codestral: Chat and FIM with 'Codestral'

Description

Create an addin in 'Rstudio' to do fill-in-the-middle (FIM) and chat with latest Mistral AI models for coding, 'Codestral' and 'Codestral Mamba'. For more details about 'Mistral AI API': https://docs.mistral.ai/getting-started/quickstart/ and https://docs.mistral.ai/api/. For more details about 'Codestral' model: https://mistral.ai/news/codestral; about 'Codestral Mamba': https://mistral.ai/news/codestral-mamba.

Author(s)

Maintainer: Marc Grossouvre marcgrossouvre@urbs.fr

Other contributors:

• URBS company contact@rubs.fr [copyright holder, funder]

See Also

Useful links:

• https://urbs-dev.github.io/codestral/

• Report bugs at https://github.com/urbs-dev/codestral/issues

Markers for Codestral

Description

Markers for Codestral

Usage

ALLMARKERS

Format

A data frame with 5 rows and 2 variables:

marker

The marker.

decription

The description of the marker.

Endpoints for the Codestral API.

Description

Endpoints for the Codestral API.

Usage

ENDPOINTS

Format

A named list with elements chat and completion.

Allow codestral to detect package environment

Description

Allow codestral to detect package environment

Usage

allow_detect_package(x = TRUE)

Arguments

Details

If set to TRUE, when codestral is used in a folder with a DESCRIPTION file, all R files in the current folder and its subfolders are included in the prompt.

Value

0 invisible.

Fill in the middle with Codestral

Description

This function completes a given prompt using the Codestral API. It supports different models for fill-in-the-middle, chat with Codestral, and chat with Codestral Mamba. The function relies on environment variables for some parameters.

Usage

codestral(
  prompt,
  suffix = "",
  path = NULL,
  mistral_apikey = Sys.getenv(x = "R_MISTRAL_APIKEY"),
  codestral_apikey = Sys.getenv(x = "R_CODESTRAL_APIKEY"),
  fim_model = Sys.getenv(x = "R_CODESTRAL_FIM_MODEL"),
  chat_model = Sys.getenv(x = "R_CODESTRAL_CHAT_MODEL"),
  mamba_model = Sys.getenv(x = "R_MAMBA_CHAT_MODEL"),
  temperature = as.integer(Sys.getenv(x = "R_CODESTRAL_TEMPERATURE")),
  max_tokens_FIM = Sys.getenv(x = "R_CODESTRAL_MAX_TOKENS_FIM"),
  max_tokens_chat = Sys.getenv(x = "R_CODESTRAL_MAX_TOKENS_CHAT"),
  role_content = Sys.getenv(x = "R_CODESTRAL_ROLE_CONTENT")
)

Arguments

Value

A character string containing the completed text.

Initialize codestral

Description

Create environment variables for operationg FIM and chat.

Usage

codestral_init(
  mistral_apikey = Sys.getenv(x = "R_MISTRAL_APIKEY"),
  codestral_apikey = Sys.getenv(x = "R_CODESTRAL_APIKEY"),
  fim_model = "codestral-latest",
  chat_model = "codestral-latest",
  mamba_model = "open-codestral-mamba",
  temperature = 0,
  max_tokens_FIM = 100,
  max_tokens_chat = "",
  role_content = NULL
)

Arguments

Details

The most important paremeters here are the ..._apikey parameters without which the Mistral AI API can not be used.

To start with, beginners may keep default values for other parameters. It seems sound to use the latest models of each type. However with time, the user may be willing to customize temperature, max_tokens_FIM, max_tokens_chat and role_content for his/her own needs.

This function creates the following environment variables using Sys.setenv():

• R_MISTRAL_APIKEY

• R_CODESTRAL_APIKEY

• R_CODESTRAL_FIM_MODEL

• R_CODESTRAL_CHAT_MODEL

• R_CODESTRAL_MAMBA_MODEL

• R_CODESTRAL_TEMPERATURE

• R_CODESTRAL_MAX_TOKENS_FIM

• R_CODESTRAL_MAX_TOKENS_CHAT

• R_CODESTRAL_DEBUG

• R_CODESTRAL_DETECT_PACKAGE

• R_CODESTRAL_ROLE_CONTENT

Value

Invisible 0.

Analyses a prompt to re-buid the dialog

Description

Analyses a prompt to re-buid the dialog

Usage

compile_dialog(prompt)

Arguments

Value

A list with the chatter (Codestral or Codestral Mamba) and the dialog in a data.frame whith columns role and content.

Fill in the middle or complete

Description

This function splits the current script into two parts: the part before the cursor and the part after the cursor.

Usage

complete_current_script()

Value

A character vector containing the two parts of the script.

Set debug mode

Description

Set debug mode

Usage

debug_mode(debug = TRUE)

Arguments

Details

When the debug mode is activated, the function codestral() will print the request body and the response body.

Value

Invisible 0.

Detect whether the working directory is that of a package

Description

Detect whether the working directory is that of a package

Usage

detect_package()

Value

TRUE if the working directory is that of a package, FALSE otherwise

Read and include files in a prompt

Description

Read and include files in a prompt

Usage

include_file(prompt, anyFile)

Arguments

Details

If anyFile[i] is TRUE then the sequence of characters following the instruction "ff:" in prompt[i] is read until the next space or the end of the string. This extracted string is assumed to be a file name. This file is looked for in the current working directory or any of its sub-directories. Once detected, the file is read with readLines() and this content is inserted in prompt between prompt[i-1] and prompt[i+1]. Note that prompt[i] is therefore deleted.

The result is returned.

Value

A vector of strings containing prompt augmented by the files refered to in the original prompt.

Include package files in the prompt

Description

This function includes R files from a package in the prompt when a package is detected. It handles the inclusion of file contents and path-specific exclusions.

Usage

include_package_files(prompt, path)

Arguments

Value

The modified prompt with package file contents included.

Insert the model's answer

Description

This function inserts a Codestral FIM into the current script.

Usage

insert_addin()

Value

0 (invisible).

Inventory R files in the current directory

Description

This function returns a data frame with the file names and paths of all R files in the current directory.

Usage

inventory_Rfiles()

Value

A data frame with the file names and paths of all R files in the current directory.

Examples

inventory_Rfiles()