The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

llmflow 3.0.2

CRAN resubmission addressing reviewer feedback:

• Replaced cat() with message() for suppressible console output
• Replaced globalenv() with isolated evaluation environment to comply with CRAN policy
• Code execution now uses .llmflow_eval_env within callr sessions, never modifying user’s global environment

llmflow 3.0.1

Initial CRAN submission.

Features

• AutoFlow(): Complete workflow combining retrieval-augmented generation (RAG) with ReAct execution
• react_r(): ReAct loop implementation with smart history management and context summarization
• response_to_r(): LLM-to-R code generation and execution in isolated sessions
• response_as_json(): Structured JSON output with schema validation
• retrieve_docs(): R function documentation retrieval for RAG workflows

Architecture

• Dual-LLM support for optimized cost and performance
• Error escalation and task degradation strategies
• Intermediate result protection near turn limits
• Session continuity via existing_session parameter

Notes

• Functions extract_package_docs(), extract_function_docs(), extract_docs_from_tarball(), and generate_qa_from_docs() have been moved to the separate llmtools package.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.