Skip to main content

LLMs for CLI

Project description

Gorilla CLI

Gorilla CLI powers your command-line interactions with a user-centric tool. Simply state your objective, and Gorilla CLI will generate potential commands for execution. Gorilla today supports ~1500 APIs, including Kubernetes, AWS, GCP, Azure, GitHub, Conda, Curl, Sed, and many more. No more recalling intricate CLI arguments! 🦍

Developed by UC Berkeley as a research prototype, Gorilla-CLI prioritizes user control and confidentiality:

  • Commands are executed solely with your explicit approval.
  • While we utilize queries and error logs (stderr) for model enhancement, we NEVER collect output data (stdout).

Getting Started

You can readily install Gorilla CLI via pip.

pip install gorilla-cli

Usage

Activate Gorilla CLI with gorilla followed by your task in plain English.

For instance, to generate a file with 100 random characters, type:

$ gorilla generate 100 random characters into a file called test.txt

or if you prefer, you can use quotes to avoid issues with string parsing:

$ gorilla "generate 100 random characters into a file called test.txt"

Gorilla CLI will then generate candidate commands. Use the arrow keys to navigate through the options, then press enter to execute the chosen command.

🦍  Welcome to Gorilla. Use arrows to select
 » cat /dev/urandom | env LC_ALL=C tr -dc 'a-zA-Z0-9' | head -c 100 > test.txt 
   echo $(head /dev/urandom | LC_CTYPE=C tr -dc 'a-zA-Z0-9' | dd bs=100 count=1) > test.txt
   dd if=/dev/urandom bs=1 count=100 of=test.txt

Some more examples

$ gorilla list all my GCP instances
» gcloud compute instances list --format="table(name,zone,status)"
  gcloud compute instances list --format table
  gcloud compute instances list --format="table(name, zone, machineType, status)"
$ gorilla get the image ids of all pods running in all namespaces in kubernetes
» kubectl get pods --all-namespaces -o jsonpath="{..imageID}"
  kubectl get pods --all --namespaces
  kubectl get pod -A -o jsonpath='{range .items[*]}{"\n"}{.metadata.name}{"\t"}{.spec.containers[].image}{"\n"}{end}'

How It Works

Gorilla-CLI fuses the capabilities of various Language Learning Models (LLMs) like Gorilla LLM, OpenAI's GPT-4, Claude v1, and others to present a user-friendly command-line interface. For each user query, we gather responses from all contributing LLMs, filter, sort, and present you with the most relevant options.

Contributions

We welcome your enhancements to Gorilla CLI! If you have improvements, feel free to submit a pull request on our GitHub page.

License

Gorilla CLI operates under the Apache 2.0 license. More details can be found in the LICENSE file. We'd also like to extend our appreciation to questionary for their fantastic UI!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gorilla-cli-0.0.10.tar.gz (29.0 kB view hashes)

Uploaded Source

Built Distribution

gorilla_cli-0.0.10-py3-none-any.whl (37.9 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page