UniqAI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2024-11-22 08:07:55 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Added timeout setting for ollama streaming response

Browse Source
This commit is contained in:
Mikael Turøy 2024-06-12 22:37:35 +02:00
parent bdd2ac0015
commit e130ad74d1
3 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
TROUBLESHOOTING.md
View File

@ -18,6 +18,10 @@ If you're experiencing connection issues, it’s often due to the WebUI docker c
docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
```
### Error on Slow Reponses for Ollama
Open WebUI has a default timeout of 15 minutes for Ollama to finish generating the response. If needed, this can be adjusted via the environment variable OLLAMA_GENERATE_TIMEOUT, which sets the timeout in seconds.
### General Connection Errors
**Ensure Ollama Version is Up-to-Date**: Always start by checking that you have the latest version of Ollama. Visit [Ollama's official site](https://ollama.com/) for the latest updates.

3
backend/apps/ollama/main.py
View File

@ -46,6 +46,7 @@ from config import (
SRC_LOG_LEVELS,
OLLAMA_BASE_URLS,
ENABLE_OLLAMA_API,
OLLAMA_GENERATE_TIMEOUT,
ENABLE_MODEL_FILTER,
MODEL_FILTER_LIST,
UPLOAD_DIR,
@ -154,7 +155,7 @@ async def cleanup_response(
async def post_streaming_url(url: str, payload: str):
r = None
try:
session = aiohttp.ClientSession(trust_env=True)
session = aiohttp.ClientSession(trust_env=True, timeout=aiohttp.ClientTimeout(total=OLLAMA_GENERATE_TIMEOUT))
r = await session.post(url, data=payload)
r.raise_for_status()

1
backend/config.py
View File

@ -425,6 +425,7 @@ OLLAMA_API_BASE_URL = os.environ.get(
)
OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
OLLAMA_GENERATE_TIMEOUT = int(os.environ.get("OLLAMA_GENERATE_TIMEOUT", "900"))
K8S_FLAG = os.environ.get("K8S_FLAG", "")
USE_OLLAMA_DOCKER = os.environ.get("USE_OLLAMA_DOCKER", "false")