cgpt

Overview ¶

Command cgpt is a command line tool for interacting with Large Language Models (LLMs).

Usage:

cgpt [flags] [input]

Input can be provided via:

• Command line arguments
• -i/--input flag (can be used multiple times)
• -f/--file flag (can be used multiple times, use '-' for stdin)
• Piped input

Flags:

-b, --backend string             The backend to use (default "anthropic")
-m, --model string               The model to use (default "claude-3-5-sonnet-20240620")
-i, --input string               Direct string input (can be used multiple times)
-f, --file string                Input file path. Use '-' for stdin (can be used multiple times)
-c, --continuous                 Run in continuous mode (interactive)
-s, --system-prompt string       System prompt to use
-p, --prefill string             Prefill the assistant's response
-I, --history-load string        File to read completion history from
-O, --history-save string        File to store completion history in
    --config string              Path to the configuration file (default "config.yaml")
-v, --verbose                    Verbose output
    --debug                      Debug output
-n, --completions int            Number of completions (when running non-interactively with history)
-t, --max-tokens int             Maximum tokens to generate (default 8000)
    --completion-timeout duration Maximum time to wait for a response (default 2m0s)
-h, --help                       Display help information

The -c/--continuous flag enables interactive mode, where the program runs in a loop, using the previous output as input for the next request. In this mode, inference