lmcli is a (Large) Language Model CLI
Go to file
Matt Low ed6ee9bea9 Add *Message[] parameter to CreateChatCompletion methods
Allows replies (tool calls, user-facing messges) to be added in sequence
as CreateChatCompleion* recurses into itself.

Cleaned up cmd.go: no longer need to create a Message based on the
string content response.
2023-11-29 04:43:53 +00:00
pkg/cli Add *Message[] parameter to CreateChatCompletion methods 2023-11-29 04:43:53 +00:00
.gitignore Update .gitignore 2023-11-04 13:35:23 -06:00
README.md Update README.md 2023-11-23 17:44:57 +00:00
go.mod Add syntax highlighting 2023-11-19 05:00:59 +00:00
go.sum Add syntax highlighting 2023-11-19 05:00:59 +00:00
main.go Minor refactor 2023-11-14 17:04:12 +00:00

README.md

lmcli

lmcli is a (Large) Language Model CLI.

Current features:

  • Perform one-shot prompts with lmcli prompt <message>
  • Manage persistent conversations with the new, reply, view, and rm sub-commands.
  • Syntax highlighted output

Planned features:

  • Ask questions about content received on stdin
  • "functions" to allow reading (and possibly writing) to files within the current working directory

Maybe features:

  • Natural language image generation, iterative editing

Install

$ go install git.mlow.ca/mlow/lmcli@latest

Usage

Invoke lmcli at least once:

$ lmcli help

Edit ~/.config/lmcli/config.yaml and set openai.apiKey to your API key.

Refer back to the output of lmcli help for usage.

Enjoy!