ellmer is an R package for working with large language models from multiple providers including OpenAI, Anthropic, Google, AWS, Azure, and many others. It provides a unified interface for chat-based interactions with LLMs, supporting streaming outputs, tool calling, and structured data extraction.
The package uses stateful R6 objects that maintain conversation context across multiple queries, making it straightforward to build interactive chat applications or programmatic workflows. It handles authentication automatically for major cloud providers and offers flexible interaction modes—from interactive console chat sessions to capturing responses as strings for downstream processing. Key features include support for multimodal inputs (text and images), control over streaming behavior, and integration with other Posit LLM tools for RAG, evaluation, and chatbot interfaces.
Contributors#
Events featuring ellmer#
Resources featuring ellmer#
Data analysis with Posit AI-assistants | Sara Altman & Simon Couch | Data Science Lab
The Data Science Lab is a live weekly call. Register at pos.it/dslab! Discord invites go out each week on lives calls. We’d love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Sara Altman who walks through using Posit’s AI assistants to analyze data, including a sneak peek at Posit Assistant, and Simon Couch drops by to give us a demo of the reviewer package! Together, Sara and Simon author the Posit AI Newsletter, the best place to stay up-to-date with all the cool tools and advice on staying an informed and level-headed AI user.
Hosting crew from Posit: Libby Heeren, Isabella Velasquez, Sara Altman, Simon Couch
Sara’s Bluesky: https://bsky.app/profile/sara-altman.bsky.social Sara’s LinkedIn: https://www.linkedin.com/in/sarakaltman/ Sara’s GitHub: https://github.com/skaltman Posit AI Newsletter by Sara and Simon: https://posit.co/blog/?category=roundups
Resources from the hosts and chat:
Positron IDE → https://positron.posit.co/ Databot Extension → https://positron.posit.co/databot.html Getting started with Positron Assistant → https://positron.posit.co/assistant-getting-started.html Posit Assistant (Private Beta) → https://posit-ai-beta.share.connect.posit.cloud/ Reviewer Package (by Simon Couch) → https://github.com/simonpcouch/reviewer ellmer Package → https://elmer.tidyverse.org/ chatlas Package → https://github.com/posit-dev/chatlas Read the Posit AI Newsletter → https://posit.co/blog/?category=roundups Sign up to get the Posit AI Newsletter → http://pos.it/ai-news Simon’s blog post about local LLMs not quite being ready for primetime → https://posit.co/blog/local-models-are-not-there-yet/ Join the waitlist for Posit AI in RStudio → https://posit.co/products/ai/ Posit AI Known Issues & FAQs → https://posit-ai-beta.share.connect.posit.cloud/#frequently-asked-questions-faqs Blog post from Simon and Sara about Privacy and LLMs → https://posit.co/blog/trust-llm-tools/ DS Lab YouTube playlist → https://youtube.com/playlist?list=PL9HYL-VRX0oSeWeMEGQt0id7adYQXebhT&si=7tmU6EAJpO5S7GBh
► Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here: Website: https://www.posit.co The Lab: https://pos.it/dslab Hangout: https://pos.it/dsh LinkedIn: https://www.linkedin.com/company/posit-software Bluesky: https://bsky.app/profile/posit.co
Thanks for learning with us!
Timestamps 00:00 Introduction 07:23 “Would you mind real quick just briefly explaining the differences between Positron Assistant and Databot?” 15:01 “Is there any way to configure reasoning efforts when signing in with GitHub Copilot?” 15:49 “Does DataBot already support other providers beyond Cloud?” 20:36 “What is the cases with monetary penalty in the console output?” 22:14 “Do you happen to know if the column names of the dataset are very, very messy?” 23:18 “Can you add skills to DataBot?” 26:36 “This code isn’t being saved anywhere. So where does it go?” 27:38 “There a way to know what all the slash commands are?” 28:51 Requesting Databot to use the namespace operator 33:58 “Is there a way to search within that Databot pane?” 39:34 “Have you noticed any time differences with how quickly things run-in RStudio versus Positron?” 40:33 “What happens if you open that URL that it mentions at the bottom in your browser?” 40:50 Clarifying the difference between Posit Assistant and Positron Assistant 43:18 “What is the typical token burn rate?” 53:31 “Is this on CRAN and working in both Positron and RStudio?”
The mall package: using LLMs with data frames in R & Python | Edgar Ruiz | Data Science Lab
The Data Science Lab is a live weekly call. Register at pos.it/dslab! Discord invites go out each week on lives calls. We’d love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Edgar Ruiz as they walk through how mall works (with ellmer) in R, and then python. The mall package lets you use LLMs to process tabular or vectors of data, letting you do things such as feeding it a column of reviews and asking mall to use an anthropic model via ellmer to add a column of summaries or sentiments. Follow along with the code here: https://github.com/LibbyHeeren/mall-package-r
Hosting crew from Posit: Libby Heeren, Isabella Velasquez, Edgar Ruiz
Edgar’s Bluesky: https://bsky.app/profile/theotheredgar.bsky.social Edgar’s LinkedIn: https://www.linkedin.com/in/edgararuiz/ Edgar’s GitHub: https://github.com/edgararuiz
Resources from the hosts and chat:
Ollama → https://ollama.com/download Posit Data Science Lab → https://posit.co/dslab mall package → https://mlverse.github.io/mall/ ellmer package → https://elmer.tidyverse.org/ Libby’s Positron theme (Catppuccin) → https://marketplace.visualstudio.com/items?itemName=Catppuccin.catppuccin-vsc GitHub repo with Libby and Edgar’s code → https://github.com/LibbyHeeren/mall-package-r LLM providers supported by ellmer → https://ellmer.tidyverse.org/index.html#providers vitals package → https://vitals.tidyverse.org/ chatlas package → https://posit-dev.github.io/chatlas/ polars package → https://pola.rs/ narwhals package → https://narwhals-dev.github.io/narwhals/ pandas package → https://pandas.pydata.org/ LM Studio → https://lmstudio.ai/ Simon Couch’s blog → https://www.simonpcouch.com/ Edgar’s dataset: TidyTuesday Animal Crossing Dataset (May 5, 2020) → https://github.com/rfordatascience/tidytuesday Libby’s dataset: Kaggle Tweets Dataset → https://www.kaggle.com/datasets/mmmarchetti/tweets-dataset Blog from Sara and Simon on evaluating LLMs → https://posit.co/blog/r-llm-evaluation-03/ Data Science Lab YouTube playlist → https://www.youtube.com/watch?v=LDHGENv1NP4&list=PL9HYL-VRX0oSeWeMEGQt0id7adYQXebhT&index=2 AWS Bedrock → https://aws.amazon.com/bedrock/ Anthropic → https://www.anthropic.com/ Google Gemini → https://gemini.google.com/ What is rubber duck debugging anyway?? → https://en.wikipedia.org/wiki/Rubber_duck_debugging
► Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here: Website: https://www.posit.co The Lab: https://pos.it/dslab Hangout: https://pos.it/dsh LinkedIn: https://www.linkedin.com/company/posit-software Bluesky: https://bsky.app/profile/posit.co
Thanks for learning with us!
Timestamps 00:00 Introduction to Libby, Isabella, Edgar, and the mall package + ellmer package 07:14 “What’s the difference between using mall for these NLP tasks versus traditional or classical NLP?” 09:37 “Can mall be used with a local LLM?” 17:32 “What kind of laptop specs should I realistically have to make good use of these models?” 22:12 “Are you limited to three output options?” 22:55 “Can mall return the prediction probabilities?” 24:14 “What are a rule of thumb set of specs for a machine so local LLMs are practically feasible?” 24:47 “Would that be in the additional prompt area where you’re defining things?” 25:04 “You could use the vitals package to compare models, right?” 25:24 “Can we use LM Studio instead of Ollama?” 28:35 “How do you iterate and validate the model?” 36:39 “Why use paste if it is all text?” 37:31 “Are these recent tweets (from X) or older ones from actual Twitter?” 40:23 “Is there a playlist for the Data Science Labs on YouTube?” 46:11 “Does that mean that the python version does not work with pandas?” 50:14 “Where is this data set from?”
Getting Started with LLM APIs in R
Getting Started with LLM APIs in R - Sara Altman
Abstract: LLMs are transforming how we write code, build tools, and analyze data, but getting started with directly working with LLM APIs can feel daunting. This workshop will introduce participants to programming with LLM APIs in R using ellmer, an open-source package that makes it easy to work with LLMs from R. We’ll cover the basics of calling LLMs from R, as well as system prompt design, tool calling, and building basic chatbots. No AI or machine learning background is required—just basic R familiarity. Participants will leave with example scripts they can adapt to their own projects.
Resources mentioned in the workshop:
- Workshop site: https://skaltman.github.io/r-pharma-llm/
- ellmer documentation: https://ellmer.tidyverse.org/
- shinychat documentation: https://posit-dev.github.io/shinychat/
Simon Couch - Practical AI for data science
Practical AI for data science (Simon Couch)
Abstract: While most discourse about AI focuses on glamorous, ungrounded applications, data scientists spend most of their days tackling unglamorous problems in sensitive data. Integrated thoughtfully, LLMs are quite useful in practice for all sorts of everyday data science tasks, even when restricted to secure deployments that protect proprietary information. At Posit, our work on ellmer and related R packages has focused on enabling these practical uses. This talk will outline three practical AI use-cases—structured data extraction, tool calling, and coding—and offer guidance on getting started with LLMs when your data and code is confidential.
Presented at the 2025 R/Pharma Conference Europe/US Track.
Resources mentioned in the presentation:
- {vitals}: Large Language Model Evaluations https://vitals.tidyverse.org/
- {mcptools}: Model Context Protocol for R https://posit-dev.github.io/mcptools/
- {btw}: A complete toolkit for connecting R and LLMs https://posit-dev.github.io/btw/
- {gander}: High-performance, low-friction Large Language Model chat for data scientists https://simonpcouch.github.io/gander/
- {chores}: A collection of large language model assistants https://simonpcouch.github.io/chores/
- {predictive}: A frontend for predictive modeling with tidymodels https://github.com/simonpcouch/predictive
- {kapa}: RAG-based search via the kapa.ai API https://github.com/simonpcouch/kapa
- Databot https://positron.posit.co/dat
From messy to meaningful data: LLM-powered classification in R (Dylan Pieper) | posit::conf(2025)
From messy to meaningful data: LLM-powered classification in R
Speaker(s): Dylan Pieper
Abstract:
Transform messy, unstructured data into meaningful, structured data using ellmer, Posit’s R package for interacting with large language models (LLMs). LLMs can quickly convert thousands of texts, PDFs, and images into the data you need for your analysis. This talk demonstrates the practical benefits and addresses the common pitfalls of using LLMs through three examples: classifying images of Iris flowers and text descriptions of disease symptoms and crimes. Learn structured outputs, prompting strategies, model accuracy and confidence measurements, and validation techniques that blend generative AI with traditional ML concepts. Perfect for both AI-curious beginners and experienced data scientists.
Materials - https://github.com/dylanpieper/posit-25 posit::conf(2025) Subscribe to posit::conf updates: https://posit.co/about/subscription-management/
Positron Assistant for Developing Shiny Apps - Tom Mock
Positron Assistant for Developing Shiny Apps - Tom Mock (Posit)
Abstract: This talk will explore building AI Apps with a focus on Positron Assistant for Shiny developer experience and in-IDE tooling for accelerating app creation. This talk will discuss tools like ellmer / chatlas / querychat / shinychat and compare it to Positron Assistant.
Resources mentioned in the presentation:
- Positron - https://positron.posit.co/
- Positron Assistant - https://positron.posit.co/assistant.html
Daniel Chen - LLMs, Chatbots, and Dashboards: Visualize Your Data with Natural Language
For information on upcoming conferences, visit https://www.dataconf.ai .
LLMs, Chatbots, and Dashboards: Visualize Your Data with Natural Language by Daniel Chen
Abstract: LLMs have a lot of hype around them these days. Let’s demystify how they work and see how we can put them in context for data science use. As data scientists, we want to make sure our results are inspectable, reliable, reproducible, and replicable. We already have many tools to help us in this front. However, LLMs provide a new challenge; we may not always be given the same results back from a query. This means trying to work out areas where LLMs excel in, and use those behaviors in our data science artifacts. This talk will introduce you to LLms, the Ellmer, and Chatlas packages for R and Python, and how they can be integrated into a Shiny to create an AI-powered dashboard. We’ll see how we can leverage the tasks LLMs are good at to better our data science products.
Presented at The New York Data Science & AI Conference Presented by Lander Analytics (August 26, 2025)
Hosted by Lander Analytics
(https://www.landeranalytics.com )
From SDKs to Agents: Building with R and Python on Databricks (Rafi Kurlansik & Zac Davies)
From SDKs to Agents: Building with R and Python on Databricks
Speaker(s): Zac Davies; Rafi Kurlansik
Abstract:
Databricks offers a rich ecosystem of packages for R and Python developers. This session explores the key tools available—like {ellmer}, {brickster}, and the Databricks SDKs—helping developers build scalable workflows and AI-powered applications. Whether you’re working in R or Python, you’ll learn how to integrate your IDE, leverage Databricks-hosted LLMs, and build agentic workflows. We’ll cover practical implementations, best practices, and how to scale your projects using Databricks’ robust infrastructure. Whether you’re automating workflows or deploying AI-driven solutions, this talk provides the essential toolkit for success.
Materials posit::conf(2025) Subscribe to posit::conf updates: https://posit.co/about/subscription-management/
Putting an {ellmer} AI in production with the blessing of IT (Andrie de Vries) | posit::conf(2025)
Putting an {ellmer} AI in production with the blessing of IT
Speaker(s): Andrie de Vries
Abstract: I had an idea to automate a process by letting an AI extract information from PDF attachments. Writing the 20 lines of {ellmer} code was very simple. My users loved the idea. But IT had different feelings, especially initially. It took multiple design changes to get IT comfortable with running experiments in our financial system. They need a solution that is secure, with guardrails, wouldn’t leak sensitive information and could be easily maintained. We wrote a simple browser extension to reduce the friction of copy/paste between different systems. If you want to put an AI in production, make sure you consider the impact on other teams, in particular IT and Information security.
posit::conf(2025) Subscribe to posit::conf updates: https://posit.co/about/subscription-management/
Keywords: production, AI, LLM
Is that LLM feature any good? (Simon P. Couch, Posit) | posit::conf(2025)
Is that LLM feature any good?
Speaker(s): Simon P. Couch
Abstract:
The ellmer package has enabled R users to build all sorts of powerful LLM-enabled tools. How do you test these features, though? How do you know whether a change to your prompt made any difference, or if a much cheaper model would work just as well for your users? This talk introduces an R port of Inspect, a Python framework for LLM evaluation that has been widely adopted by both LLM developers and tool builders. Attendees will learn about the process of—and importance of—evaluating LLM-enabled apps empirically.
Materials - https://github.com/simonpcouch/conf-25 posit::conf(2025) Subscribe to posit::conf updates: https://posit.co/about/subscription-management/
Demystifying LLMs with Ellmer
From R/Medicine 2025
Joe Cheng, CTO, Posit Joe Cheng is the CTO of Posit, PBC. He’s the original creator of the Shiny web framework and co-creator of ellmer.
Today’s best LLMs are incredibly powerful–but you’re only scratching the surface of their capabilities if your use is limited to ChatGPT or Copilot. Accessing LLMs programmatically opens up a whole new world of possibilities, letting you integrate LLMs into your own apps, scripts, and workflows. In this workshop, we’ll cover:
A practical introduction to LLM APIs
– Configuring R to access LLMs via the ellmer package – Customizing LLM behavior using system prompts and tool calling – Creating Shiny apps with integrated chatbots – Using LLMs for natural language processing
Attendees will leave the workshop armed with ready-to-run examples, and the confidence and inspiration to run their own experiments with LLMs.
Attendees should be familiar with the basics of R and have a working R installation.
Note that to avoid any potential firewall issues, it is recommended that participants use a personal computer for this workshop.
Resources
Presentation: https://jcheng5.github.io/rmedicine-2025 R/Medicine: https://rconsortium.github.io/RMedicine_website/ R Consortium: https://www.r-consortium.org/
Harnessing LLMs for Data Analysis | Led by Joe Cheng, CTO at Posit
When we think of LLMs (large language models), usually what comes to mind are general purpose chatbots like ChatGPT or code assistants like GitHub Copilot. But as useful as ChatGPT and Copilot are, LLMs have so much more to offer—if you know how to code. In this demo Joe Cheng will explain LLM APIs from zero, and have you building and deploying custom LLM-empowered data workflows and apps in no time.
Posit PBC hosts these Workflow Demos the last Wednesday of every month. To join us for future events, you can register here: https://posit.co/events/
Slides: https://jcheng5.github.io/workflow-demo/ GitHub repo: https://github.com/jcheng5/workflow-demo
Resources shared during the demo: Ellmer https://ellmer.tidyverse.org/ Chatlas https://posit-dev.github.io/chatlas/
Environment variable management: For R: https://docs.posit.co/ide/user/ide/guide/environments/r/managing-r.html#renviron For Python https://pypi.org/project/python-dotenv/
Shiny chatbot UI: For R, Shinychat https://posit-dev.github.io/shinychat/ For Python, ui.Chat https://shiny.posit.co/py/docs/genai-inspiration.html
Deployment Cloud hosting https://connect.posit.cloud On-premises (Enterprise) https://posit.co/products/enterprise/connect/ On-premises (Open source) https://posit.co/products/open-source/shiny-server/
Querychat Demo: https://jcheng.shinyapps.io/sidebot/ Package: https://github.com/posit-dev/querychat/
If you have specific follow-up questions about our professional products, you can schedule time to chat with our team: pos.it/llm-demo
Bringing data science to the construction industry | Blake Abbenante | Data Science Hangout
To join future data science hangouts, add it to your calendar here: https://pos.it/dsh - All are welcome! We’d love to see you!
We were recently joined by Blake Abbenante, Director of Analytics and Data Science at Suffolk Construction, to chat about his career journey in data science, implementing modern data practices in the construction industry, innovative applications of AI and data science in construction, and building a data-driven culture in a traditionally less tech-focused sector.
In this Hangout, we explore innovative applications of AI and data science in construction. Blake shared how Suffolk Construction is leveraging cutting-edge technologies like AI to revolutionize traditional processes. One focus is their GenAI scheduling tool, which aims to augment and speed up the design and planning phases of building projects. This tool has the potential to significantly reduce the time planners spend on creating schedules, moving from weeks to potentially minutes or hours for an 80% completion rate. Blake discussed the development and implementation of safety models that forecast risk on projects, enabling proactive measures to ensure safer construction sites by predicting which projects might require additional safety personnel based on historical data.
Resources mentioned in the video and zoom chat: The ellmer R package → https://ellmer.tidyverse.org/ The chatlas R package → https://github.com/posit-dev/chatlas Posit Blog Post on ellmer → https://posit.co/blog/announcing-ellmer/
If you didn’t join live, one great discussion you missed from the zoom chat was about the challenges of data collection and analysis when encountering pushback from those whose work is being analyzed, and strategies to build trust and demonstrate value. Let us know below if you’d like to hear more about this topic!
► Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here: Website: https://www.posit.co Hangout: https://pos.it/dsh LinkedIn: https://www.linkedin.com/company/posit-software Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us!
Shiny community, hackathons, and his AI mindset | Joe Cheng | Data Science Hangout
To join future data science hangouts, add it to your calendar here: https://pos.it/dsh - All are welcome! We’d love to see you!
We were recently joined by Joe Cheng, CTO at Posit, to chat about the Shiny contest, the use of AI in data science, and designing hackathons for learning new technologies. We were joined by several past and present Shiny contest winners who gave great advice on how to get started if you want to participate (and we really hope you do)!
In this Hangout, we explore the evolution of the Shiny contest since its inception, including what made the 2024 submissions unique and the ways the contest encourages community contribution and learning. Joe also shared about his personal journey from feeling skepticism about AI to seeing and embracing its potential. We got some amazing questions from the Hangout attendees! We hope you join us live next time to ask some of your own questions
Resources mentioned in the video and zoom chat:
2024 Shiny Contest Winners → https://posit.co/blog/winners-of-the-2024-shiny-contest/
Joe’s AI Hackathon Slides → https://jcheng5.github.io/llm-quickstart/quickstart.html
Shiny Assistant → https://gallery.shinyapps.io/assistant/
Isabella’s blog post on prototyping with Shiny Assistant → https://posit.co/blog/ai-powered-shiny-app-prototyping/
Posit Conf Workshops → https://reg.rainfocus.com/flow/posit/positconf25/attendee-portal/page/sessioncatalog?tab.day=20250916&search.sessiontype=1675316728702001wr6r
Shiny Conference 2025 → https://www.shinyconf.com/
Call for Speakers Shiny Conf 2025 → https://sessionize.com/shiny-conf-2025/
Shiny Tableau → https://rstudio.github.io/shinytableau/
Echarts4r → https://echarts4r.john-coene.com
Elmer package on Github → https://github.com/tidyverse/ellmer
All the Shiny app links mentioned in the video and zoom chat: Eric Nantz 2021 Shiny Contest Submission → https://forum.posit.co/t/the-hotshots-racing-dashboard-shiny-contest-submission/104925 Eric Nantz’s R/Pharma conference keynote on AI → https://youtu.be/AfMa1CVUdXU?si=ThLsKFyonntxzBUF Eric Nantz’s Haunted Places app → https://youtu.be/vX09QGMuOfo?si=K5_uPfK5bcfZZ92l Umair Durrani’s Shiny Storytelling app → https://umair.shinyapps.io/storytimegcp/ Umair’s Blue Sky profile → https://bsky.app/profile/transport-talk.bsky.social Umair’s Shiny meetings project on Github → https://github.com/shiny-meetings/shiny-meetings Abby Stamm’s Shiny Accessibility app → https://github.com/ajstamm/shiny-a11y-app
If you didn’t join live, one great discussion you missed from the zoom chat was about everyone’s favorite interactive plotting tools. Someone asked whether Plotly was the best option, and lots of people said they loved ggiraph, echarts4r, ObservableJS, and others. What about you?! What’s your favorite interactive plotting library?
► Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here: Website: https://www.posit.co Hangout: https://pos.it/dsh LinkedIn: https://www.linkedin.com/company/posit-software Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us!
