From a547c57c9ccc048ff9a86ce91f4c15427ee419a5 Mon Sep 17 00:00:00 2001 From: Matt Low Date: Sun, 23 Jun 2024 21:19:34 +0000 Subject: [PATCH] Update README --- README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index ac1a7a6..1735f7a 100644 --- a/README.md +++ b/README.md @@ -87,8 +87,6 @@ Available formatters: ## Usage -Here's the default help output for `lmcli`: - ```console $ lmcli help lmcli - Large Language Model CLI @@ -141,16 +139,18 @@ $ lmcli prompt "What is the answer to life, the universe, and everything?" ## Agents -Agents in `lmcli` are configurations that combine a system prompt with a set of available tools. You can define agents in the `config.yaml` file and switch between them using the `--agent` or `-a` flag. +Agents in `lmcli` combine a system prompt with a set of available tools. Agents are defined in`config.yaml` and you use them with the `-a`/`--agent` flag. Example: -```sh -lmcli chat -a financier +```console +$ lmcli chat -a financier ``` +Agent functionality is expected to be expanded on, bringing them to close parity with something like OpenAI's "Assistants" feature. + ## Tools -`lmcli` supports tool calling. The following built-in tools are currently available: +Tools in `lmcli` are used by agents to to acquire information from and interact with external systems. The following built-in tools are available: - `dir_tree`: Display a directory structure - `read_file`: Read the contents of a file