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.
Expected Behavior:
Filter work well when leaving the conversation before it stopped
Actual Behavior:
Filter not work when leaving the conversation before it stopped
Description
Bug Summary:
Filter not work when leaving the conversation before it stopped
Reproduction Details
Steps to Reproduce:
I make a simple Filter to reproduce.
from pydantic import BaseModel, Field
from typing import Optional
class Filter:
class Valves(BaseModel):
priority: int = Field(
default=0, description="Priority level for the filter operations."
)
pass
class UserValves(BaseModel):
pass
def __init__(self):
self.valves = self.Valves()
pass
def inlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
print("Start !")
return body
def outlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
print("Filter worked!")
return body
and a model named test1 with the Filter (base model is gemini-2.0-flash-exp)
i tell tell me 1000 words about you to the model
when i didn't leave the conversation,the Filter worked well
the docker logs are here
INFO: IP:0 - "POST /api/v1/chats/27070a2c-b6fc-465d-8fc0-45986faecefa HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO [open_webui.routers.openai] get_all_models()
Start !
INFO: IP:0 - "GET /c/27070a2c-b6fc-465d-8fc0-45986faecefa HTTP/1.1" 200 OK
INFO: IP:0 - "POST /api/chat/completions HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO: IP:0 - "GET / HTTP/1.1" 200 OK
INFO [open_webui.routers.openai] get_all_models()
Filter worked!
INFO: IP:0 - "POST /api/chat/completed HTTP/1.1" 200 OK
but when I left the conversation before it stopped, something was wrong
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO [open_webui.routers.openai] get_all_models()
Start !
INFO: IP:0 - "POST /api/chat/completions HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/ba981aee-e91b-4ba4-9510-0f55bc74d60f HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/ba981aee-e91b-4ba4-9510-0f55bc74d60f/tags HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK
INFO: IP:0 - "GET /ollama/api/version HTTP/1.1" 200 OK
In this steps, I switch to another conversation after press enter
the words Filter worked! didn't appear, even if switch back
Logs and Screenshots
Docker Container Logs:
Additional Information
[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]
Originally created by @xinhai-ai on GitHub (Jan 23, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8795
# Bug Report
---
## Installation Method
docker
## Environment
- **Open WebUI Version:** [v0.5.6]
- **Operating System:** [Debian GNU/Linux 12]
- **Browser (if applicable):** [chrome 131.0.6778.265]
**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.
- [x] 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.
## Expected Behavior:
Filter work well when leaving the conversation before it stopped
## Actual Behavior:
Filter not work when leaving the conversation before it stopped
## Description
**Bug Summary:**
Filter not work when leaving the conversation before it stopped
## Reproduction Details
**Steps to Reproduce:**
I make a simple Filter to reproduce.
```
from pydantic import BaseModel, Field
from typing import Optional
class Filter:
class Valves(BaseModel):
priority: int = Field(
default=0, description="Priority level for the filter operations."
)
pass
class UserValves(BaseModel):
pass
def __init__(self):
self.valves = self.Valves()
pass
def inlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
print("Start !")
return body
def outlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
print("Filter worked!")
return body
```
and a model named test1 with the Filter (base model is gemini-2.0-flash-exp)
i tell `tell me 1000 words about you` to the model
when i didn't leave the conversation,the Filter worked well
the docker logs are here
```
INFO: IP:0 - "POST /api/v1/chats/27070a2c-b6fc-465d-8fc0-45986faecefa HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO [open_webui.routers.openai] get_all_models()
Start !
INFO: IP:0 - "GET /c/27070a2c-b6fc-465d-8fc0-45986faecefa HTTP/1.1" 200 OK
INFO: IP:0 - "POST /api/chat/completions HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO: IP:0 - "GET / HTTP/1.1" 200 OK
INFO [open_webui.routers.openai] get_all_models()
Filter worked!
INFO: IP:0 - "POST /api/chat/completed HTTP/1.1" 200 OK
```
but when I left the conversation before it stopped, something was wrong
```
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO [open_webui.routers.openai] get_all_models()
Start !
INFO: IP:0 - "POST /api/chat/completions HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/ba981aee-e91b-4ba4-9510-0f55bc74d60f HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/chats/ba981aee-e91b-4ba4-9510-0f55bc74d60f/tags HTTP/1.1" 200 OK
INFO: IP:0 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK
INFO: IP:0 - "GET /ollama/api/version HTTP/1.1" 200 OK
```
In this steps, I switch to another conversation after press enter
the words `Filter worked!` didn't appear, even if switch back
## Logs and Screenshots
**Docker Container Logs:**
## Additional Information
[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]
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 (Jan 23, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8795
Bug Report
Installation Method
docker
Environment
Open WebUI Version: [v0.5.6]
Operating System: [Debian GNU/Linux 12]
Browser (if applicable): [chrome 131.0.6778.265]
Confirmation:
Expected Behavior:
Filter work well when leaving the conversation before it stopped
Actual Behavior:
Filter not work when leaving the conversation before it stopped
Description
Bug Summary:
Filter not work when leaving the conversation before it stopped
Reproduction Details
Steps to Reproduce:
I make a simple Filter to reproduce.
and a model named test1 with the Filter (base model is gemini-2.0-flash-exp)
i tell
tell me 1000 words about youto the modelwhen i didn't leave the conversation,the Filter worked well
the docker logs are here
but when I left the conversation before it stopped, something was wrong
In this steps, I switch to another conversation after press enter
the words
Filter worked!didn't appear, even if switch backLogs and Screenshots
Docker Container Logs:
Additional Information
[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]