Help for package chattr

Title:

Interact with Large Language Models in 'RStudio'

Version:

0.3.0

Description:

Enables user interactivity with large-language models ('LLM') inside the 'RStudio' integrated development environment (IDE). The user can interact with the model using the 'shiny' app included in this package, or directly in the 'R' console. It comes with back-ends for 'OpenAI', 'GitHub' 'Copilot', and 'LlamaGPT'.

URL:

https://github.com/mlverse/chattr, https://mlverse.github.io/chattr/

BugReports:

https://github.com/mlverse/chattr/issues

License:

MIT + file LICENSE

Encoding:

UTF-8

RoxygenNote:

7.3.2

Imports:

rstudioapi, lifecycle, processx, config, ellmer (≥ 0.2.0), purrr, rlang, bslib, shiny, clipr, httr2 (≥ 1.1.0), yaml, glue, coro, cli, fs

Depends:

R (≥ 2.10)

Suggests:

covr, knitr, rmarkdown, testthat (≥ 3.0.0), shinytest2, withr

Config/testthat/edition:

VignetteBuilder:

knitr

NeedsCompilation:

Packaged:

2025-05-28 18:14:47 UTC; edgar

Author:

Edgar Ruiz [aut, cre], Posit Software, PBC [cph, fnd]

Maintainer:

Edgar Ruiz <edgar@posit.co>

Repository:

CRAN

Date/Publication:

2025-05-28 18:30:02 UTC

Displays and sets the current session' chat history

Description

Displays and sets the current session' chat history

Usage

ch_history(x = NULL)

Arguments

x

An list object that contains chat history. Use this argument to override the current history.

Value

A list object with the current chat history

Examples

library(chattr)

chattr_use("test", stream = FALSE)

chattr("hello")

# View history
ch_history()

# Save history to a file
chat_file <- tempfile()
saveRDS(ch_history(), chat_file)

# Reset history
ch_history(list())

# Re-load history
ch_history(readRDS(chat_file))

Method to integrate to new LLM API's

Description

Method to integrate to new LLM API's

Usage

ch_submit(
  defaults,
  prompt = NULL,
  stream = NULL,
  prompt_build = TRUE,
  preview = FALSE,
  ...
)

Arguments

defaults

Defaults object, generally puled from chattr_defaults()

prompt

The prompt to send to the LLM

stream

To output the response from the LLM as it happens, or wait until the response is complete. Defaults to TRUE.

prompt_build

Include the context and additional prompt as part of the request

preview

Primarily used for debugging. It indicates if it should send the prompt to the LLM (FALSE), or if it should print out the resulting prompt (TRUE)

...

Optional arguments; currently unused.

Value

The output from the model currently in use.

Submits prompt to LLM

Description

Submits prompt to LLM

Usage

chattr(prompt = NULL, preview = FALSE, prompt_build = TRUE, stream = NULL)

Arguments

prompt

Request to send to LLM. Defaults to NULL

preview

Primarily used for debugging. It indicates if it should send the prompt to the LLM (FALSE), or if it should print out the resulting prompt (TRUE)

prompt_build

Include the context and additional prompt as part of the request

stream

To output the response from the LLM as it happens, or wait until the response is complete. Defaults to TRUE.

Value

The output of the LLM to the console, document or script.

Examples

library(chattr)
chattr_use("test")
chattr("hello")
chattr("hello", preview = TRUE)

Starts a Shiny app interface to the LLM

Description

Starts a Shiny app interface to the LLM

Usage

chattr_app(
  viewer = c("viewer", "dialog"),
  as_job = getOption("chattr.as_job", FALSE),
  as_job_port = getOption("shiny.port", 7788),
  as_job_host = getOption("shiny.host", "127.0.0.1")
)

Arguments

viewer

Specifies where the Shiny app is going to display

as_job

App runs as an RStudio IDE Job. Defaults to FALSE. If set to TRUE, the Shiny app will not be able to transfer the code blocks directly to the document, or console, in the IDE.

as_job_port

Port to use for the Shiny app. Applicable only if as_job is set to TRUE.

as_job_host

Host IP to use for the Shiny app. Applicable only if as_job is set to TRUE.

Value

A chat interface inside the 'RStudio' IDE

Default arguments to use when making requests to the LLM

Description

Default arguments to use when making requests to the LLM

Usage

chattr_defaults(
  type = "default",
  prompt = NULL,
  max_data_files = NULL,
  max_data_frames = NULL,
  include_doc_contents = NULL,
  include_history = NULL,
  provider = NULL,
  path = NULL,
  model = NULL,
  model_arguments = NULL,
  system_msg = NULL,
  yaml_file = "chattr.yml",
  force = FALSE,
  label = NULL,
  ...
)

Arguments

type

Entry point to interact with the model. Accepted values: 'notebook', chat'

prompt

Request to send to LLM. Defaults to NULL

max_data_files

Sets the maximum number of data files to send to the model. It defaults to 20. To send all, set to NULL

max_data_frames

Sets the maximum number of data frames loaded in the current R session to send to the model. It defaults to 20. To send all, set to NULL

include_doc_contents

Send the current code in the document

include_history

Indicates whether to include the chat history when every time a new prompt is submitted

provider

The name of the provider of the LLM. Today, only "openai" is is available

path

The location of the model. It could be an URL or a file path.

model

The name or path to the model to use.

model_arguments

Additional arguments to pass to the model as part of the request, it requires a list. Examples of arguments: temperature, top_p, max_tokens

system_msg

For OpenAI GPT 3.5 or above, the system message to send as part of the request

yaml_file

The path to a valid config YAML file that contains the defaults to use in a session

force

Re-process the base and any work space level file defaults

label

Label to display in the Shiny app, and other locations

...

Additional model arguments that are not standard for all models/backends

Details

The idea is that because we will use addin shortcut to execute the request, all of the other arguments can be controlled via this function. By default, it will try to load defaults from a config YAML file, if none are found, then the defaults for GPT 3.5 will be used. The defaults can be modified by calling this function, even after the interactive session has started.

Value

An 'ch_model' object that contains the current defaults that will be used to communicate with the LLM.

Saves the current defaults in a yaml file that is compatible with the config package

Description

Saves the current defaults in a yaml file that is compatible with the config package

Usage

chattr_defaults_save(path = "chattr.yml", overwrite = FALSE, type = NULL)

Arguments

path

Path to the file to save the configuration to

overwrite

Indicates to replace the file if it exists

type

The type of UI to save the defaults for. It defaults to NULL which will save whatever types had been used during the current R session

Value

It creates a YAML file with the defaults set in the current R session.

Confirms connectivity to LLM interface

Description

Confirms connectivity to LLM interface

Usage

chattr_test(defaults = NULL)

ch_test(defaults = NULL)

Arguments

defaults

Defaults object, generally puled from chattr_defaults()

Value

It returns console massages with the status of the test.

Sets the LLM model to use in your session

Description

Sets the LLM model to use in your session

Usage

chattr_use(x = NULL, ...)

Arguments

x

A pre-determined provider/model name, an ellmer Chat object, or the path to a YAML file that contains a valid chattr model specification. The value 'test' is also acceptable, but it is meant for package examples, and internal testing. See 'Details' for more information.

...

Default values to modify.

Details

The valid pre-determined provider/models values are: 'databricks-dbrx', 'databricks-meta-llama31-70b', 'databricks-mixtral8x7b', 'gpt41-mini', 'gpt41-nano', 'gpt41', 'gpt4o', and 'ollama'.

If you need a provider, or model, not available as a pre-determined value, create an ellmer chat object and pass that to chattr_use(). The list of valid models are found here: https://ellmer.tidyverse.org/index.html#providers

Set a default

You can setup an R option to designate a default provider/model connection. To do this, pass an ellmer connection command you wish to use in the .chattr_chat option, for example: options(.chattr_chat = ellmer::chat_anthropic()). If you add that code to your .Rprofile, chattr will use that as the default model and settings to use every time you start an R session. Use the usethis::edit_r_profile() command to easily edit your .Rprofile.

Value

It returns console messages to allow the user select the model to use.

Examples

## Not run: 

# Use a valid provider/model label
chattr_use("gpt41-mini")

# Pass an `ellmer` object
my_chat <- ellmer::chat_anthropic()
chattr_use(my_chat)

## End(Not run)