https://github.com/edubruell/tidyllm
An tidy interface to large language model APIs for R
https://github.com/edubruell/tidyllm
Last synced: 3 months ago
JSON representation
An tidy interface to large language model APIs for R
- Host: GitHub
- URL: https://github.com/edubruell/tidyllm
- Owner: edubruell
- License: other
- Created: 2024-04-24T15:21:39.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-11-18T13:54:18.000Z (3 months ago)
- Last Synced: 2024-11-18T15:22:05.886Z (3 months ago)
- Language: R
- Homepage: https://edubruell.github.io/tidyllm/
- Size: 13.4 MB
- Stars: 31
- Watchers: 2
- Forks: 2
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- Changelog: NEWS.md
- License: LICENSE
Awesome Lists containing this project
- jimsghstars - edubruell/tidyllm - An tidy interface to large language model APIs for R (R)
README
# tidyllm 
[](https://opensource.org/licenses/MIT)
[](https://cran.r-project.org/package=tidyllm)
**tidyllm** is an R package designed to access various large language model APIs, including **Anthropic Claude**, **OpenAI**,**Google Gemini**, **Groq**, **Mistral**, and local models via **Ollama** or OpenAI-compatible APIS. Built for simplicity and functionality, it helps you generate text, analyze media, and integrate model feedback into your data workflows with ease.
## Features
- **Multiple Model Support**: Seamlessly switch between various model providers using the best of what each has to offer.
- **Media Handling**: Extract and process text from PDFs and capture console outputs for messaging. Upload imagefiles or the last plotpane to multimodal models. For the Gemini API even video and audio inputs are supported.
- **Interactive Messaging History**: Manage an ongoing conversation with models, maintaining a structured history of messages and media interactions, which are automatically formatted for each API
- **Batch processing:** Efficiently handle large workloads with Anthropic and OpenAI batch processing APIs, reducing costs by up to 50%.
- **Tidy Workflow**: Use R's functional programming features for a side-effect-free, pipeline-oriented operation style.
## Installation
To install **tidyllm** from CRAN, use:
```r
install.packages("tidyllm")
```
Or for the development version from GitHub:
```r
# Install devtools if not already installed
if (!requireNamespace("devtools", quietly = TRUE)) {
install.packages("devtools")
}
devtools::install_github("edubruell/tidyllm")
```
## Basic Example
Here’s a quick example using tidyllm to describe an image using the Claude model
to and follow up with local open-source models:
```R
library("tidyllm")
# Describe an image with claude
conversation <- llm_message("Describe this image",
.imagefile = here("image.png")) |>
chat(claude())
# Use the description to query further with groq
conversation |>
llm_message("Based on the previous description,
what could the research in the figure be about?") |>
chat(ollama(.model = "gemma2"))
```
For more examples and advanced usage, check the [Get Started vignette](https://edubruell.github.io/tidyllm/articles/tidyllm.html).
Please note: To use **tidyllm**, you need either an installation of **ollama** or an active API key for one of the supported providers (e.g., Claude, ChatGPT). See the [Get Started vignette](https://edubruell.github.io/tidyllm/articles/tidyllm.html) for setup instructions.
## Interface-change in 0.2.3.
The development version 0.2.3. of **tidyllm**, introduces a major interface change to provide a more intuitive user experience. Previously, provider-specific functions like `claude()`, `openai()`, and others were directly used for chat-based workflows. They specified both an API-provider and performed a chat-interaction. Now, these functions primarily serve as provider configuration for more general verbs like `chat()`,`embed()` or `send_batch()`. A combination of a general verb and a provider will always route requests to a provider-specific function like `openai_chat()`. Read the [Changelog](https://edubruell.github.io/tidyllm/news/) or the [package vignette](https://edubruell.github.io/tidyllm/articles/tidyllm.html) for more information.
For backward compatibility, the old use of functions like `openai()` or `claude()` directly for chat requests still works but now but issues deprecation warnings. It is recommended to either use the verb-based interface:
```r
llm_message("Hallo") |> chat(openai(.model="gpt-4o"))
```
or to use the more verbose provider-specific functions directly:
```r
llm_message("Hallo") |> openai_chat(.model="gpt-4o")
```
## Learn More
For detailed instructions and advanced features, see:
- [Get Started with tidyllm](https://edubruell.github.io/tidyllm/articles/tidyllm.html)
- [Changelog](https://edubruell.github.io/tidyllm/news/)
- [Documentation](https://edubruell.github.io/tidyllm/)
- Use-case oriented articles:
- [Classifying Texts with tidyllm](https://edubruell.github.io/tidyllm/articles/tidyllm_classifiers.html)
- [Structured Question Answering from PDFs](https://edubruell.github.io/tidyllm/articles/tidyllm-pdfquestions.html)
- [Generate Synthetic Survey Data](https://edubruell.github.io/tidyllm/articles/tidyllm-synthetic-data.html)
- [Using Embedding Models for Semantic Search](https://edubruell.github.io/tidyllm/articles/tidyllm_embed.html)
- [Video and Audio Data with the Gemini API](https://edubruell.github.io/tidyllm/articles/tidyllm_video.html)
## Contributing
We welcome contributions! Feel free to open issues or submit pull requests on [GitHub](https://github.com/edubruell/tidyllm).
## License
This project is licensed under the MIT License - see the [LICENSE](https://opensource.org/licenses/MIT) file for details.