search

looker-open-source / looker-explore-assistant

A React Application for interacting with Looker data through natural language.
MIT License
103 stars 68 forks source link

Install / Prerequisite Instructions Need More Detail #6

Closed markrittman closed 7 months ago

markrittman commented 7 months ago

Hi,

The install instructions in the readme file don't work unless, I suspect, the reader has all of the development software already pre-installed that Luka has on his development workstation.

For example, running them on my Mac (Sonoma 14.3 with Intel CPU):

  1. git clone git@github.com:LukaFontanilla/looker-explore-assistant.git

gives the error message: `"Cloning into 'looker-explore-assistant'... git@github.com: Permission denied (publickey). fatal: Could not read from remote repository.

Please make sure you have the correct access rights and the repository exists."`

and instead I have to use git clone https://github.com/LukaFontanilla/looker-explore-assistant.git

  1. The steps that use Terraform e.g. terraform init, terraform apply etc need Terraform to be first installed, which on my Mac needs me to run:
brew tap hashicorp/tap
brew install hashicorp/tap/terraform

which then errors unless I've run brew install gcc, which then requires me to run xcode-select --install .. etc etc

Could you either (1) update the install instructions to either list-out what needs to be installed to make the development environment sufficient to then run you instructions, correcting the git step so that it works without a private/public key, or (2) is there a way you can pre-build the code, as has been done with the other Gen AI Extension Framework example that's available for Looker that include another take on natural-language querying of Looker explores?

Btw - great work on this example and thanks for making it available ;-)

Mark

LukaFontanilla commented 7 months ago

Hey Mark - thank you for the callout on the pre-requisites. Yes, a git ssh-config, npm & terraform and/or gcloud installed are required to deploy this extension. We can make an update to link to the relevant documentation to be followed depending on the OS type.

RE: bundling the Extension source code. I would love to have this pre-bundled, but there are a few ways the extension is configured that will prevent that:

  1. The extension is setup to be deployed and trained on one explore at a time.
  2. The extension has starter queries that are categorized for a given use case, this will need to be swapped for the dataset connected.
  3. The extension follows a database agnostic approach, by deploying the LLM integration as a separate API and not in the database layer and that API endpoint URL we can't anticipate ahead of time.

On this note, we've considered adding a command line package that guides the user through deployment of resources with customization per deployment. That could be something we can look into again.

Your feedback is appreciated!

LukaFontanilla commented 7 months ago

We've added a few new enhancements in the latest release. Namely documentation additions (pre-requisites in each step, optional install via cloud shell, and a BQ deployment version). Thanks for the feedback in helping us improve the solution!

markrittman commented 7 months ago

Excellent, I'll take a look through it and provide feedback if there's any remaining challenges - thanks!