diff --git a/demos/employee_details_copilot/bolt_config.yaml b/demos/employee_details_copilot/bolt_config.yaml
index 875f176d..1ad1d556 100644
--- a/demos/employee_details_copilot/bolt_config.yaml
+++ b/demos/employee_details_copilot/bolt_config.yaml
@@ -6,11 +6,6 @@ overrides:
   # confidence threshold for prompt target intent matching
   prompt_target_intent_matching_threshold: 0.8
 
-# should not be here
-embedding_provider:
-  name: "bge-large-en-v1.5"
-  model: "BAAI/bge-large-en-v1.5"
-
 llm_providers:
 
   - name: open-ai-gpt-4
diff --git a/demos/function_calling/bolt_config.yaml b/demos/function_calling/bolt_config.yaml
index 684ac5ba..5d7c6e3a 100644
--- a/demos/function_calling/bolt_config.yaml
+++ b/demos/function_calling/bolt_config.yaml
@@ -6,11 +6,6 @@ overrides:
   # confidence threshold for prompt target intent matching
   prompt_target_intent_matching_threshold: 0.6
 
-# should not be here
-embedding_provider:
-  name: "bge-large-en-v1.5"
-  model: "BAAI/bge-large-en-v1.5"
-
 llm_providers:
 
   - name: open-ai-gpt-4
diff --git a/demos/network_copilot/bolt_config.yaml b/demos/network_copilot/bolt_config.yaml
index f79955dc..3d9f6a82 100644
--- a/demos/network_copilot/bolt_config.yaml
+++ b/demos/network_copilot/bolt_config.yaml
@@ -6,11 +6,6 @@ overrides:
   # confidence threshold for prompt target intent matching
   prompt_target_intent_matching_threshold: 0.7
 
-# should not be here
-embedding_provider:
-  name: "bge-large-en-v1.5"
-  model: "BAAI/bge-large-en-v1.5"
-
 llm_providers:
 
   - name: open-ai-gpt-4
diff --git a/demos/prompt_guards/bolt_config.yaml b/demos/prompt_guards/bolt_config.yaml
index d9de7632..21a78983 100644
--- a/demos/prompt_guards/bolt_config.yaml
+++ b/demos/prompt_guards/bolt_config.yaml
@@ -2,12 +2,6 @@ default_prompt_endpoint: "127.0.0.1"
 load_balancing: "round_robin"
 timeout_ms: 5000
 
-
-# should not be here
-embedding_provider:
-  name: "bge-large-en-v1.5"
-  model: "BAAI/bge-large-en-v1.5"
-
 llm_providers:
 
   - name: open-ai-gpt-4
diff --git a/envoyfilter/katanemo-config.yaml b/envoyfilter/katanemo-config.yaml
index ce894965..273902c3 100644
--- a/envoyfilter/katanemo-config.yaml
+++ b/envoyfilter/katanemo-config.yaml
@@ -2,10 +2,6 @@ default_prompt_endpoint: "127.0.0.1"
 load_balancing: "round_robin"
 timeout_ms: 5000
 
-embedding_provider:
-  name: "SentenceTransformer"
-  model: "all-MiniLM-L6-v2"
-
 llm_providers:
 
   - name: "open-ai-gpt-4"
diff --git a/envoyfilter/tests/integration.rs b/envoyfilter/tests/integration.rs
index afcac01d..6651f16e 100644
--- a/envoyfilter/tests/integration.rs
+++ b/envoyfilter/tests/integration.rs
@@ -153,10 +153,6 @@ default_prompt_endpoint: "127.0.0.1"
 load_balancing: "round_robin"
 timeout_ms: 5000
 
-embedding_provider:
-  name: "SentenceTransformer"
-  model: "all-MiniLM-L6-v2"
-
 llm_providers:
   - name: "open-ai-gpt-4"
     api_key: "$OPEN_AI_API_KEY"
diff --git a/public_types/src/configuration.rs b/public_types/src/configuration.rs
index 40c481f1..3a0de1d9 100644
--- a/public_types/src/configuration.rs
+++ b/public_types/src/configuration.rs
@@ -11,7 +11,6 @@ pub struct Configuration {
     pub load_balancing: LoadBalancing,
     pub timeout_ms: u64,
     pub overrides: Option<Overrides>,
-    pub embedding_provider: EmbeddingProviver,
     pub llm_providers: Vec<LlmProvider>,
     pub prompt_guards: Option<PromptGuard>,
     pub system_prompt: Option<String>,
@@ -132,10 +131,6 @@ default_prompt_endpoint: "127.0.0.1"
 load_balancing: "round_robin"
 timeout_ms: 5000
 
-embedding_provider:
-  name: "SentenceTransformer"
-  model: "all-MiniLM-L6-v2"
-
 llm_providers:
   - name: "open-ai-gpt-4"
     api_key: "$OPEN_AI_API_KEY"