Pipeline with llamaindex streaming reponse does not work #133

New Issue

2026-02-15T19:16:12-05:00

yindo commented

2026-02-15 19:16:12 -05:00

Originally created by @Zeeeeta on GitHub (Sep 25, 2024).

I am using llamaindex with Open WebUI pipeline, following the example on https://github.com/open-webui/pipelines/blob/main/examples/pipelines/rag/llamaindex_pipeline.py

However, if I try to use streaming reponse like the example, returning with "return response.response_gen"
Open WebUI is unable to display any result and leaving the chat as below

There is no error.

Tried to run llamaindex streaming response locally with "response.print_response_stream()" does print the result word by word.

Any help would be appreciated, thank you.

Edit: My bad, my logging of debug messages caused that.

Originally created by @Zeeeeta on GitHub (Sep 25, 2024). I am using llamaindex with Open WebUI pipeline, following the example on https://github.com/open-webui/pipelines/blob/main/examples/pipelines/rag/llamaindex_pipeline.py However, if I try to use streaming reponse like the example, returning with "return response.response_gen" Open WebUI is unable to display any result and leaving the chat as below ![{E90B6BC6-0250-4882-A120-0A6C8F50ECF4}](https://github.com/user-attachments/assets/c191e769-a5bf-4883-af9d-9766f8e046f7) There is no error. Tried to run llamaindex streaming response locally with "response.print_response_stream()" does print the result word by word. Any help would be appreciated, thank you. **Edit: My bad, my logging of debug messages caused that.**

yindo closed this issue

2026-02-15 19:16:12 -05:00

yindo referenced this issue

2026-02-15 20:15:05 -05:00

[PR #133] [MERGED] refactor(examples/azure_openai_pipeline): make use of env variables and prefixed with a consistent prefix to avoid conflicts #321

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: open-webui/pipelines#133