prompt_from_history

Provides a framework for integrating Large Language Models (LLMs) with R programming through workflow automation. Built on the ReAct (Reasoning and Acting) architecture, enables bi-directional communication between LLMs and R environments. Features include automated code generation and execution, intelligent error handling with retry mechanisms, persistent session management, structured JSON output validation, and context-aware conversation management.

Zaoqu Liu

llmflow

Reasoning and Acting Workflow for Automated Data Analysis

prompt_from_history function

<dl><dt>chat_obj</dt>
<dd>Chat object</dd>
<dt>add_text</dt>
<dd>Additional text to append</dd>
<dt>add_role</dt>
<dd>Role for add_text ("user" or "assistant")</dd>
<dt>start_turn_index</dt>
<dd>Starting turn index (default 1)</dd></dl>

Arguments

Build prompt from chat history — prompt_from_history

<dl>

<dt>chat_obj</dt>
<dd>Chat object</dd>


<dt>add_text</dt>
<dd>Additional text to append</dd>


<dt>add_role</dt>
<dd>Role for add_text ("user" or "assistant")</dd>


<dt>start_turn_index</dt>
<dd>Starting turn index (default 1)</dd>

</dl>

prompt_from_history: Build prompt from chat history

Description

Usage

Value

Arguments