[CLI] llama-stack-client CLI for querying server distro #3
Conversation
|
I should be able to just configure the client cli to point to a host by providing an API key if needed. $ llama-stack-client configure After that, I should be able to do: $ llama-stack-client <models|memory_banks|shields> <list|get> without having to specify host/port each time. |
ashwinb
left a comment
There was a problem hiding this comment.
Requesting changes mainly for Raghu's comment on doing a configuration first and then reusing those values for contacting the distribution server.
A small nit -- can the cli directory be placed until src/llama_stack_client instead of inside src/llama_stack_client/lib/
I put it to |
ashwinb
left a comment
There was a problem hiding this comment.
This looks pretty reasonable to me, but I want to have @raghotham take one look at it since he has had a lot of thoughts on how precisely this needs to work.
| type=str, | ||
| help="Llama Stack distribution port number", | ||
| ) | ||
| self.parser.add_argument( |
There was a problem hiding this comment.
I don't think we should have this one if we have separate host and port arguments. It feels confusing.
There was a problem hiding this comment.
I was thinking that if we have an endpoint like https://llama-stack.together.ai, we don't need to specify separate host:port args.
|
|
||
| self.endpoint = get_config().get("endpoint") | ||
| self.parser.add_argument( | ||
| "--endpoint", |
There was a problem hiding this comment.
So I think @raghotham wanted things to work like the aws CLI. i.e., there's a notion of a "profile"... its default value is "default". And you can update the default. And then each command gets an optional "profile" name which it uses to look up the corresponding YAML and gets all its values from there.
Specifically, we should never have an endpoint here (and in all commands) but only a "name" which represents a link to the YAML.
There was a problem hiding this comment.
Hmm, my understanding is that for now we only have endpoint to store in "profile", but I could remove this --endpoint s.t. we read from "profile" config only.
| f.write( | ||
| yaml.dump( | ||
| { | ||
| "endpoint": endpoint, |
There was a problem hiding this comment.
currently saves endpoint only, could introduce a map later if we want to store different endpoints.
These are the changes we had made on top of whatever Stainless generates. We are going to get them into this repository now so (a) future updates can just be simple PRs from Stainless and (b) we can directly publish from the repository.
Automated Release PR --- ## 0.1.0-alpha.3 (2025-06-27) Full Changelog: [v0.1.0-alpha.2...v0.1.0-alpha.3](llamastack/llama-stack-client-python@v0.1.0-alpha.2...v0.1.0-alpha.3) ### Features * **api:** update via SDK Studio ([e87f225](llamastack@e87f225)) * make custom code changes ([llamastack#3](llamastack#3)) ([83fa371](llamastack@83fa371)) --- This pull request is managed by Stainless's [GitHub App](https://github.com/apps/stainless-app). The [semver version number](https://semver.org/#semantic-versioning-specification-semver) is based on included [commit messages](https://www.conventionalcommits.org/en/v1.0.0/). Alternatively, you can manually set the version number in the title of this pull request. For a better experience, it is recommended to use either rebase-merge or squash-merge when merging this pull request. 🔗 Stainless [website](https://www.stainlessapi.com) 📚 Read the [docs](https://app.stainlessapi.com/docs) 🙋 [Reach out](mailto:[email protected]) for help or questions --------- Co-authored-by: stainless-app[bot] <142633134+stainless-app[bot]@users.noreply.github.com>
CLI Reference
llama-stack-client$ llama-stack-client -h usage: llama-stack-client [-h] {models,memory_banks,shields} ... Welcome to the LlamaStackClient CLI options: -h, --help show this help message and exit subcommands: {models,memory_banks,shields}llama-stack-client configurellama-stack-client models listllama-stack-client models getllama-stack-client memory_banks listllama-stack-client shields list