te_request_count (method=single) is incremented twice for single requests

[hanizav]

System Info

Tei version: 1.4
Platform: Docker

Summary
A single "single" embed/predict request increments the te_request_count metric twice, causing request counts to be inflated.

Information

• Docker
• The CLI directly

Tasks

• An officially supported command
• My own modifications

Reproduction

Reproduction Steps

Scrape baseline te_request_count{method="single"}
Send a single embed request: curl http://localhost:8080/embed -X POST -H 'Content-Type: application/json' -d '{"inputs":"test"}'
Scrape te_request_count{method="single"} again
Observe that the metric increased by 2 for one request

Expected behavior

te_request_count{method="single"} should increase by exactly 1 for each single request.