Update response type for `/v1/chat/completions` and `/v1/completions` (#1747)
`/v1/chat/completions` and `/v1/completions` have different output types depending on the `stream` parameter. This PR aims at fixing the inconsistency in the auto-generated [openapi.json](https://huggingface.github.io/text-generation-inference/openapi.json) specs. cc @OlivierDehaene @drbh I reused what had been done for the `/` endpoint but haven't tested anything myself. Could you confirm this is the correct way of handling things? Also, should I update the openapi.json file manually? If yes, how can I do it?
This commit is contained in:
parent
7276d43495
commit
00f365353e
|
@ -548,7 +548,11 @@ async fn generate_stream_internal(
|
|||
path = "/v1/completions",
|
||||
request_body = CompletionRequest,
|
||||
responses(
|
||||
(status = 200, description = "Generated Text", body = ChatCompletionChunk),
|
||||
(status = 200, description = "Generated Chat Completion",
|
||||
content(
|
||||
("application/json" = Completion),
|
||||
("text/event-stream" = CompletionCompleteChunk),
|
||||
)),
|
||||
(status = 424, description = "Generation Error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Request failed during generation"})),
|
||||
(status = 429, description = "Model is overloaded", body = ErrorResponse,
|
||||
|
@ -652,7 +656,7 @@ async fn completions(
|
|||
})
|
||||
.map_or_else(
|
||||
|e| {
|
||||
println!("Failed to serialize ChatCompletionChunk: {:?}", e);
|
||||
println!("Failed to serialize CompletionCompleteChunk: {:?}", e);
|
||||
Event::default()
|
||||
},
|
||||
|data| data,
|
||||
|
@ -725,7 +729,11 @@ async fn completions(
|
|||
path = "/v1/chat/completions",
|
||||
request_body = ChatRequest,
|
||||
responses(
|
||||
(status = 200, description = "Generated Text", body = ChatCompletionChunk),
|
||||
(status = 200, description = "Generated Chat Completion",
|
||||
content(
|
||||
("application/json" = ChatCompletion),
|
||||
("text/event-stream" = ChatCompletionChunk),
|
||||
)),
|
||||
(status = 424, description = "Generation Error", body = ErrorResponse,
|
||||
example = json ! ({"error": "Request failed during generation"})),
|
||||
(status = 429, description = "Model is overloaded", body = ErrorResponse,
|
||||
|
|
Loading…
Reference in New Issue