LiteLLM Minor Fixes & Improvement (11/14/2024) (#6730)

* fix(ollama.py): fix get model info request

Fixes https://github.com/BerriAI/litellm/issues/6703

* feat(anthropic/chat/transformation.py): support passing user id to anthropic via openai 'user' param

* docs(anthropic.md): document all supported openai params for anthropic

* test: fix tests

* fix: fix tests

* feat(jina_ai/): add rerank support

Closes https://github.com/BerriAI/litellm/issues/6691

* test: handle service unavailable error

* fix(handler.py): refactor together ai rerank call

* test: update test to handle overloaded error

* test: fix test

* Litellm router trace (#6742)

* feat(router.py): add trace_id to parent functions - allows tracking retry/fallbacks

* feat(router.py): log trace id across retry/fallback logic

allows grouping llm logs for the same request

* test: fix tests

* fix: fix test

* fix(transformation.py): only set non-none stop_sequences

* Litellm router disable fallbacks (#6743)

* bump: version 1.52.6 → 1.52.7

* feat(router.py): enable dynamically disabling fallbacks

Allows for enabling/disabling fallbacks per key

* feat(litellm_pre_call_utils.py): support setting 'disable_fallbacks' on litellm key

* test: fix test

* fix(exception_mapping_utils.py): map 'model is overloaded' to internal server error

* test: handle gemini error

* test: fix test

* fix: new run

litellm/rerank_api/main.py

@@ -8,7 +8,8 @@ from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.azure_ai.rerank import AzureAIRerank
 from litellm.llms.cohere.rerank import CohereRerank
-from litellm.llms.together_ai.rerank import TogetherAIRerank
+from litellm.llms.jina_ai.rerank.handler import JinaAIRerank
+from litellm.llms.together_ai.rerank.handler import TogetherAIRerank
 from litellm.secret_managers.main import get_secret
 from litellm.types.rerank import RerankRequest, RerankResponse
 from litellm.types.router import *
@@ -19,6 +20,7 @@ from litellm.utils import client, exception_type, supports_httpx_timeout
 cohere_rerank = CohereRerank()
 together_rerank = TogetherAIRerank()
 azure_ai_rerank = AzureAIRerank()
+jina_ai_rerank = JinaAIRerank()
 #################################################
 
 
@@ -247,7 +249,23 @@ def rerank(
                 api_key=api_key,
                 _is_async=_is_async,
             )
+        elif _custom_llm_provider == "jina_ai":
 
+            if dynamic_api_key is None:
+                raise ValueError(
+                    "Jina AI API key is required, please set 'JINA_AI_API_KEY' in your environment"
+                )
+            response = jina_ai_rerank.rerank(
+                model=model,
+                api_key=dynamic_api_key,
+                query=query,
+                documents=documents,
+                top_n=top_n,
+                rank_fields=rank_fields,
+                return_documents=return_documents,
+                max_chunks_per_doc=max_chunks_per_doc,
+                _is_async=_is_async,
+            )
         else:
             raise ValueError(f"Unsupported provider: {_custom_llm_provider}")