mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-09 11:24:53 +00:00
fmt
This commit is contained in:
parent
ab32074fe2
commit
d845e377fd
@ -82,21 +82,21 @@ async fn health(infer: Extension<Infer>) -> Result<(), (StatusCode, Json<ErrorRe
|
||||
|
||||
/// Generate tokens
|
||||
#[utoipa::path(
|
||||
post,
|
||||
tag = "Text Generation Inference",
|
||||
path = "/generate",
|
||||
request_body = GenerateRequest,
|
||||
responses(
|
||||
(status = 200, description = "Generated Text", body = GenerateResponse),
|
||||
(status = 424, description = "Generation Error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Request failed during generation"})),
|
||||
(status = 429, description = "Model is overloaded", body = ErrorResponse,
|
||||
example = json ! ({"error": "Model is overloaded"})),
|
||||
(status = 422, description = "Input validation error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Input validation error"})),
|
||||
(status = 500, description = "Incomplete generation", body = ErrorResponse,
|
||||
example = json ! ({"error": "Incomplete generation"})),
|
||||
)
|
||||
post,
|
||||
tag = "Text Generation Inference",
|
||||
path = "/generate",
|
||||
request_body = GenerateRequest,
|
||||
responses(
|
||||
(status = 200, description = "Generated Text", body = GenerateResponse),
|
||||
(status = 424, description = "Generation Error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Request failed during generation"})),
|
||||
(status = 429, description = "Model is overloaded", body = ErrorResponse,
|
||||
example = json ! ({"error": "Model is overloaded"})),
|
||||
(status = 422, description = "Input validation error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Input validation error"})),
|
||||
(status = 500, description = "Incomplete generation", body = ErrorResponse,
|
||||
example = json ! ({"error": "Incomplete generation"})),
|
||||
)
|
||||
)]
|
||||
#[instrument(
|
||||
skip(infer),
|
||||
@ -204,26 +204,26 @@ async fn generate(
|
||||
|
||||
/// Generate a stream of token using Server-Sent Events
|
||||
#[utoipa::path(
|
||||
post,
|
||||
tag = "Text Generation Inference",
|
||||
path = "/generate_stream",
|
||||
request_body = GenerateRequest,
|
||||
responses(
|
||||
(status = 200, description = "Generated Text", body = StreamResponse,
|
||||
content_type = "text/event-stream"),
|
||||
(status = 424, description = "Generation Error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Request failed during generation"}),
|
||||
content_type = "text/event-stream"),
|
||||
(status = 429, description = "Model is overloaded", body = ErrorResponse,
|
||||
example = json ! ({"error": "Model is overloaded"}),
|
||||
content_type = "text/event-stream"),
|
||||
(status = 422, description = "Input validation error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Input validation error"}),
|
||||
content_type = "text/event-stream"),
|
||||
(status = 500, description = "Incomplete generation", body = ErrorResponse,
|
||||
example = json ! ({"error": "Incomplete generation"}),
|
||||
content_type = "text/event-stream"),
|
||||
)
|
||||
post,
|
||||
tag = "Text Generation Inference",
|
||||
path = "/generate_stream",
|
||||
request_body = GenerateRequest,
|
||||
responses(
|
||||
(status = 200, description = "Generated Text", body = StreamResponse,
|
||||
content_type = "text/event-stream"),
|
||||
(status = 424, description = "Generation Error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Request failed during generation"}),
|
||||
content_type = "text/event-stream"),
|
||||
(status = 429, description = "Model is overloaded", body = ErrorResponse,
|
||||
example = json ! ({"error": "Model is overloaded"}),
|
||||
content_type = "text/event-stream"),
|
||||
(status = 422, description = "Input validation error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Input validation error"}),
|
||||
content_type = "text/event-stream"),
|
||||
(status = 500, description = "Incomplete generation", body = ErrorResponse,
|
||||
example = json ! ({"error": "Incomplete generation"}),
|
||||
content_type = "text/event-stream"),
|
||||
)
|
||||
)]
|
||||
#[instrument(
|
||||
skip(infer),
|
||||
@ -365,10 +365,10 @@ async fn generate_stream(
|
||||
|
||||
/// Prometheus metrics scrape endpoint
|
||||
#[utoipa::path(
|
||||
get,
|
||||
tag = "Text Generation Inference",
|
||||
path = "/metrics",
|
||||
responses((status = 200, description = "Prometheus Metrics", body = String))
|
||||
get,
|
||||
tag = "Text Generation Inference",
|
||||
path = "/metrics",
|
||||
responses((status = 200, description = "Prometheus Metrics", body = String))
|
||||
)]
|
||||
async fn metrics(prom_handle: Extension<PrometheusHandle>) -> String {
|
||||
prom_handle.render()
|
||||
@ -393,35 +393,35 @@ pub async fn run(
|
||||
// OpenAPI documentation
|
||||
#[derive(OpenApi)]
|
||||
#[openapi(
|
||||
paths(
|
||||
generate,
|
||||
generate_stream,
|
||||
metrics,
|
||||
),
|
||||
components(
|
||||
schemas(
|
||||
GenerateRequest,
|
||||
GenerateParameters,
|
||||
PrefillToken,
|
||||
Token,
|
||||
GenerateResponse,
|
||||
Details,
|
||||
FinishReason,
|
||||
StreamResponse,
|
||||
StreamDetails,
|
||||
ErrorResponse,
|
||||
)
|
||||
),
|
||||
tags(
|
||||
(name = "Text Generation Inference", description = "Hugging Face Text Generation Inference API")
|
||||
),
|
||||
info(
|
||||
title = "Text Generation Inference",
|
||||
license(
|
||||
name = "Apache 2.0",
|
||||
url = "https://www.apache.org/licenses/LICENSE-2.0"
|
||||
)
|
||||
)
|
||||
paths(
|
||||
generate,
|
||||
generate_stream,
|
||||
metrics,
|
||||
),
|
||||
components(
|
||||
schemas(
|
||||
GenerateRequest,
|
||||
GenerateParameters,
|
||||
PrefillToken,
|
||||
Token,
|
||||
GenerateResponse,
|
||||
Details,
|
||||
FinishReason,
|
||||
StreamResponse,
|
||||
StreamDetails,
|
||||
ErrorResponse,
|
||||
)
|
||||
),
|
||||
tags(
|
||||
(name = "Text Generation Inference", description = "Hugging Face Text Generation Inference API")
|
||||
),
|
||||
info(
|
||||
title = "Text Generation Inference",
|
||||
license(
|
||||
name = "Apache 2.0",
|
||||
url = "https://www.apache.org/licenses/LICENSE-2.0"
|
||||
)
|
||||
)
|
||||
)]
|
||||
struct ApiDoc;
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user