github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-16 14:39:31 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

SSE streaming in Open WebUI API Endpoints (Chat Completions) fails to handle incomplete chunks #5032

New Issue
Closed
opened 2025-11-11 16:10:20 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-11 16:10:20 -06:00
Owner
Copy Link

Originally created by @hide212131 on GitHub (May 4, 2025).

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

main

Ollama Version (if applicable)

No response

Operating System

macOS Sequoia

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have listed steps to reproduce the bug in detail.

Expected Behavior

The Open WebUI Chat Completions API endpoint (/api/chat/completions) should properly handle SSE streaming messages that are split across multiple chunks, automatically combining incomplete lines with subsequent reads to form complete messages.

Actual Behavior

When using the Chat Completions API endpoint (/api/chat/completions) with streaming=true, SSE messages from certain backends (especially Java/Spring MVC/SseEmitter implementations) can be split across chunks. For example, a message starting with 'data: ' might arrive in one chunk, with its content arriving in the next chunk. The current implementation processes these fragments separately instead of combining them, resulting in malformed data in the client application.

Steps to Reproduce

  1. Run a Java-based SSE server (example: https://github.com/hide212131/openai-compatible-api-java-example)
  2. In Settings > Connections, specify localhost:8000
  3. Select 'mock-gpt-model' as the model and enter a conversation prompt

Logs & Screenshots

Image 
2025-05-04 15:24:46.671 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "OPTIONS /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {}
2025-05-04 15:24:46.722 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "POST /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {}
2025-05-04 15:24:46.726 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "OPTIONS /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-04 15:24:46.734 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-04 15:24:46.738 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "OPTIONS /api/chat/completions HTTP/1.1" 200 - {}
2025-05-04 15:24:46.745 | INFO     | open_webui.utils.chat:generate_direct_chat_completion:69 - generate_direct_chat_completion - {}
2025-05-04 15:24:46.759 | INFO     | open_webui.utils.chat:generate_direct_chat_completion:106 - res: {'status': True} - {}
2025-05-04 15:24:46.762 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "POST /api/chat/completions HTTP/1.1" 200 - {}
2025-05-04 15:24:46.772 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-04 15:24:50.047 | INFO     | open_webui.utils.chat:generate_direct_chat_completion:69 - generate_direct_chat_completion - {}
2025-05-04 15:24:50.051 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "OPTIONS /api/chat/completed HTTP/1.1" 200 - {}
2025-05-04 15:24:50.062 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "POST /api/chat/completed HTTP/1.1" 200 - {}
2025-05-04 15:24:50.071 | INFO     | open_webui.utils.chat:generate_direct_chat_completion:69 - generate_direct_chat_completion - {}
2025-05-04 15:24:50.075 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "POST /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {}
2025-05-04 15:24:50.077 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-04 15:24:50.080 | INFO     | open_webui.models.chats:count_chats_by_tag_name_and_user_id:817 - Count of chats for tag 'tag3': 0 - {}
2025-05-04 15:24:50.082 | INFO     | open_webui.models.chats:count_chats_by_tag_name_and_user_id:817 - Count of chats for tag 'tag1': 0 - {}
2025-05-04 15:24:50.083 | INFO     | open_webui.models.chats:count_chats_by_tag_name_and_user_id:817 - Count of chats for tag 'tag2': 0 - {}
2025-05-04 15:24:50.092 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-05-04 15:24:50.094 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "GET /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {}
2025-05-04 15:24:50.099 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "OPTIONS /api/v1/chats/all/tags HTTP/1.1" 200 - {}
2025-05-04 15:24:50.103 | INFO     | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "GET /api/v1/chats/all/tags HTTP/1.1" 200 - {}

Additional Information

No response

Originally created by @hide212131 on GitHub (May 4, 2025). ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version main ### Ollama Version (if applicable) _No response_ ### Operating System macOS Sequoia ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have listed steps to reproduce the bug in detail. ### Expected Behavior The Open WebUI Chat Completions API endpoint (/api/chat/completions) should properly handle SSE streaming messages that are split across multiple chunks, automatically combining incomplete lines with subsequent reads to form complete messages. ### Actual Behavior When using the Chat Completions API endpoint (/api/chat/completions) with streaming=true, SSE messages from certain backends (especially Java/Spring MVC/SseEmitter implementations) can be split across chunks. For example, a message starting with 'data: ' might arrive in one chunk, with its content arriving in the next chunk. The current implementation processes these fragments separately instead of combining them, resulting in malformed data in the client application. ### Steps to Reproduce 1. Run a Java-based SSE server (example: https://github.com/hide212131/openai-compatible-api-java-example) 2. In Settings > Connections, specify localhost:8000 3. Select 'mock-gpt-model' as the model and enter a conversation prompt ### Logs & Screenshots <img width="1686" alt="Image" src="https://github.com/user-attachments/assets/4c96b4ed-661e-4708-aaaa-bcfca54f6cd7" /> ``` 2025-05-04 15:24:46.671 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "OPTIONS /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {} 2025-05-04 15:24:46.722 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "POST /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {} 2025-05-04 15:24:46.726 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "OPTIONS /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-04 15:24:46.734 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-04 15:24:46.738 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "OPTIONS /api/chat/completions HTTP/1.1" 200 - {} 2025-05-04 15:24:46.745 | INFO | open_webui.utils.chat:generate_direct_chat_completion:69 - generate_direct_chat_completion - {} 2025-05-04 15:24:46.759 | INFO | open_webui.utils.chat:generate_direct_chat_completion:106 - res: {'status': True} - {} 2025-05-04 15:24:46.762 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "POST /api/chat/completions HTTP/1.1" 200 - {} 2025-05-04 15:24:46.772 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63779 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-04 15:24:50.047 | INFO | open_webui.utils.chat:generate_direct_chat_completion:69 - generate_direct_chat_completion - {} 2025-05-04 15:24:50.051 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "OPTIONS /api/chat/completed HTTP/1.1" 200 - {} 2025-05-04 15:24:50.062 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "POST /api/chat/completed HTTP/1.1" 200 - {} 2025-05-04 15:24:50.071 | INFO | open_webui.utils.chat:generate_direct_chat_completion:69 - generate_direct_chat_completion - {} 2025-05-04 15:24:50.075 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "POST /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {} 2025-05-04 15:24:50.077 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-04 15:24:50.080 | INFO | open_webui.models.chats:count_chats_by_tag_name_and_user_id:817 - Count of chats for tag 'tag3': 0 - {} 2025-05-04 15:24:50.082 | INFO | open_webui.models.chats:count_chats_by_tag_name_and_user_id:817 - Count of chats for tag 'tag1': 0 - {} 2025-05-04 15:24:50.083 | INFO | open_webui.models.chats:count_chats_by_tag_name_and_user_id:817 - Count of chats for tag 'tag2': 0 - {} 2025-05-04 15:24:50.092 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63799 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-05-04 15:24:50.094 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "GET /api/v1/chats/2fdfe2ca-4b5e-4f38-a59b-cf60d5d584d7 HTTP/1.1" 200 - {} 2025-05-04 15:24:50.099 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "OPTIONS /api/v1/chats/all/tags HTTP/1.1" 200 - {} 2025-05-04 15:24:50.103 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 127.0.0.1:63801 - "GET /api/v1/chats/all/tags HTTP/1.1" 200 - {} ``` ### Additional Information _No response_
GiteaMirror added the bug label 2025-11-11 16:10:20 -06:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#5032
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?