Fix HostedVLLMRerankConfig will not be used (#16352)

* 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>

litellm/__init__.py

@@ -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

litellm/llms/hosted_vllm/rerank/transformation.py

@@ -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]

litellm/utils.py

@@ -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:

tests/test_litellm/test_utils.py

@@ -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"]