Originally created by @xinhai-ai on GitHub (Mar 4, 2025).
Bug Report
Installation Method
git clone
Environment
Open WebUI Version: v0.5.18 dev version
Postgres:Latest: in local docker
Operating System: Windows 10
Browser (if applicable): Firefox
Confirmation:
I have read and followed all the instructions provided in the README.md.
I am on 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 provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
Description
When using an external database (e.g., PostgreSQL), fast model output with enabled functions causes abnormal database reads and abnormally slow output speeds. It appears that streaming responses are constantly requesting the database, resulting in performance degradation. I believe this issue is critical.
Reproduction Details
Steps to Reproduce:
An external database(e.g., PostgreSQL), A fast model (e.g. o3-mini or R1 70b) with an simple functions like
from pydantic import BaseModel, Field
from typing import Optional
class Filter:
def __init__(self):
pass
def inlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
return body
def outlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
return body
Originally created by @xinhai-ai on GitHub (Mar 4, 2025).
# Bug Report
## Installation Method
git clone
## Environment
- **Open WebUI Version:** v0.5.18 dev version
- **Postgres:Latest:** in local docker
- **Operating System:** Windows 10
- **Browser (if applicable):** Firefox
**Confirmation:**
- [x] I have read and followed all the instructions provided in the README.md.
- [x] I am on the latest version of both Open WebUI and Ollama.
- [ ] I have included the browser console logs.
- [ ] I have included the Docker container logs.
- [x] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
## Description
When using an external database (e.g., PostgreSQL), fast model output with enabled functions causes abnormal database reads and abnormally slow output speeds. It appears that streaming responses are constantly requesting the database, resulting in performance degradation. I believe this issue is critical.
## Reproduction Details
**Steps to Reproduce:**
An external database(e.g., PostgreSQL), A fast model (e.g. o3-mini or R1 70b) with an simple functions like
```
from pydantic import BaseModel, Field
from typing import Optional
class Filter:
def __init__(self):
pass
def inlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
return body
def outlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
return body
```
## Logs and Screenshots
**Screenshots/Screen Recordings (if applicable):**
https://github.com/user-attachments/assets/854a592d-8749-48fd-a25a-370f4a1561e3
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @xinhai-ai on GitHub (Mar 4, 2025).
Bug Report
Installation Method
git clone
Environment
Confirmation:
Description
When using an external database (e.g., PostgreSQL), fast model output with enabled functions causes abnormal database reads and abnormally slow output speeds. It appears that streaming responses are constantly requesting the database, resulting in performance degradation. I believe this issue is critical.
Reproduction Details
Steps to Reproduce:
An external database(e.g., PostgreSQL), A fast model (e.g. o3-mini or R1 70b) with an simple functions like
Logs and Screenshots
Screenshots/Screen Recordings (if applicable):
https://github.com/user-attachments/assets/854a592d-8749-48fd-a25a-370f4a1561e3
@tjbck commented on GitHub (Mar 4, 2025):
You should use
async.