Merge branch 'main' into litellm_fix_proxy_health_readiness

litellm/proxy/proxy_config.yaml

@@ -77,8 +77,10 @@ litellm_settings:
   cache_params:
     type: "redis-semantic"
     similarity_threshold: 0.8
-    redis_semantic_cache_use_async: True
-  # cache: True
+    redis_semantic_cache_embedding_model: azure-embedding-model
+  upperbound_key_generate_params:
+    max_budget: 100
+    duration: "30d"   
   # setting callback class
   # callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
 

litellm/tests/test_completion.py

@@ -41,7 +41,7 @@ def test_completion_custom_provider_model_name():
             messages=messages,
             logger_fn=logger_fn,
         )
-        # Add any assertions here to check the, response
+        # Add any assertions here to check the,response
         print(response)
         print(response["choices"][0]["finish_reason"])
     except litellm.Timeout as e:

requirements.txt

@@ -8,7 +8,7 @@ pyyaml>=6.0.1 # server dep
 uvicorn==0.22.0 # server dep
 gunicorn==21.2.0 # server dep
 boto3==1.28.58 # aws bedrock/sagemaker calls
-redis==4.6.0 # caching
+redis==5.0.0 # caching
 numpy==1.24.3 # semantic caching
 prisma==0.11.0 # for db
 mangum==0.17.0 # for aws lambda functions