llmflow: Reasoning and Acting Workflow for Automated Data Analysis
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.
| Version: | 3.0.2 |
| Depends: | R (≥ 4.1.0) |
| Imports: | callr, cli, glue, jsonlite, jsonvalidate |
| Suggests: | ellmer, testthat (≥ 3.0.0) |
| Published: | 2026-01-31 |
| DOI: | 10.32614/CRAN.package.llmflow (may not be active yet) |
| Author: | Zaoqu Liu  [aut,
cre] |
| Maintainer: | Zaoqu Liu <liuzaoqu at 163.com> |
| BugReports: | https://github.com/Zaoqu-Liu/llmflow/issues |
| License: | GPL (≥ 3) |
| URL: | https://github.com/Zaoqu-Liu/llmflow |
| NeedsCompilation: | no |
| Materials: | README, NEWS |
| CRAN checks: | llmflow results |
Documentation:
| Reference manual: | llmflow.html , llmflow.pdf |
Downloads:
| Package source: | llmflow_3.0.2.tar.gz |
| Windows binaries: | r-devel: not available, r-release: not available, r-oldrel: not available |
| macOS binaries: | r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): llmflow_3.0.2.tgz, r-oldrel (x86_64): llmflow_3.0.2.tgz |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=llmflow to link to this page.