Add router name to /info endpoint (#1854)

Add `router` key in `/info` endpoint and set it to
`env!("CARGO_PKG_NAME")` => so always set to `"text-generation-router"`
in TGI. Happy to change the naming if you think of a better one
(framework? package_name?)

The goal is to use this information in `InferenceClient` to know the
model is served with TGI. At the moment we can use
https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2/info
to infer it is TGI-served because it returns information but having a
proper key would be better.


For context, a transformers-served model is only outputting `{"ok":
"ok"}` (see
[here](https://api-inference.huggingface.co/models/microsoft/DialoGPT-large/info)).
This commit is contained in:
Lucain 2024-05-03 16:39:04 +02:00 committed by GitHub
parent a25737139d
commit bb2b2959a2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 0 deletions

View File

@ -159,6 +159,8 @@ pub struct Info {
#[schema(example = "32")]
pub max_client_batch_size: usize,
/// Router Info
#[schema(example = "text-generation-router")]
pub router: &'static str,
#[schema(example = "0.5.0")]
pub version: &'static str,
#[schema(nullable = true, example = "null")]

View File

@ -1564,6 +1564,7 @@ pub async fn run(
max_batch_size,
validation_workers,
max_client_batch_size,
router: env!("CARGO_PKG_NAME"),
version: env!("CARGO_PKG_VERSION"),
sha: option_env!("VERGEN_GIT_SHA"),
docker_label: option_env!("DOCKER_LABEL"),