phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

Merge pull request #2188 from BerriAI/litellm_fix_health_checks

Browse source 
[Fix] Fix health check when API base set for OpenAI compatible models
This commit is contained in:
Ishaan Jaff 2024-02-24 18:47:13 -08:00 • committed by GitHub
commit c8daf61592
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 12 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/my-website/docs/proxy/health.md
View file

@ -12,7 +12,7 @@ The proxy exposes:
#### Request
Make a GET Request to `/health` on the proxy
```shell
curl --location 'http://0.0.0.0:8000/health'
curl --location 'http://0.0.0.0:8000/health' -H "Authorization: Bearer sk-1234"
```
You can also run `litellm -health` it makes a `get` request to `http://0.0.0.0:8000/health` for you

12
litellm/llms/openai.py
View file

@ -772,9 +772,13 @@ class OpenAIChatCompletion(BaseLLM):
input: Optional[list] = None,
prompt: Optional[str] = None,
organization: Optional[str] = None,
api_base: Optional[str] = None,
):
client = AsyncOpenAI(
api_key=api_key, timeout=timeout, organization=organization
api_key=api_key,
timeout=timeout,
organization=organization,
base_url=api_base,
)
if model is None and mode != "image_generation":
raise Exception("model is not set")
@ -870,9 +874,9 @@ class OpenAITextCompletion(BaseLLM):
if "model" in response_object:
model_response_object.model = response_object["model"]
model_response_object._hidden_params[
"original_response"
] = response_object # track original response, if users make a litellm.text_completion() request, we can return the original response
model_response_object._hidden_params["original_response"] = (
response_object # track original response, if users make a litellm.text_completion() request, we can return the original response
)
return model_response_object
except Exception as e:
raise e

3
litellm/main.py
View file

@ -3358,12 +3358,15 @@ async def ahealth_check(
or default_timeout
)
api_base = model_params.get("api_base") or get_secret("OPENAI_API_BASE")
response = await openai_chat_completions.ahealth_check(
model=model,
messages=model_params.get(
"messages", None
), # Replace with your actual messages list
api_key=api_key,
api_base=api_base,
timeout=timeout,
mode=mode,
prompt=prompt,