diff --git a/docs/my-website/docs/proxy/embedding.md b/docs/my-website/docs/proxy/embedding.md
new file mode 100644
index 000000000..ed724beed
--- /dev/null
+++ b/docs/my-website/docs/proxy/embedding.md
@@ -0,0 +1,42 @@
+# Embeddings 
+Route between Sagemaker, Bedrock, Azure embeddings
+
+
+Here's how to route between GPT-J embedding (sagemaker endpoint), Amazon Titan embedding (Bedrock) and Azure OpenAI embedding on the proxy server: 
+
+1. Save them in your config.yaml
+```yaml
+model_list:
+  - model_name: sagemaker-embeddings
+    litellm_params: 
+      model: "sagemaker/berri-benchmarking-gpt-j-6b-fp16"
+  - model_name: amazon-embeddings
+    litellm_params:
+      model: "bedrock/amazon.titan-embed-text-v1"
+  - model_name: azure-embeddings
+    litellm_params: 
+      model: "azure/azure-embedding-model"
+      api_base: "os.environ/AZURE_API_BASE" # os.getenv("AZURE_API_BASE")
+      api_key: "os.environ/AZURE_API_KEY" # os.getenv("AZURE_API_KEY")
+      api_version: "2023-07-01-preview"
+
+general_settings:
+  master_key: sk-1234 # [OPTIONAL] if set all calls to proxy will require either this key or a valid generated token
+```
+
+2. Start the proxy
+```shell
+$ litellm --config /path/to/config.yaml
+```
+
+3. Test the embedding call
+
+```shell
+curl --location 'http://0.0.0.0:8000/v1/embeddings' \
+--header 'Authorization: Bearer sk-1234' \
+--header 'Content-Type: application/json' \
+--data '{
+    "input": "The food was delicious and the waiter..",
+    "model": "sagemaker-embeddings",
+}'
+```
\ No newline at end of file
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 11f81fa4d..12fa7ec9b 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -96,7 +96,8 @@ const sidebars = {
       },
       items: [
         "proxy/quick_start", 
-        "proxy/configs", 
+        "proxy/configs",
+        "proxy/embedding", 
         "proxy/load_balancing", 
         "proxy/virtual_keys",
         "proxy/model_management",
diff --git a/litellm/tests/test_custom_callback_input.py b/litellm/tests/test_custom_callback_input.py
index a2258a170..73bb913c9 100644
--- a/litellm/tests/test_custom_callback_input.py
+++ b/litellm/tests/test_custom_callback_input.py
@@ -127,7 +127,6 @@ class CompletionCustomHandler(CustomLogger): # https://docs.litellm.ai/docs/obse
             assert isinstance(kwargs['original_response'], (str, litellm.CustomStreamWrapper))
             assert isinstance(kwargs['additional_args'], (dict, type(None)))
             assert isinstance(kwargs['log_event_type'], str) 
-            assert isinstance(kwargs["cache_hit"], Optional[bool])
         except:
             print(f"Assertion Error: {traceback.format_exc()}")
             self.errors.append(traceback.format_exc())