chatAI4R (version 0.3.6)

discussion_flow_v2: discussion_flow_v2: Interactions and Flow Control Between LLM-based Bots (LLBs)

Description

Simulates interactions and flow control between three different roles of LLM-based bots (LLBs).

Usage

discussion_flow_v2(
  issue,
  Domain = "bioinformatics",
  Model = "gpt-4o-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  language = "English",
  Summary_nch = 50,
  Sentence_difficulty = 2,
  R_expert_setting = TRUE,
  verbose = TRUE,
  sayENorJA = TRUE,
  rep_x = 3
)

Value

A summary of the conversation between the bots.

Arguments

issue

The issue to be discussed. Example: "I want to solve linear programming and create a timetable."

Domain

The domain of the discussion, default is "bioinformatics".

Model

The LLM model to be used, default is "gpt-4o-mini".

api_key

The API key for OpenAI, default is retrieved from the system environment variable "OPENAI_API_KEY".

language

The language for the discussion, default is "English".

Summary_nch

The number of characters for the summary, default is 50.

Sentence_difficulty

Numeric, the complexity level for sentence construction, default is 2.

R_expert_setting

Logical, whether R expert settings are enabled, default is TRUE.

verbose

Logical, whether to print verbose output, default is TRUE.

sayENorJA

Logical, whether to speak in English or Japanese, default is TRUE. This feature is available on macOS systems only.

rep_x

Numeric, a number of repeats for the conversations, default is 3.

Author

Satoshi Kume

Details

Interactions and Flow Control Between LLM-based Bots (LLBs)

In the v2 model, we added a regulation of the difficulty of the sentence, the human intervention in their conversation between LLM bots, and number of repetitions of conversation. This function is described to simulate the interactions and flow control between three different roles of LLM-based bots, abbreviated as LLBs, namely A (Beginner), B (Expert), and C (Peer Reviewer). These roles have distinct functions and work together to facilitate more complex and meaningful discussions. Here is a brief description of the roles: A (Beginner): This bot generates questions and summaries based on the content of the discussion provided by the user. B (Expert): This bot provides professional answers to questions posed by LLB A. C (Peer Reviewer): This bot reviews the dialog between LLB A and LLB B and suggests improvements or refinements. The three parties independently call the OpenAI API according to their roles. In addition, it keeps track of the conversation history between the bots and performs processes such as questioning, answering, and peer review. The function is designed to work in a "domain," which is essentially a specific area or topic around which conversations revolve. It is recommended to use GPT-4 or a model with higher accuracy than GPT-4. English is recommended as the input language, but the review will also be conducted in Japanese, the native language of the author.

Examples

if (FALSE) {
issue <-  "I want to solve linear programming and create a timetable."

#Run Discussion with the domain of bioinformatics
discussion_flow_v2(issue)
}