fish-ai
adds AI functionality to Fish shell. It
should run on any system with Python and git installed.
Originally based on Tom DΓΆrr's fish.codex
repository,
but with some additional functionality.
It can be hooked up to OpenAI, Azure OpenAI, Google, Hugging Face, or a self-hosted LLM behind any OpenAI-compatible API.
If you like it, please add a β. If you don't like it, create a PR. π
Create a configuration file ~/.config/fish-ai.ini
.
If you use a self-hosted LLM:
[fish-ai]
configuration = self-hosted
[self-hosted]
provider = self-hosted
server = https://<your server>:<port>/v1
model = <your model>
api_key = <your API key>
If you are self-hosting, my recommendation is to use
Ollama with
Llama 3 70B. An out of the box
configuration running on localhost
could then look something
like this:
[fish-ai]
configuration = local-llama
[local-llama]
provider = self-hosted
server = http://localhost:11434/v1
model = llama3
If you use OpenAI:
[fish-ai]
configuration = openai
[openai]
provider = openai
model = gpt-4-turbo
api_key = <your API key>
organization = <your organization>
If you use Azure OpenAI:
[fish-ai]
configuration = azure
[azure]
provider = azure
server = https://<your instance>.openai.azure.com
model = <your deployment name>
api_key = <your API key>
If you use Gemini:
[fish-ai]
configuration = gemini
[gemini]
provider = google
api_key = <your API key>
If you use Hugging Face:
[fish-ai]
configuration = huggingface
[huggingface]
provider = huggingface
email = <your email>
password = <your password>
model = meta-llama/Meta-Llama-3-70B-Instruct
Available models are listed here. Note that 2FA must be disabled on the account.
Install the plugin. You can install it using fisher
.
fisher install realiserad/fish-ai
For detailed installation instructions tailored for your distribution, see the installation tests.
Type a comment (anything starting with #
), and press Ctrl + P to turn it
into shell command!
You can also run it in reverse. Type a command and press Ctrl + P to turn it into a comment explaining what the command does.
Begin typing your command and press Ctrl + Space to display a list of
completions in fzf
(it is bundled
with the plugin, no need to install it separately). Completions load in the
background and show up as they become available.
If a command fails, you can immediately press Ctrl + Space at the command prompt
to let fish-ai
suggest a fix!
You can tweak the behaviour of fish-ai
by putting additional options in the
active section of your fish-ai.ini
file.
To explain shell commands in a different language, set the language
option
to the name of the language. For example:
[fish-ai]
configuration = foo
[foo]
language = Swedish
This will only work well if the LLM you are using has been trained on a dataset with the chosen language.
Temperature is a decimal number between 0 and 1 controlling the randomness of
the output. Higher values make the LLM more creative, but may impact accuracy.
The default value is 0.2
.
Here is an example of how to increase the temperature to 0.5
.
[fish-ai]
configuration = foo
[foo]
temperature = 0.5
This option is not supported when using the huggingface
provider.
To change the number of completions suggested by the LLM when pressing
Ctrl + Space, set the completions
option. The default value is 5
.
Here is an example of how you can increase the number of completions to 10
:
[fish-ai]
configuration = foo
[foo]
completions = 10
You can personalise completions suggested by the LLM by sending an excerpt of your commandline history.
To enable it, specify the maximum number of commands from the history
to send to the LLM using the history_size
option. The default value
is 0
(do not send any commandline history).
[fish-ai]
configuration = foo
[foo]
history_size = 5
You can switch between different sections in the configuration using the
fish_ai_switch_context
command.
When using the plugin, fish-ai
submits the name of your OS and the
commandline buffer to the LLM.
When you codify a command, it also sends the contents of any files you mention (as long as the file is readable), and when you explain or autocomplete a command, the manpage of the current command is provided to the LLM for reference.
fish-ai
can also send an exerpt of your command line history
when autocompleting a command. This is disabled by default.
Finally, to fix the previous command, the previous commandline buffer, along with any terminal output and the corresponding exit code is sent to the LLM.
If you are concerned with data privacy, you should use a self-hosted LLM. When hosted locally, no data ever leaves your machine.
This repository ships with a devcontainer.json
which can be used with
GitHub Codespaces or Visual Studio Code with
the Dev Containers extension.
To install fish-ai
from a local copy, use fisher
:
fisher install .
Enable debug logging by putting debug = True
in your fish-ai.ini
.
Logging is done to syslog by default (if available). You can also enable
logging to file using log = <path to file>
, for example:
[fish-ai]
configuration = foo
[foo]
debug = True
log = ~/.fish-ai/log.txt
The installation tests
are packaged into containers and can be executed locally with e.g. docker
.
docker build -f tests/ubuntu-22/Dockerfile .
docker build -f tests/fedora-40/Dockerfile .
docker build -f tests/archlinux-base/Dockerfile .
The Python modules containing most of the business logic can be tested using
pytest
.