mirror of
https://github.com/open-webui/open-webui.git
synced 2026-11-13 17:58:56 -06:00
[GH-ISSUE #16831] issue: embedding generation to chat completion takes time (approx 3min) #72666
Reference in New Issue
Block a user
Originally created by @zeeshanyshaikh on GitHub (Aug 22, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16831
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.25
Ollama Version (if applicable)
No response
Operating System
Ubuntu 20
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
The chat completion request should be dispatched to the model immediately after payload assembly. Once the embeddings are generated, chat completion should be immediately triggered without delay
Actual Behavior
from the logs it can be seen that between embedding generation and chat completion there is approx 3min delay which (from logs) seems nothing is happening (even is log is set to debug)
Steps to Reproduce
When making a POST /api/chat/completions request, there is a ~3 minute delay between when the request reaches the server and when the payload is actually sent to the model backend. Logs show retrieval finishing quickly, but the actual completion request isn’t dispatched until much later.
Steps to reproduce:
Logs & Screenshots
Additional Information
Added timing checkpoints but no INFO logs appeared in Docker — possibly logging config issue. Using print should confirm where the delay is.
@tjbck commented on GitHub (Aug 28, 2025):
We're unable to reproduce, keep us updated!