Large language model inference for power users. At the current development stage it is more or less a ChatGPT CLI/TUI.

pipx install git+https://github.com/danisztls/llmux

Go to platform.openai.com and log-in with your OpenAI account (register if you don't have one). Click on your name initial in the top-right corner, then select "View API keys". Finally click on "Create new secret key". That's it.

You may also need to add a payment method, clicking on Billing --> Payment methods. New accounts should have some free credits, but adding a payment method may still be mandatory. For pricing, check this page.

There are three alternatives.

a. Export the key as an env var: export OPENAI_API_KEY="<YOUR_KEY>"

b. Create a global configuration at $XDG_CONFIG_HOME/llmux/config.yaml or a local at ./llmux.yaml:

api-key: "YOUR_KEY"

c. Use the command line option --key <YOUR_KEY>.

The configuration priority order is: Command line option > Environment variable > Local configuration file > Global configuration file.

Run llmux. Then just chat!

The number next to the prompt is the tokens used in the conversation at that point.

Use the /q command to quit and show the number of total tokens used and an estimate of the expense for that session, based on the specific model in use.

model: "gpt-3.5-turbo"
markdown: false
max_tokens: 500
temperature: 1

ChatGPT CLI, by default, uses the original gpt-3.5-turbo model. In order to use other ChatGPT models, edit the model parameter in the config.yml file ore use the --model command line option. Here is a list of all the available options:

Pricing is calculated as $/1000 tokens.

Check this page for the technical details of each model.

Add the --multiline (or -ml) flag in order to toggle multi-line input mode. In this mode use Alt+Enter or Esc+Enter to submit messages.

Use the --context <FILE PATH> command line option (or -c as a short version) in order to provide the model an initial context (technically a system message for ChatGPT). For example:

llmux --context notes.txt

Both absolute and relative paths are accepted. Note that this option can be specified multiple times to give multiple files for context. Example:

llmux --context notes-from-thursday.txt --context notes-from-friday.txt

ChatGPT CLI saves all the past conversations (including context and token usage) in $XDG_DATA_HOME/llmux. In order to restore a session the --restore <YYYYMMDD-hhmmss> (or -r) option is available. For example:

llmux --restore 20230728-162302 restores the session from the $XDG_DATA_HOME/llmux/session-20230728-162302.json file. Then the chat goes on from that point.

It is also possible to use the special value last:

llmux --restore last

In this case it restores the last chat session, without specifying the timestamp.

Note that, if --restore is set, it overwrites any --context option.