llm-workflow-engine
Power CLI and Workflow manager for LLMs (core package)
What is llm-workflow-engine?
Power CLI and Workflow manager for LLMs (core package)
Overview of llm-workflow-engine
What it is
LLM Workflow Engine (LWE) is a command-line interface and workflow manager for large language models. It is the core package of the project, hosted on GitHub under the MIT license.
Key features
- Lets you use ChatGPT/GPT4 from the command line
- Runs in the shell; you can call and interact with ChatGPT/GPT4 in the terminal
- Supports the official ChatGPT API, making API calls directly to the OpenAI ChatGPT endpoint (all supported models accessible by your OpenAI account)
- Simple plugin architecture to extend LWE with custom functionality
- Supports multiple LLM providers via provider plugins (GPT-3, Cohere, Huggingface, etc.)
- Build workflows by integrating calls to an LLM into larger workflows via Ansible Playbooks
- Tool use for supported providers
- Available as a Docker image (experimental)
- Python API for using ChatGPT/GPT4 in Python scripts
Use cases
LWE is suitable for developers and power users who want to interact with LLMs from the terminal, automate multi-step tasks by chaining LLM calls into workflows, or extend functionality through plugins. It can be used for scripting, testing prompts, and integrating LLM capabilities into larger automation pipelines.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
The project is licensed under the MIT License. It is open source and free to use.
Based on the project's public README and repository metadata.