scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 35

Fix HostedVLLMRerankConfig will not be used (#16352)

Browse source 
* Fix HostedVLLMRerankConfig will not be used

Signed-off-by: Jun-Fei Cherng <jfcherng@realtek.com>

* Fix no usage statistics in rerank with hosted_vllm

Signed-off-by: Jun-Fei Cherng <jfcherng@realtek.com>

* Revise typo in comment

Signed-off-by: Jun-Fei Cherng <jfcherng@realtek.com>

---------

Signed-off-by: Jun-Fei Cherng <jfcherng@realtek.com>
This commit is contained in:
Jack Cherng 2025-11-08 11:11:59 +08:00 • committed by GitHub
parent 0a527bd1d8
commit 2ab34f9a52
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 14 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
litellm/__init__.py
View file

@ -1098,6 +1098,7 @@ from .llms.azure_ai.rerank.transformation import AzureAIRerankConfig
from .llms.infinity.rerank.transformation import InfinityRerankConfig
from .llms.jina_ai.rerank.transformation import JinaAIRerankConfig
from .llms.deepinfra.rerank.transformation import DeepinfraRerankConfig
from .llms.hosted_vllm.rerank.transformation import HostedVLLMRerankConfig
from .llms.nvidia_nim.rerank.transformation import NvidiaNimRerankConfig
from .llms.vertex_ai.rerank.transformation import VertexAIRerankConfig
from .llms.clarifai.chat.transformation import ClarifaiConfig

2
litellm/llms/hosted_vllm/rerank/transformation.py
View file

@ -156,7 +156,7 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
f"Error parsing response: {raw_response.text}, status_code={raw_response.status_code}"
)
return RerankResponse(**raw_response_json)
return self._transform_response(raw_response_json)
def get_error_class(
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]

2
litellm/utils.py
View file

@ -7294,6 +7294,8 @@ class ProviderConfigManager:
return litellm.InfinityRerankConfig()
elif litellm.LlmProviders.JINA_AI == provider:
return litellm.JinaAIRerankConfig()
elif litellm.LlmProviders.HOSTED_VLLM == provider:
return litellm.HostedVLLMRerankConfig()
elif litellm.LlmProviders.HUGGINGFACE == provider:
return litellm.HuggingFaceRerankConfig()
elif litellm.LlmProviders.DEEPINFRA == provider:

10
tests/test_litellm/test_utils.py
View file

@ -845,6 +845,16 @@ def test_check_provider_match():
model_info = {"litellm_provider": "bedrock"}
assert litellm.utils._check_provider_match(model_info, "openai") is False
def test_get_provider_rerank_config():
"""
Test the get_provider_rerank_config function for various providers
"""
from litellm import HostedVLLMRerankConfig
from litellm.utils import LlmProviders, ProviderConfigManager
# Test for hosted_vllm provider
config = ProviderConfigManager.get_provider_rerank_config("my_model", LlmProviders.HOSTED_VLLM, 'http://localhost', [])
assert isinstance(config, HostedVLLMRerankConfig)
# Models that should be skipped during testing
OLD_PROVIDERS = ["aleph_alpha", "palm"]