadley Wickham was first posted on May 13, 2025 at 3:06 pm.

To leave a comment for the author, please follow the link and comment on their blog: R-posts.com.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you’re looking to post or find an R/data-science job.


Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.

Continue reading: Using LLMs with ellmer workshop by Hadley Wickham

Analysis: The Future of LLMs with ellmer Workshops

In the ever-evolving field of data science, continuous learning and keeping up-to-date with the latest technologies and methodologies are of utmost importance. A recent announcement on R-bloggers.com discussed a fast-approaching online workshop on ‘Using LLMs with ellmer’ which undoubtedly caught the attention of many data science enthusiasts.

Implications and Future Developments

Large Language Models (LLMs), as introduced in this workshop, are a critical component in the realm of AI, capable of understanding and generating human-like text. Notably, the ellmer package enables these advanced AI capabilities to be integrated into the R environment. Ensuring that data scientists are adept in such tools has long-term implications for the speed, efficiency, and novel applications in data science.

Hadley Wickham, the speaker for this session, is a distinguished data scientist and prolific contributor to R packages, making the promise of future workshops held by him or speakers of a similar calibre, highly beneficial for learners. It’s quite plausible that the increased demand for these workshops could lead them to become a regular occurrence, facilitating upskilling in the R community.

In the future, we might see an expansion of topics, covering more R packages and advanced AI techniques. Furthermore, the flexible approach today’s workshop adopted towards payment (acceptable in different currencies and also by sponsoring a student) combined with its charitable cause, paints an encouraging picture of an inclusive learning community that values diversity and social responsibility. This could lead to increased accessibility in the future, as more and more professionals and students benefit from these affordable (or sponsored) learning opportunities.

Actionable Advice

  1. Stay Informed: Regularly check R-bloggers and similar resources for updates about forthcoming workshops and apply promptly. Remember that registration confirmations are sent out a day before the workshop.
  2. Prepare Adequately: Ensuring that the necessary prerequisites are met before the workshop (such as having R installed and setting up the ellmer package) allows for a more effective learning experience.
  3. Be Charitable: If able, consider sponsoring a student. This not only supports the learning of individuals unable to afford the fee, but additionally contributes towards addressing social implications in areas such as Ukraine.
  4. Take Part: Even if one is not an R user, such workshops, often held by industry experts, offer valuable insights which could be applied to data science work in general.

By utilizing such actionable advice, not only can individuals further their personal knowledge and skills, but the broader R, data science, and AI communities can continue to grow and evolve positively.

Read the original article

“Data Centres: A Growing Contributor to Global Electricity Consumption”

As technology continues to evolve and our dependence on digital infrastructure grows, data centres have become a critical component of our modern society. However, the massive amounts of electricity required to power and cool these facilities have raised concerns about their environmental impact. According to a recent report, data centres accounted for approximately 1.5% of global electricity consumption in 2024 (Nature). This staggering statistic highlights the urgent need for the industry to explore more sustainable practices and embrace future trends that can help mitigate their carbon footprint.

The Rise of Renewable Energy

One clear trend that we can expect to see in the future is the increased adoption of renewable energy sources to power data centres. As the urgency to combat climate change grows, governments and businesses are recognizing the importance of transitioning to clean energy alternatives. Renewable energy technologies such as solar, wind, and hydroelectric power offer a reliable and sustainable solution for data centres.

In recent years, we have already witnessed prominent tech companies and data centre operators investing in renewable energy projects. For instance, Google has pledged to reach 100% renewable energy for its global operations, including data centres (Google Sustainability). This commitment not only helps reduce their environmental impact but also provides an opportunity for the industry to lead by example and inspire others to follow suit.

Improving Energy Efficiency

Another crucial aspect of future trends for data centres is the continuous pursuit of energy efficiency. With power consumption being a significant contributor to their environmental footprint, data centre operators are investing in innovative solutions to optimize energy usage and reduce waste.

Advanced cooling technologies, such as liquid cooling, are gaining traction as they can significantly improve energy efficiency compared to traditional air-cooling methods. Furthermore, implementing intelligent software systems and artificial intelligence algorithms can help optimize workload distribution and resource utilization, ultimately reducing overall energy consumption.

The Advent of Edge Computing

Edge computing is poised to revolutionize the data centre industry by bringing computation closer to the source of data generation. Instead of transmitting vast amounts of data to centralized data centres, edge computing allows for processing and storage to occur directly on the devices or at the edge of the network, reducing the need for extensive data infrastructure.

This trend has the potential to lower the overall energy requirements of data centres, as fewer resources will be needed for long-distance data transmission. As the Internet of Things (IoT) continues to expand, edge computing can play a vital role in managing and processing the massive volumes of data generated by billions of connected devices.

Recommendations for the Industry

  1. Invest in renewable energy: Data centre operators should prioritize the adoption of renewable energy sources to power their facilities. Collaborating with energy providers, governments, and clean energy advocates can help accelerate the transition to sustainable energy.
  2. Implement energy-efficient practices: By investing in advanced cooling technologies and optimizing resource utilization, data centres can significantly improve their energy efficiency. This includes exploring innovative solutions such as liquid cooling and leveraging artificial intelligence for workload management.
  3. Embrace edge computing: As the industry moves towards edge computing, data centre operators should adapt their infrastructure to support this trend. This involves developing edge data centres and investing in robust network infrastructure at the edge to facilitate efficient data processing and storage.
  4. Educate and raise awareness: It is crucial for the industry to actively educate the public and stakeholders about the environmental impact of data centres and the steps being taken to mitigate it. Spreading awareness and promoting sustainable practices can inspire change and encourage others to follow suit.

In conclusion, the future trends for data centres revolve around sustainability and efficiency. The adoption of renewable energy, continuous improvements in energy efficiency, and the rise of edge computing are key factors that will shape the industry in the coming years. By embracing these trends and implementing the recommended practices, the data centre industry can pave the way towards a more sustainable and environmentally conscious future.

References:
Nature, Published online: 10 April 2025; doi:10.1038/d41586-025-01113-z
Google Sustainability. (n.d.). Responsible Operations: Renewable Energy. Retrieved from https://sustainability.google/responsible-operations/renewable-energy/

“From Novice to Contributor: Supporting First-Time Contributions to FOSS”

“From Novice to Contributor: Supporting First-Time Contributions to FOSS”

[This article was first published on rOpenSci – open tools for open science, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)


Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.

This week we had a wonderful community call, From Novice to Contributor: Making and Supporting First-Time Contributions to FOSS, where Sunny Tseng, Pascal Burkhard, and Yaoxiang Li shared with us their experiences with, and advice for, first time contributors, with the excellent moderation of Hugo Gruson.
This was a perfect start to our special series of activities to support first time contributors to Open Source Software.

Our next two activities, Coworking Mini-Hackathons for First-Time Contributors, will take place February 4th 2025 1-3 UTC and March 4th 2025 13-15 UTC (see below for details), but first, let’s review what we learned from this Community Call.

Community call

Our three panellists each shared different experiences and perspectives on making contributions to open source software.
Sunny and Pascal shared their experiences with getting involved, Pascal and Yaoxiang shared technical tips for git and testing, and all three offered advice for first time contributors.

Sunny focused on her journey making her first R package, bbsTaiwan as part of the rOpenSci Champions Program and Pascal shared his experiences as a first time contributor to the babelquarto package after being a long-time solo user of git.
Then Yaoxiang rounded out our call with advice for first-time contributors on the importance of including tests and how to deal with different testing situations, referring to his experience with medrxivr.

Sunny recommended that you have a plan for your contributions, but remain flexible as things change or don’t proceed as you may have expected.
Both Sunny and Pascal pointed out that they found git to be less scary than they expected once they got started, and that they learned so much while collaborating with others.
Among other technical suggestions, Pascal and Yaoxiang both commented that starting small and using good descriptions can be really helpful, whether for git commit messages or code tests.

Mini-hackathons

Hopefully this community call has inspired you to get involved open source software.
If you’re curious about contributing to Open Source Software, and would like some support to get started, our coworking mini-hackathons are for you!

We’ll be hosting two events, the first on February 4th 2025 1-3 UTC and the second on March 4th 2025 13-15 UTC.

During these session you’ll join others making contributions to R packages while package maintainers and other mentors are available ’live’ to answer questions and give guidance.

We’ll also have a special Slack channel ready as a place for asynchronous questions during the event and in the week following.

These collaborative events are designed to help first-time contributors get started with open-source projects.
Whether you’re improving documentation, reviewing translations, fixing bugs, or adding new features, our mentors will guide you every step of the way.

No prior experience required. Non-first time contributors are very welcome too—just bring your curiosity and enthusiasm!

Note that this event requires registration.
Please fill out this short form to sign up.

We’ll send out reminders, some information to get you started, and a Zoom link closer to the date.

Resources

To leave a comment for the author, please follow the link and comment on their blog: rOpenSci – open tools for open science.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you’re looking to post or find an R/data-science job.


Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.

Continue reading: Coworking Mini-Hackathon for First-Time Contributors

The Future of Open Source Contributions: Insights from the FOSS Community Call

In a recent webinar themed “From Novice to Contributor: Making and Supporting First-Time Contributions to FOSS,” industry experts Sunny Tseng, Pascal Burkhard, and Yaoxiang Li shared their first-hand experiences and advice for novice contributors. The session, moderated by Hugo Gruson, served as the opening of a series of activities to support first-time contributors to Open Source Software and offers valuable insights on the future of open source contributions.

Key Takeaways and Future Implications

During the call, the panellists each shared unique experiences and perspectives, extending valuable advice to newcomers in the field. The first-time contributors offered their candid insights that could essentially drive the future development of the open-source ecosystem.

Focus on Improving Skills

Sunny discussed the importance of planning while also staying versatile as things may not always go as expected. She reiterated the need for new contributors to develop their skills, something she learned while creating her first R package, which fosters a culture of continuous learning in the open source industry.

Collaboration and User-friendly Tools

Pascal’s experiences underlined the importance of collaboration in open source projects, suggesting that the future of open source contributions could involve more collaborative efforts. He stressed the benefit of user-friendly tools like git, which he found to be less intimidating than anticipated and incredibly helpful for collaborations.

Technical Expertise and Descriptive Communication

Yaoxiang advocated the importance of including tests and dealing in diverse testing situations, using his experiences with medrxivr as an example. His advice hints at the importance of technical prowess in successful open source contributions. Both Pascal and Yaoxiang also emphasized the value of detailed and descriptive communication, whether for commit messages or code tests. This could influence the culture of open communication and diligence in open source contributions.

Long-Term Implications and Future Developments

The trends mentioned above suggest that the open-source community continues to evolve towards inclusivity, collaboration, technical mastery, and transparent communication. The field will likely become more welcoming for first-time contributors, continuously facilitate skill growth, encourage collaboration, and promote diligent, descriptive communication.

Actionable Advice for Future Contributors

  • Plan your contributions but remain adaptable as situations may change
  • Take advantage of user-friendly tools like git for collaboration.
  • Utilize descriptive communication in your contributions, whether for commit messages or code tests.
  • Do not overlook the significance of technical skills, especially for conducting tests.

Looking Forward: Coworking Mini-Hackathons for First-Time Contributors

rOpenSci is hosting Coworking Mini-Hackathons for First-Time Contributors in February and March of 2025. These events are a great opportunity for novice contributors to learn and explore the world of open source. They can get hands-on experience, benefit from live mentors, and connect with a supportive community. The move towards such inclusive events further highlights the future development of the open-source world – that of embracing first-time contributors and providing them with the necessary support.

Final Thoughts

The open-source community is heading towards a more inclusive and collaborative future. The insights shared by Sunny, Pascal, and Yaoxiang are not only inspiring for novices but also indicate the direction in which open-source contributions are moving. By offering ample support to first-time contributors, we can foster a richer and more diverse community, driving innovation and technological advancements.

Read the original article