huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Record request parameters in OTel span for /v1/chat/completions endpoint

Browse Source
This commit is contained in:
Alex Weston 2025-02-07 13:16:49 -05:00
parent 4b8cda684b
commit b0e66983be
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
router/src/server.rs
View File

@ -1217,7 +1217,7 @@ example = json ! ({"error": "Incomplete generation"})),
#[instrument( #[instrument(
skip_all, skip_all,
fields( fields(
// parameters = ? req.parameters, parameters,
total_time, total_time,
validation_time, validation_time,
queue_time, queue_time,
@ -1243,7 +1243,7 @@ pub(crate) async fn chat_completions(
} = chat.clone(); } = chat.clone();
let (generate_request, using_tools): (GenerateRequest, bool) = let (generate_request, using_tools): (GenerateRequest, bool) =
chat.try_into_generate(&infer)?; chat.try_into_generate(&infer)?;
span.record("parameters", format!("{:?}", generate_request.parameters));
let logprobs = logprobs.unwrap_or_default(); let logprobs = logprobs.unwrap_or_default();
// extract model id from request if specified // extract model id from request if specified