phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(proxy_server.md): adding /ollama_logs endpoint to docs

Browse source
This commit is contained in:
Krrish Dholakia 2023-10-07 20:38:19 -07:00
parent a8c3871b02
commit a833e3f929
2 changed files with 11 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

11
docs/my-website/docs/proxy_server.md
View file

@ -223,6 +223,17 @@ litellm --model ollama/llama2 \
--temperature 0.5 --temperature 0.5
``` ```
## Ollama Logs
Ollama calls can sometimes fail (out-of-memory errors, etc.).
To see your logs just call
```shell
$ curl 'http://0.0.0.0:8000/ollama_logs'
```
This will return your logs from `~/.ollama/logs/server.log`.
## Deploy Proxy ## Deploy Proxy
<Tabs> <Tabs>

9
litellm/proxy/proxy_server.py
View file

@ -209,13 +209,4 @@ async def retrieve_server_log(request: Request):
filepath = os.path.expanduser('~/.ollama/logs/server.log') filepath = os.path.expanduser('~/.ollama/logs/server.log')
return FileResponse(filepath) return FileResponse(filepath)
# @router.get("/ollama_logs")
# async def chat_completion(request: Request):
# if platform.system() == "Darwin":
# print("This is a MacOS system.")
# elif platform.system() == "Linux":
# print("This is a Linux system.")
# else:
# print("This is an unknown operating system.")
app.include_router(router) app.include_router(router)