diff --git a/DSL/CronManager/DSL/store_in_vault.yml b/DSL/CronManager/DSL/store_in_vault.yml
index 63522a1..3052219 100644
--- a/DSL/CronManager/DSL/store_in_vault.yml
+++ b/DSL/CronManager/DSL/store_in_vault.yml
@@ -2,4 +2,4 @@ store_secrets:
   trigger: off
   type: exec
   command: "/app/scripts/store_secrets_in_vault.sh"
-  allowedEnvs: ['cookie', 'connectionId','llmPlatform', 'llmModel','secretKey','accessKey','deploymentName','targetUrl','apiKey','embeddingModel','embeddingPlatform','embeddingModelApiKey','deploymentEnvironment']
\ No newline at end of file
+  allowedEnvs: ['cookie', 'connectionId','llmPlatform', 'llmModel','secretKey','accessKey','deploymentName','targetUrl','apiKey','embeddingModel','embeddingPlatform','embeddingAccessKey','embeddingSecretKey','embeddingDeploymentName','embeddingTargetUri','embeddingAzureApiKey','deploymentEnvironment']
\ No newline at end of file
diff --git a/DSL/Liquibase/changelog/rag-search-script-v1-llm-connections.sql b/DSL/Liquibase/changelog/rag-search-script-v1-llm-connections.sql
index 55cccd2..6367462 100644
--- a/DSL/Liquibase/changelog/rag-search-script-v1-llm-connections.sql
+++ b/DSL/Liquibase/changelog/rag-search-script-v1-llm-connections.sql
@@ -1,39 +1,40 @@
 -- Schema for LLM Connections
 CREATE TABLE llm_connections (
+    -- Metadata
     id SERIAL PRIMARY KEY,
     connection_name VARCHAR(255) NOT NULL DEFAULT '',
-    -- LLM Model Configuration
-    llm_platform VARCHAR(100) NOT NULL,       -- e.g. Azure AI, OpenAI
-    llm_model VARCHAR(100) NOT NULL,          -- e.g. GPT-4o
-    
-    -- Embedding Model Configuration
-    embedding_platform VARCHAR(100) NOT NULL, -- e.g. Azure AI, OpenAI
-    embedding_model VARCHAR(100) NOT NULL,    -- e.g. Ada-200-1
-    
-    -- Budget and Usage Tracking
-    monthly_budget NUMERIC(12,2) NOT NULL,    -- e.g. 1000.00
-    used_budget NUMERIC(12,2) DEFAULT 0.00,  -- e.g. 250.00
-    warn_budget_threshold NUMERIC(5) DEFAULT 80, -- percentage to warn at
-    stop_budget_threshold NUMERIC(5) DEFAULT 100, -- percentage to stop at
-    disconnect_on_budget_exceed BOOLEAN DEFAULT TRUE,
-    
-    -- Metadata
     connection_status VARCHAR(50) DEFAULT 'active',      -- active / inactive
     created_at TIMESTAMP DEFAULT NOW(),
     environment VARCHAR(50) NOT NULL,
 
-    -- Mocked Credentials and Access Info
+    -- LLM Model Configuration
+    llm_platform VARCHAR(100) NOT NULL,       -- e.g. Azure AI, OpenAI
+    llm_model VARCHAR(100) NOT NULL,          -- e.g. GPT-4o
     -- Azure
     deployment_name VARCHAR(150),  -- for Azure deployments
     target_uri TEXT,                -- for custom endpoints
     api_key TEXT,                   -- secured api key mocked here
-
     -- AWS Bedrock
     secret_key TEXT,
     access_key TEXT, 
 
-    -- Embedding Model 
-    embedding_model_api_key TEXT
+    -- Embedding Model Configuration
+    embedding_platform VARCHAR(100) NOT NULL, -- e.g. Azure AI, OpenAI
+    embedding_model VARCHAR(100) NOT NULL,    -- e.g. Ada-200-1
+    -- Azure
+    embedding_deployment_name VARCHAR(150),  -- for Azure deployments
+    embedding_target_uri TEXT,                -- for custom endpoints
+    embedding_azure_api_key TEXT,                   -- secured api key mocked here
+    -- AWS Bedrock
+    embedding_secret_key TEXT,
+    embedding_access_key TEXT,
+
+    -- Budget and Usage Tracking
+    monthly_budget NUMERIC(12,2) NOT NULL,    -- e.g. 1000.00
+    used_budget NUMERIC(12,2) DEFAULT 0.00,  -- e.g. 250.00
+    warn_budget_threshold NUMERIC(5) DEFAULT 80, -- percentage to warn at
+    stop_budget_threshold NUMERIC(5) DEFAULT 100, -- percentage to stop at
+    disconnect_on_budget_exceed BOOLEAN DEFAULT TRUE
 );
 
 CREATE TABLE inference_results (
diff --git a/DSL/Resql/rag-search/POST/get-llm-connection.sql b/DSL/Resql/rag-search/POST/get-llm-connection.sql
index 30fdb93..a1128df 100644
--- a/DSL/Resql/rag-search/POST/get-llm-connection.sql
+++ b/DSL/Resql/rag-search/POST/get-llm-connection.sql
@@ -21,7 +21,11 @@ SELECT
     secret_key,
     access_key,
     -- Embedding model credentials
-    embedding_model_api_key
+    embedding_access_key,
+    embedding_secret_key,
+    embedding_deployment_name,
+    embedding_target_uri,
+    embedding_azure_api_key
 FROM llm_connections
 WHERE id = :connection_id
   AND connection_status <> 'deleted';
diff --git a/DSL/Resql/rag-search/POST/get-llm-connections-paginated.sql b/DSL/Resql/rag-search/POST/get-llm-connections-paginated.sql
index 419d7bc..faf1600 100644
--- a/DSL/Resql/rag-search/POST/get-llm-connections-paginated.sql
+++ b/DSL/Resql/rag-search/POST/get-llm-connections-paginated.sql
@@ -14,7 +14,6 @@ SELECT
     connection_status,
     created_at,
     CEIL(COUNT(*) OVER() / :page_size::DECIMAL) AS totalPages,
-    -- Calculate budget status based on usage percentage and configured thresholds
     CASE 
         WHEN used_budget IS NULL OR used_budget = 0 OR (used_budget::DECIMAL / monthly_budget::DECIMAL) < (warn_budget_threshold::DECIMAL / 100.0) THEN 'within_budget'
         WHEN stop_budget_threshold != 0 AND (used_budget::DECIMAL / monthly_budget::DECIMAL) >= (stop_budget_threshold::DECIMAL / 100.0) THEN 'over_budget'
diff --git a/DSL/Resql/rag-search/POST/get-production-connection-filtered.sql b/DSL/Resql/rag-search/POST/get-production-connection-filtered.sql
new file mode 100644
index 0000000..4d5ced0
--- /dev/null
+++ b/DSL/Resql/rag-search/POST/get-production-connection-filtered.sql
@@ -0,0 +1,54 @@
+SELECT 
+    id,
+    connection_name,
+    llm_platform,
+    llm_model,
+    embedding_platform,
+    embedding_model,
+    monthly_budget,
+    warn_budget_threshold,
+    stop_budget_threshold,
+    disconnect_on_budget_exceed,
+    used_budget,
+    environment,
+    connection_status,
+    created_at,
+    deployment_name,
+    target_uri,
+    api_key,
+    secret_key,
+    access_key,
+    embedding_secret_key,
+    embedding_access_key,
+    embedding_deployment_name,
+    embedding_target_uri,
+    embedding_azure_api_key,
+    -- Calculate budget status based on usage percentage and configured thresholds
+    CASE 
+        WHEN used_budget IS NULL OR used_budget = 0 OR (used_budget::DECIMAL / monthly_budget::DECIMAL) < (warn_budget_threshold::DECIMAL / 100.0) THEN 'within_budget'
+        WHEN stop_budget_threshold != 0 AND (used_budget::DECIMAL / monthly_budget::DECIMAL) >= (stop_budget_threshold::DECIMAL / 100.0) THEN 'over_budget'
+        WHEN stop_budget_threshold = 0 AND (used_budget::DECIMAL / monthly_budget::DECIMAL) >= 1 THEN 'over_budget'
+        WHEN (used_budget::DECIMAL / monthly_budget::DECIMAL) >= (warn_budget_threshold::DECIMAL / 100.0) THEN 'close_to_exceed'
+        ELSE 'within_budget'
+    END AS budget_status
+FROM llm_connections
+WHERE environment = 'production'
+    AND connection_status <> 'deleted'
+    AND (:llm_platform IS NULL OR :llm_platform = '' OR llm_platform = :llm_platform)
+    AND (:llm_model IS NULL OR :llm_model = '' OR llm_model = :llm_model)
+    AND (:embedding_platform IS NULL OR :embedding_platform = '' OR embedding_platform = :embedding_platform)
+    AND (:embedding_model IS NULL OR :embedding_model = '' OR embedding_model = :embedding_model)
+    AND (:connection_status IS NULL OR :connection_status = '' OR connection_status = :connection_status)
+ORDER BY
+    CASE WHEN :sorting = 'connection_name asc' THEN connection_name END ASC,
+    CASE WHEN :sorting = 'connection_name desc' THEN connection_name END DESC,
+    CASE WHEN :sorting = 'llm_platform asc' THEN llm_platform END ASC,
+    CASE WHEN :sorting = 'llm_platform desc' THEN llm_platform END DESC,
+    CASE WHEN :sorting = 'llm_model asc' THEN llm_model END ASC,
+    CASE WHEN :sorting = 'llm_model desc' THEN llm_model END DESC,
+    CASE WHEN :sorting = 'monthly_budget asc' THEN monthly_budget END ASC,
+    CASE WHEN :sorting = 'monthly_budget desc' THEN monthly_budget END DESC,
+    CASE WHEN :sorting = 'created_at asc' THEN created_at END ASC,
+    CASE WHEN :sorting = 'created_at desc' THEN created_at END DESC,
+    created_at DESC  -- Default fallback sorting
+LIMIT 1;
diff --git a/DSL/Resql/rag-search/POST/insert-llm-connection.sql b/DSL/Resql/rag-search/POST/insert-llm-connection.sql
index c4d9679..29465ce 100644
--- a/DSL/Resql/rag-search/POST/insert-llm-connection.sql
+++ b/DSL/Resql/rag-search/POST/insert-llm-connection.sql
@@ -16,7 +16,11 @@ INSERT INTO llm_connections (
     api_key,
     secret_key,
     access_key,
-    embedding_model_api_key
+    embedding_access_key,
+    embedding_secret_key,
+    embedding_deployment_name,
+    embedding_target_uri,
+    embedding_azure_api_key
 ) VALUES (
     :connection_name,
     :llm_platform,
@@ -35,7 +39,11 @@ INSERT INTO llm_connections (
     :api_key,
     :secret_key,
     :access_key,
-    :embedding_model_api_key
+    :embedding_access_key,
+    :embedding_secret_key,
+    :embedding_deployment_name,
+    :embedding_target_uri,
+    :embedding_azure_api_key
 ) RETURNING 
     id, 
     connection_name,
@@ -55,4 +63,8 @@ INSERT INTO llm_connections (
     api_key,
     secret_key,
     access_key,
-    embedding_model_api_key;
+    embedding_secret_key,
+    embedding_access_key,
+    embedding_deployment_name,
+    embedding_target_uri,
+    embedding_azure_api_key
diff --git a/DSL/Resql/rag-search/POST/update-llm-connection-environment.sql b/DSL/Resql/rag-search/POST/update-llm-connection-environment.sql
index c16b98c..5b894c9 100644
--- a/DSL/Resql/rag-search/POST/update-llm-connection-environment.sql
+++ b/DSL/Resql/rag-search/POST/update-llm-connection-environment.sql
@@ -20,5 +20,4 @@ RETURNING
     target_uri,
     api_key,
     secret_key,
-    access_key,
-    embedding_model_api_key;
+    access_key;
diff --git a/DSL/Resql/rag-search/POST/update-llm-connection-status.sql b/DSL/Resql/rag-search/POST/update-llm-connection-status.sql
index 463936e..f71194a 100644
--- a/DSL/Resql/rag-search/POST/update-llm-connection-status.sql
+++ b/DSL/Resql/rag-search/POST/update-llm-connection-status.sql
@@ -19,5 +19,4 @@ RETURNING
     target_uri,
     api_key,
     secret_key,
-    access_key,
-    embedding_model_api_key;
+    access_key;
diff --git a/DSL/Resql/rag-search/POST/update-llm-connection.sql b/DSL/Resql/rag-search/POST/update-llm-connection.sql
index a442227..e4fa4fd 100644
--- a/DSL/Resql/rag-search/POST/update-llm-connection.sql
+++ b/DSL/Resql/rag-search/POST/update-llm-connection.sql
@@ -18,7 +18,12 @@ SET
     secret_key = :secret_key,
     access_key = :access_key,
     -- Embedding model credentials
-    embedding_model_api_key = :embedding_model_api_key
+    -- Embedding platform specific credentials
+    embedding_access_key = :embedding_access_key,
+    embedding_secret_key = :embedding_secret_key,
+    embedding_deployment_name = :embedding_deployment_name,
+    embedding_target_uri = :embedding_target_uri,
+    embedding_azure_api_key = :embedding_azure_api_key
 WHERE id = :connection_id
 RETURNING 
     id, 
@@ -39,4 +44,8 @@ RETURNING
     api_key,
     secret_key,
     access_key,
-    embedding_model_api_key;
+    embedding_secret_key,
+    embedding_access_key,
+    embedding_deployment_name,
+    embedding_target_uri,
+    embedding_azure_api_key;
diff --git a/DSL/Ruuter.private/rag-search/GET/llm-connections/production.yml b/DSL/Ruuter.private/rag-search/GET/llm-connections/production.yml
index be75219..b64e046 100644
--- a/DSL/Ruuter.private/rag-search/GET/llm-connections/production.yml
+++ b/DSL/Ruuter.private/rag-search/GET/llm-connections/production.yml
@@ -1,15 +1,57 @@
 declaration:
   call: declare
   version: 0.1
-  description: "Get production LLM connection"
+  description: "Get production LLM connection with optional filters"
   method: get
   returns: json
   namespace: rag-search
+  allowlist:
+    params:
+      - field: llmPlatform
+        type: string
+        description: "Filter by LLM platform"
+      - field: llmModel
+        type: string
+        description: "Filter by LLM model"
+      - field: embeddingPlatform
+        type: string
+        description: "Filter by embedding platform"
+      - field: embeddingModel
+        type: string
+        description: "Filter by embedding model"
+      - field: connectionStatus
+        type: string
+        description: "Filter by connection status"
+      - field: sortBy
+        type: string
+        description: "Field to sort by"
+      - field: sortOrder
+        type: string
+        description: "Sort order: 'asc' or 'desc'"
+
+extract_request_data:
+  assign:
+    llmPlatform: ${incoming.params.llmPlatform ?? ""}
+    llmModel: ${incoming.params.llmModel ?? ""}
+    embeddingPlatform: ${incoming.params.embeddingPlatform ?? ""}
+    embeddingModel: ${incoming.params.embeddingModel ?? ""}
+    connectionStatus: ${incoming.params.connectionStatus ?? ""}
+    sortBy: ${incoming.params.sortBy ?? "created_at"}
+    sortOrder: ${incoming.params.sortOrder ?? "desc"}
+    sorting: ${sortBy + " " + sortOrder}
+  next: get_production_connection
 
 get_production_connection:
   call: http.post
   args:
-    url: "[#RAG_SEARCH_RESQL]/get-production-connection"
+    url: "[#RAG_SEARCH_RESQL]/get-production-connection-filtered"
+    body:
+      llm_platform: ${llmPlatform}
+      llm_model: ${llmModel}
+      embedding_platform: ${embeddingPlatform}
+      embedding_model: ${embeddingModel}
+      connection_status: ${connectionStatus}
+      sorting: ${sorting}
   result: connection_result
   next: return_success
 
diff --git a/DSL/Ruuter.private/rag-search/POST/llm-connections/add.yml b/DSL/Ruuter.private/rag-search/POST/llm-connections/add.yml
index dffe487..5e7326a 100644
--- a/DSL/Ruuter.private/rag-search/POST/llm-connections/add.yml
+++ b/DSL/Ruuter.private/rag-search/POST/llm-connections/add.yml
@@ -56,9 +56,23 @@ declaration:
         type: string
         description: "AWS access key"
       # Embedding model credentials
-      - field: embedding_model_api_key
+      # Embedding AWS Bedrock credentials
+      - field: embedding_access_key
         type: string
-        description: "Embedding model API key"
+        description: "AWS access key for embedding model"
+      - field: embedding_secret_key
+        type: string
+        description: "AWS secret key for embedding model"
+      # Embedding Azure credentials
+      - field: embedding_deployment_name
+        type: string
+        description: "Azure embedding deployment name"
+      - field: embedding_target_uri
+        type: string
+        description: "Azure embedding endpoint URI"
+      - field: embedding_azure_api_key
+        type: string
+        description: "Azure embedding API key"
 
 extract_request_data:
   assign:
@@ -77,7 +91,12 @@ extract_request_data:
     api_key: ${incoming.body.api_key || ""}
     secret_key: ${incoming.body.secret_key || ""}
     access_key: ${incoming.body.access_key || ""}
-    embedding_model_api_key: ${incoming.body.embedding_model_api_key || ""}
+    # Embedding platform specific credentials
+    embedding_access_key: ${incoming.body.embedding_access_key || ""}
+    embedding_secret_key: ${incoming.body.embedding_secret_key || ""}
+    embedding_deployment_name: ${incoming.body.embedding_deployment_name || ""}
+    embedding_target_uri: ${incoming.body.embedding_target_uri || ""}
+    embedding_azure_api_key: ${incoming.body.embedding_azure_api_key || ""}
     created_at: ${new Date().toISOString()}
   next: validate_environment
 
@@ -138,7 +157,12 @@ add_llm_connection:
       api_key: ${api_key}
       secret_key: ${secret_key}
       access_key: ${access_key}
-      embedding_model_api_key: ${embedding_model_api_key}
+      # Embedding platform specific credentials
+      embedding_access_key: ${embedding_access_key}
+      embedding_secret_key: ${embedding_secret_key}
+      embedding_deployment_name: ${embedding_deployment_name}
+      embedding_target_uri: ${embedding_target_uri}
+      embedding_azure_api_key: ${embedding_azure_api_key}
   result: connection_result
   next: assign_connection_response
 
diff --git a/DSL/Ruuter.private/rag-search/POST/llm-connections/edit.yml b/DSL/Ruuter.private/rag-search/POST/llm-connections/edit.yml
index 420f3ca..84b375d 100644
--- a/DSL/Ruuter.private/rag-search/POST/llm-connections/edit.yml
+++ b/DSL/Ruuter.private/rag-search/POST/llm-connections/edit.yml
@@ -56,9 +56,23 @@ declaration:
       - field: access_key
         type: string
         description: "AWS access key"
-      - field: embedding_model_api_key
+      # Embedding AWS Bedrock credentials
+      - field: embedding_access_key
         type: string
-        description: "Embedding model API key"
+        description: "AWS access key for embedding model"
+      - field: embedding_secret_key
+        type: string
+        description: "AWS secret key for embedding model"
+      # Embedding Azure credentials
+      - field: embedding_deployment_name
+        type: string
+        description: "Azure embedding deployment name"
+      - field: embedding_target_uri
+        type: string
+        description: "Azure embedding endpoint URI"
+      - field: embedding_azure_api_key
+        type: string
+        description: "Azure embedding API key"
 
 extract_request_data:
   assign:
@@ -78,7 +92,12 @@ extract_request_data:
     api_key: ${incoming.body.api_key || ""}
     secret_key: ${incoming.body.secret_key || ""}
     access_key: ${incoming.body.access_key || ""}
-    embedding_model_api_key: ${incoming.body.embedding_model_api_key || ""}
+    # Embedding platform specific credentials
+    embedding_access_key: ${incoming.body.embedding_access_key || ""}
+    embedding_secret_key: ${incoming.body.embedding_secret_key || ""}
+    embedding_deployment_name: ${incoming.body.embedding_deployment_name || ""}
+    embedding_target_uri: ${incoming.body.embedding_target_uri || ""}
+    embedding_azure_api_key: ${incoming.body.embedding_azure_api_key || ""}
     updated_at: ${new Date().toISOString()}
   next: validate_environment
 
@@ -124,7 +143,12 @@ update_llm_connection:
       api_key: ${api_key}
       secret_key: ${secret_key}
       access_key: ${access_key}
-      embedding_model_api_key: ${embedding_model_api_key}
+      # Embedding platform specific credentials
+      embedding_access_key: ${embedding_access_key}
+      embedding_secret_key: ${embedding_secret_key}
+      embedding_deployment_name: ${embedding_deployment_name}
+      embedding_target_uri: ${embedding_target_uri}
+      embedding_azure_api_key: ${embedding_azure_api_key}
   result: connection_result
   next: return_success
 
diff --git a/DSL/Ruuter.private/rag-search/POST/vault/secret/create.yml b/DSL/Ruuter.private/rag-search/POST/vault/secret/create.yml
index e05d015..96501b3 100644
--- a/DSL/Ruuter.private/rag-search/POST/vault/secret/create.yml
+++ b/DSL/Ruuter.private/rag-search/POST/vault/secret/create.yml
@@ -38,9 +38,23 @@ declaration:
       - field: embeddingPlatform
         type: string
         description: "Body field 'embeddingPlatform'"
-      - field: embeddingModelApiKey
+      # Embedding AWS Bedrock credentials
+      - field: embeddingAccessKey
         type: string
-        description: "Body field 'embeddingModelApiKey'"
+        description: "Body field 'embeddingAccessKey'"
+      - field: embeddingSecretKey
+        type: string
+        description: "Body field 'embeddingSecretKey'"
+      # Embedding Azure credentials
+      - field: embeddingDeploymentName
+        type: string
+        description: "Body field 'embeddingDeploymentName'"
+      - field: embeddingTargetUri
+        type: string
+        description: "Body field 'embeddingTargetUri'"
+      - field: embeddingAzureApiKey
+        type: string
+        description: "Body field 'embeddingAzureApiKey'"
       - field: deploymentEnvironment
         type: string
         description: "Body field 'deploymentEnvironment'"
@@ -61,7 +75,13 @@ extract_request_data:
     apiKey: ${incoming.body.apiKey}
     embeddingModel: ${incoming.body.embeddingModel}
     embeddingPlatform: ${incoming.body.embeddingPlatform}
-    embeddingModelApiKey: ${incoming.body.embeddingModelApiKey}
+    # Embedding AWS Bedrock credentials
+    embeddingAccessKey: ${incoming.body.embeddingAccessKey}
+    embeddingSecretKey: ${incoming.body.embeddingSecretKey}
+    # Embedding Azure credentials
+    embeddingDeploymentName: ${incoming.body.embeddingDeploymentName}
+    embeddingTargetUri: ${incoming.body.embeddingTargetUri}
+    embeddingAzureApiKey: ${incoming.body.embeddingAzureApiKey}
     deploymentEnvironment: ${incoming.body.deploymentEnvironment}
     cookie: ${incoming.headers.cookie}
   next: check_provider
@@ -87,7 +107,9 @@ execute_aws_request:
       accessKey: ${accessKey}
       embeddingModel: ${embeddingModel}
       embeddingPlatform: ${embeddingPlatform}
-      embeddingModelApiKey: ${embeddingModelApiKey}
+      # Embedding AWS Bedrock credentials
+      embeddingAccessKey: ${embeddingAccessKey}
+      embeddingSecretKey: ${embeddingSecretKey}
       deploymentEnvironment: ${deploymentEnvironment}
   result: cron_aws_res
   next: return_aws_ok
@@ -106,7 +128,10 @@ execute_azure_request:
       apiKey: ${apiKey}
       embeddingModel: ${embeddingModel}
       embeddingPlatform: ${embeddingPlatform}
-      embeddingModelApiKey: ${embeddingModelApiKey}
+      # Embedding Azure credentials
+      embeddingDeploymentName: ${embeddingDeploymentName}
+      embeddingTargetUri: ${embeddingTargetUri}
+      embeddingAzureApiKey: ${embeddingAzureApiKey}
       deploymentEnvironment: ${deploymentEnvironment}
   result: cron_azure_res
   next: return_azure_ok
diff --git a/GUI/src/components/MainNavigation/index.tsx b/GUI/src/components/MainNavigation/index.tsx
index 2c7d73b..2ae1c70 100644
--- a/GUI/src/components/MainNavigation/index.tsx
+++ b/GUI/src/components/MainNavigation/index.tsx
@@ -34,6 +34,12 @@ const MainNavigation: FC = () => {
       label: 'Test LLM',
       path: '/test-llm',
       icon: <MdSearch />
+    },
+    {
+      id: 'testProductionLLM',
+      label: 'Test Production LLM',
+      path: '/test-production-llm',
+      icon: <MdSearch />
     }
   ];
 
diff --git a/GUI/src/components/molecules/LLMConnectionForm/index.tsx b/GUI/src/components/molecules/LLMConnectionForm/index.tsx
index 04557de..a86e7bd 100644
--- a/GUI/src/components/molecules/LLMConnectionForm/index.tsx
+++ b/GUI/src/components/molecules/LLMConnectionForm/index.tsx
@@ -38,6 +38,13 @@ export type LLMConnectionFormData = {
   apiKey?: string;
   // Embedding model credentials
   embeddingModelApiKey?: string;
+  // Embedding AWS Bedrock credentials
+  embeddingAccessKey?: string;
+  embeddingSecretKey?: string;
+  // Embedding Azure credentials
+  embeddingDeploymentName?: string;
+  embeddingTargetUri?: string;
+  embeddingAzureApiKey?: string;
 };
 
 type LLMConnectionFormProps = {
@@ -71,7 +78,6 @@ const LLMConnectionForm: React.FC<LLMConnectionFormProps> = ({
       llmModel: '',
       embeddingModelPlatform: '',
       embeddingModel: '',
-      embeddingModelApiKey: '',
       monthlyBudget: '',
       warnBudget: '',
       stopBudget: '',
@@ -85,6 +91,14 @@ const LLMConnectionForm: React.FC<LLMConnectionFormProps> = ({
       targetUri: '',
       apiKey: '',
       // Embedding model credentials
+      embeddingModelApiKey: '',
+      // Embedding AWS Bedrock credentials
+      embeddingAccessKey: '',
+      embeddingSecretKey: '',
+      // Embedding Azure credentials
+      embeddingDeploymentName: '',
+      embeddingTargetUri: '',
+      embeddingAzureApiKey: '',
       ...defaultValues,
     },
     mode: 'onChange',
@@ -126,6 +140,10 @@ const embeddingModelOptions = toOptions(embeddingModelsData);
   const [secretKeyReplaceMode, setSecretKeyReplaceMode] = React.useState(isEditing);
   const [accessKeyReplaceMode, setAccessKeyReplaceMode] = React.useState(isEditing);
   const [embeddingApiKeyReplaceMode, setEmbeddingApiKeyReplaceMode] = React.useState(isEditing);
+  // Embedding platform specific replace modes
+  const [embeddingSecretKeyReplaceMode, setEmbeddingSecretKeyReplaceMode] = React.useState(isEditing);
+  const [embeddingAccessKeyReplaceMode, setEmbeddingAccessKeyReplaceMode] = React.useState(isEditing);
+  const [embeddingAzureApiKeyReplaceMode, setEmbeddingAzureApiKeyReplaceMode] = React.useState(isEditing);
 
   const resetLLMCredentialFields = () => {
     setValue('accessKey', '');
@@ -144,9 +162,18 @@ const embeddingModelOptions = toOptions(embeddingModelsData);
   const resetEmbeddingModelCredentialFields = () => {
     setValue('embeddingModelApiKey', '');
     setValue('embeddingModel', '');
+    // Reset embedding platform specific fields
+    setValue('embeddingAccessKey', '');
+    setValue('embeddingSecretKey', '');
+    setValue('embeddingDeploymentName', '');
+    setValue('embeddingTargetUri', '');
+    setValue('embeddingAzureApiKey', '');
 
-    // Reset replace mode state when platform changes
+    // Reset replace mode states when platform changes
     setEmbeddingApiKeyReplaceMode(false);
+    setEmbeddingSecretKeyReplaceMode(false);
+    setEmbeddingAccessKeyReplaceMode(false);
+    setEmbeddingAzureApiKeyReplaceMode(false);
   };
   // Model options based on selected platform
   const getLLMModelOptions = () => {
@@ -315,6 +342,165 @@ const embeddingModelOptions = toOptions(embeddingModelsData);
     }
   };
 
+  const renderEmbeddingPlatformSpecificFields = () => {
+    switch (selectedEmbeddingPlatform) {
+      case 'aws':
+        return (
+          <>
+            <div className="form-row">
+              <p className='form-label'>Embedding Access Key</p>
+              <p className='form-description'>AWS Access Key for Bedrock embedding service</p>
+              <Controller
+                name="embeddingAccessKey"
+                control={control}
+                rules={{ required: 'Embedding Access Key is required for AWS Bedrock' }}
+                render={({ field }) => (
+                  <FormInput
+                    label=""
+                    type={isEditing ? 'text' : 'password'}
+                    placeholder="Enter AWS Access Key for embeddings"
+                    error={errors.embeddingAccessKey?.message}
+                    readOnly={embeddingAccessKeyReplaceMode}
+                    showEndButton={embeddingAccessKeyReplaceMode}
+                    onEndButtonClick={() => {
+                      setEmbeddingAccessKeyReplaceMode(false);
+                      setValue('embeddingAccessKey', '');
+                    }}
+                    endButtonText="Change"
+                    {...field}
+                  />
+                )}
+              />
+            </div>
+            <div className="form-row">
+              <p className='form-label'>Embedding Secret Key</p>
+              <p className='form-description'>AWS Secret Key for Bedrock embedding service</p>
+              <Controller
+                name="embeddingSecretKey"
+                control={control}
+                rules={{ required: 'Embedding Secret Key is required for AWS Bedrock' }}
+                render={({ field }) => (
+                  <FormInput
+                    label=""
+                    type={isEditing ? 'text' : 'password'}
+                    placeholder="Enter AWS Secret Key for embeddings"
+                    error={errors.embeddingSecretKey?.message}
+                    readOnly={embeddingSecretKeyReplaceMode}
+                    showEndButton={embeddingSecretKeyReplaceMode}
+                    onEndButtonClick={() => {
+                      setEmbeddingSecretKeyReplaceMode(false);
+                      setValue('embeddingSecretKey', '');
+                    }}
+                    endButtonText="Change"
+                    {...field}
+                  />
+                )}
+              />
+            </div>
+          </>
+        );
+      case 'azure':
+        return (
+          <>
+            <div className="form-row">
+              <p className='form-label'>Embedding Deployment Name</p>
+              <p className='form-description'>Azure OpenAI embedding deployment name</p>
+              <Controller
+                name="embeddingDeploymentName"
+                control={control}
+                rules={{ required: 'Embedding Deployment Name is required for Azure OpenAI' }}
+                render={({ field }) => (
+                  <FormInput
+                    label=""
+                    placeholder="Enter embedding deployment name"
+                    error={errors.embeddingDeploymentName?.message}
+                    {...field}
+                  />
+                )}
+              />
+            </div>
+            <div className="form-row">
+              <p className='form-label'>Embedding Endpoint / Target URI</p>
+              <p className='form-description'>Azure OpenAI embedding service endpoint URL</p>
+              <Controller
+                name="embeddingTargetUri"
+                control={control}
+                rules={{
+                  required: 'Embedding Endpoint is required for Azure OpenAI',
+                  pattern: {
+                    value: /^https?:\/\/.+/,
+                    message: 'Please enter a valid URL starting with http:// or https://'
+                  }
+                }}
+                render={({ field }) => (
+                  <FormInput
+                    label=""
+                    placeholder="https://your-resource.openai.azure.com/"
+                    error={errors.embeddingTargetUri?.message}
+                    {...field}
+                  />
+                )}
+              />
+            </div>
+            <div className="form-row">
+              <p className='form-label'>Embedding API Key</p>
+              <p className='form-description'>Azure OpenAI embedding API key</p>
+              <Controller
+                name="embeddingAzureApiKey"
+                control={control}
+                rules={{ required: 'Embedding API Key is required for Azure OpenAI' }}
+                render={({ field }) => (
+                  <FormInput
+                    label=""
+                    type={isEditing ? 'text' : 'password'}
+                    placeholder="Enter Azure OpenAI embedding API key"
+                    error={errors.embeddingAzureApiKey?.message}
+                    readOnly={embeddingAzureApiKeyReplaceMode}
+                    showEndButton={embeddingAzureApiKeyReplaceMode}
+                    onEndButtonClick={() => {
+                      setEmbeddingAzureApiKeyReplaceMode(false);
+                      setValue('embeddingAzureApiKey', '');
+                    }}
+                    endButtonText="Change"
+                    {...field}
+                  />
+                )}
+              />
+            </div>
+          </>
+        );
+
+      default:
+        return (
+          <div className="form-row">
+            <p className='form-label'>Embedding Model API Key</p>
+            <p className='form-description'>API key of your embedding model</p>
+            <Controller
+              name="embeddingModelApiKey"
+              control={control}
+              rules={{ required: 'Embedding API Key is required' }}
+              render={({ field }) => (
+                <FormInput
+                  label=""
+                  type={isEditing ? 'text' : 'password'}
+                  placeholder="Enter your Embedding API key"
+                  error={errors.embeddingModelApiKey?.message}
+                  readOnly={embeddingApiKeyReplaceMode}
+                  showEndButton={embeddingApiKeyReplaceMode}
+                  onEndButtonClick={() => {
+                    setEmbeddingApiKeyReplaceMode(false);
+                    setValue('embeddingModelApiKey', '');
+                  }}
+                  endButtonText="Change"
+                  {...field}
+                />
+              )}
+            />
+          </div>
+        );
+    }
+  };
+
   const handleFormSubmit = (data: LLMConnectionFormData) => {
     const cleanedData = {
       ...data,
@@ -395,7 +581,7 @@ const embeddingModelOptions = toOptions(embeddingModelsData);
                   options={getLLMModelOptions() || []}
                   placeholder={
                     llmModelsLoading
-                      ? "Loading models..."
+                      ? "Select LLM Model"
                       : llmModelsError
                         ? "Error loading models"
                         : !selectedLLMPlatform
@@ -467,7 +653,7 @@ const embeddingModelOptions = toOptions(embeddingModelsData);
                   options={getEmbeddingModelOptions() || []}
                   placeholder={
                     embeddingModelsLoading
-                      ? "Loading models..."
+                      ? "Select Embedding Model"
                       : embeddingModelsError
                         ? "Error loading models"
                         : !selectedEmbeddingPlatform
@@ -486,32 +672,8 @@ const embeddingModelOptions = toOptions(embeddingModelsData);
             />
           </div>
 
-          <div className="form-row">
-            <p className='form-label'>Embedding Model API Key</p>
-            <p className='form-description'>API key of your embedding model</p>
-
-            <Controller
-              name="embeddingModelApiKey"
-              control={control}
-              rules={{ required: 'Embedding API Key is required' }}
-              render={({ field }) => (
-                <FormInput
-                  label=""
-                  type={isEditing ? 'text' : 'password'}
-                  placeholder="Enter your Embedding API key"
-                  error={errors.embeddingModelApiKey?.message}
-                  readOnly={embeddingApiKeyReplaceMode}
-                  showEndButton={embeddingApiKeyReplaceMode}
-                  onEndButtonClick={() => {
-                    setEmbeddingApiKeyReplaceMode(false);
-                    setValue('embeddingModelApiKey', '');
-                  }}
-                  endButtonText="Change"
-                  {...field}
-                />
-              )}
-            />
-          </div>
+          {/* Embedding Platform-specific fields */}
+          {renderEmbeddingPlatformSpecificFields()}
         </div>
 
         <div className="form-section">
diff --git a/GUI/src/pages/LLMConnections/CreateLLMConnection.tsx b/GUI/src/pages/LLMConnections/CreateLLMConnection.tsx
index dfeb583..c77bdfc 100644
--- a/GUI/src/pages/LLMConnections/CreateLLMConnection.tsx
+++ b/GUI/src/pages/LLMConnections/CreateLLMConnection.tsx
@@ -15,8 +15,8 @@ const CreateLLMConnection = () => {
     
     // Query to check for existing production connection
     const { data: existingProductionConnection } = useQuery({
-      queryKey: ['production-connection'],
-      queryFn: getProductionConnection,
+      queryKey: llmConnectionsQueryKeys.production(),
+      queryFn: () => getProductionConnection(),
     });
     
     const createConnectionMutation = useMutation({
diff --git a/GUI/src/pages/LLMConnections/ViewLLMConnection.tsx b/GUI/src/pages/LLMConnections/ViewLLMConnection.tsx
index 28e429f..3a55528 100644
--- a/GUI/src/pages/LLMConnections/ViewLLMConnection.tsx
+++ b/GUI/src/pages/LLMConnections/ViewLLMConnection.tsx
@@ -249,6 +249,13 @@ const ViewLLMConnection = () => {
     accessKey: connectionData.accessKey || '', // Don't show API keys
     // Embedding model credentials (don't show sensitive data, but include structure)
     embeddingModelApiKey: connectionData.embeddingModelApiKey || '', // Don't show API keys
+    // Embedding AWS Bedrock credentials
+    embeddingAccessKey: connectionData.embeddingAccessKey || '',
+    embeddingSecretKey: connectionData.embeddingSecretKey || '',
+    // Embedding Azure credentials
+    embeddingDeploymentName: connectionData.embeddingDeploymentName || '',
+    embeddingTargetUri: connectionData.embeddingTargetUri || '',
+    embeddingAzureApiKey: connectionData.embeddingAzureApiKey || '',
   };
 
   return (
diff --git a/GUI/src/pages/LLMConnections/index.tsx b/GUI/src/pages/LLMConnections/index.tsx
index 6d46024..18dd7f4 100644
--- a/GUI/src/pages/LLMConnections/index.tsx
+++ b/GUI/src/pages/LLMConnections/index.tsx
@@ -13,7 +13,7 @@ import BudgetBanner from 'components/molecules/BudgetBanner';
 import './LLMConnections.scss';
 import { platforms, trainingStatuses } from 'config/dataModelsConfig';
 import LLMConnectionCard from 'components/molecules/LLMConnectionCard';
-import { fetchLLMConnectionsPaginated, LLMConnectionFilters, LLMConnection, getProductionConnection } from 'services/llmConnections';
+import { fetchLLMConnectionsPaginated, LLMConnectionFilters, LLMConnection, getProductionConnection, ProductionConnectionFilters } from 'services/llmConnections';
 import { llmConnectionsQueryKeys } from 'utils/queryKeys';
 
 const LLMConnections: FC = () => {
@@ -35,10 +35,17 @@ const LLMConnections: FC = () => {
     queryFn: () => fetchLLMConnectionsPaginated(filters),
   });
 
-  // Fetch production connection separately
+  // Fetch production connection separately with potential filters
+  const [productionFilters, setProductionFilters] = useState<ProductionConnectionFilters>({
+    sortBy: 'created_at',
+    sortOrder: 'desc',
+    llmPlatform: '',
+    llmModel: '',
+  });
+  
   const { data: productionConnection, isLoading: isProductionLoading } = useQuery({
-    queryKey: llmConnectionsQueryKeys.production(),
-    queryFn: getProductionConnection,
+    queryKey: llmConnectionsQueryKeys.production(productionFilters),
+    queryFn: () => getProductionConnection(productionFilters),
   });
 
 
@@ -50,11 +57,23 @@ const LLMConnections: FC = () => {
     setFilters(prev => ({ ...prev, pageNumber: pageIndex }));
   }, [pageIndex]);
 
+  // Sync production filters with main filters on component mount
+  useEffect(() => {
+    setProductionFilters(prev => ({
+      ...prev,
+      llmPlatform: filters.llmPlatform || '',
+      llmModel: filters.llmModel || '',
+      sortBy: filters.sortBy || 'created_at',
+      sortOrder: filters.sortOrder || 'desc',
+    }));
+  }, [filters.llmPlatform, filters.llmModel, filters.sortBy, filters.sortOrder]);
+
   const handleFilterChange = (
     name: string,
     value: string | number | undefined | { name: string; id: string }
   ) => {
     let filterUpdate: Partial<LLMConnectionFilters> = {};
+    let productionFilterUpdate: Partial<ProductionConnectionFilters> = {};
 
     if (name === 'sorting') {
       // Handle sorting format - no conversion needed, use snake_case directly
@@ -62,11 +81,21 @@ const LLMConnections: FC = () => {
       const [sortBy, sortOrder] = sortingValue.split(' ');
 
       filterUpdate = {
+        sortBy: sortBy,
+        sortOrder: sortOrder as 'asc' | 'desc' 
+      };
+
+      productionFilterUpdate = {
         sortBy: sortBy,
         sortOrder: sortOrder as 'asc' | 'desc'
       };
     } else {
       filterUpdate = { [name]: value };
+
+      // Update production filters for relevant fields
+      if (name === 'llmPlatform' || name === 'llmModel') {
+        productionFilterUpdate = { [name]: value as string };
+      }
     }
 
     setFilters((prevFilters) => ({
@@ -74,6 +103,14 @@ const LLMConnections: FC = () => {
       ...filterUpdate,
     }));
 
+    // Update production filters if relevant
+    if (Object.keys(productionFilterUpdate).length > 0) {
+      setProductionFilters((prevFilters) => ({
+        ...prevFilters,
+        ...productionFilterUpdate,
+      }));
+    }
+
     // Reset to first page when filters change
     if (name !== 'pageNumber') {
       setPageIndex(1);
@@ -192,6 +229,12 @@ const LLMConnections: FC = () => {
                           llmModel: '',
                           environment: '',
                         });
+                        setProductionFilters({
+                          sortBy: 'created_at',
+                          sortOrder: 'desc',
+                          llmPlatform: '',
+                          llmModel: '',
+                        });
                         setPageIndex(1);
                       }}
                       appearance={ButtonAppearanceTypes.SECONDARY}
@@ -202,7 +245,7 @@ const LLMConnections: FC = () => {
                 </div>
               </div>
 
-              {productionConnection && (
+              {productionConnection && filters?.environment !== "testing" && (
                 <div className="m-30-0">
                   <p>Production LLM Connection</p>
                   <div className="grid-container m-30-0">
diff --git a/GUI/src/pages/TestProductionLLM/index.tsx b/GUI/src/pages/TestProductionLLM/index.tsx
index b5334c1..a9c1493 100644
--- a/GUI/src/pages/TestProductionLLM/index.tsx
+++ b/GUI/src/pages/TestProductionLLM/index.tsx
@@ -124,11 +124,11 @@ const TestProductionLLM: FC = () => {
       setMessages(prev => [...prev, botMessage]);
 
       // Show toast notification
-      toast.open({
-        type: botMessageType,
-        title: t('errorOccurred'),
-        message: t('errorMessage'),
-      });
+      // toast.open({
+      //   type: botMessageType,
+      //   title: t('errorOccurred'),
+      //   message: t('errorMessage'),
+      // });
 
     } catch (error) {
       console.error('Error sending message:', error);
diff --git a/GUI/src/services/llmConnections.ts b/GUI/src/services/llmConnections.ts
index 83882ab..5b3921c 100644
--- a/GUI/src/services/llmConnections.ts
+++ b/GUI/src/services/llmConnections.ts
@@ -30,6 +30,13 @@ export interface LLMConnection {
   accessKey?: string;
   // Embedding model credentials
   embeddingModelApiKey?: string;
+  // Embedding AWS Bedrock credentials
+  embeddingAccessKey?: string;
+  embeddingSecretKey?: string;
+  // Embedding Azure credentials
+  embeddingDeploymentName?: string;
+  embeddingTargetUri?: string;
+  embeddingAzureApiKey?: string;
 }
 
 export interface LLMConnectionsResponse {
@@ -69,6 +76,16 @@ export interface LLMConnectionFilters {
   environment?: string;
   status?: string;
 }
+
+export interface ProductionConnectionFilters {
+  llmPlatform?: string;
+  llmModel?: string;
+  embeddingPlatform?: string;
+  embeddingModel?: string;
+  connectionStatus?: string;
+  sortBy?: string;
+  sortOrder?: string;
+}
 export interface LegacyLLMConnectionFilters {
   page: number;
   pageSize: number;
@@ -98,11 +115,18 @@ export interface LLMConnectionFormData {
   accessKey?: string;
   // Embedding model credentials
   embeddingModelApiKey?: string;
+  // Embedding AWS Bedrock credentials
+  embeddingAccessKey?: string;
+  embeddingSecretKey?: string;
+  // Embedding Azure credentials
+  embeddingDeploymentName?: string;
+  embeddingTargetUri?: string;
+  embeddingAzureApiKey?: string;
 }
 
 // Vault secret service functions
 async function createVaultSecret(connectionId: string, connectionData: LLMConnectionFormData): Promise<void> {
- 
+
   const payload = {
     connectionId,
     llmPlatform: connectionData.llmPlatform,
@@ -121,19 +145,29 @@ async function createVaultSecret(connectionId: string, connectionData: LLMConnec
       targetUrl: connectionData.targetUri || '',
       apiKey: connectionData.apiKey || '',
     }),
-    embeddingModelApiKey: connectionData.embeddingModelApiKey || '',
+    // Embedding AWS Bedrock credentials
+    ...(connectionData.embeddingModelPlatform === 'aws' && {
+      embeddingAccessKey: connectionData.embeddingAccessKey || '',
+      embeddingSecretKey: connectionData.embeddingSecretKey || '',
+    }),
+    // Embedding Azure credentials
+    ...(connectionData.embeddingModelPlatform === 'azure' && {
+      embeddingDeploymentName: connectionData.embeddingDeploymentName || '',
+      embeddingTargetUri: connectionData.embeddingTargetUri || '',
+      embeddingAzureApiKey: connectionData.embeddingAzureApiKey || '',
+    }),
   };
 
   await apiDev.post(vaultEndpoints.CREATE_VAULT_SECRET(), payload);
 }
 
 async function deleteVaultSecret(connectionId: string, connectionData: Partial<LLMConnectionFormData>): Promise<void> {
-  
+
   const payload = {
     connectionId,
     llmPlatform: connectionData.llmPlatform || '',
     llmModel: connectionData.llmModel || '',
-    embeddingModel: connectionData.embeddingModel || '', 
+    embeddingModel: connectionData.embeddingModel || '',
     embeddingPlatform: connectionData.embeddingModelPlatform || '',
     deploymentEnvironment: connectionData.deploymentEnvironment?.toLowerCase() || '',
   };
@@ -164,8 +198,22 @@ export async function getLLMConnection(id: string | number): Promise<LLMConnecti
   return data?.response;
 }
 
-export async function getProductionConnection(): Promise<LLMConnection | null> {
-  const { data } = await apiDev.get(llmConnectionsEndpoints.GET_PRODUCTION_CONNECTION());
+export async function getProductionConnection(filters?: ProductionConnectionFilters): Promise<LLMConnection | null> {
+  const queryParams = new URLSearchParams();
+
+  if (filters?.llmPlatform) queryParams.append('llmPlatform', filters.llmPlatform);
+  if (filters?.llmModel) queryParams.append('llmModel', filters.llmModel);
+  if (filters?.embeddingPlatform) queryParams.append('embeddingPlatform', filters.embeddingPlatform);
+  if (filters?.embeddingModel) queryParams.append('embeddingModel', filters.embeddingModel);
+  if (filters?.connectionStatus) queryParams.append('connectionStatus', filters.connectionStatus);
+  if (filters?.sortBy) queryParams.append('sortBy', filters.sortBy);
+  if (filters?.sortOrder) queryParams.append('sortOrder', filters.sortOrder);
+
+  const url = queryParams.toString()
+    ? `${llmConnectionsEndpoints.GET_PRODUCTION_CONNECTION()}?${queryParams.toString()}`
+    : llmConnectionsEndpoints.GET_PRODUCTION_CONNECTION();
+
+  const { data } = await apiDev.get(url);
   return data?.response?.[0] || null;
 }
 
@@ -190,11 +238,17 @@ export async function createLLMConnection(connectionData: LLMConnectionFormData)
     secret_key: maskSensitiveKey(connectionData.secretKey) || "",
     access_key: maskSensitiveKey(connectionData.accessKey) || "",
     // Embedding model credentials
-    embedding_model_api_key: maskSensitiveKey(connectionData.embeddingModelApiKey) || "",
+    // Embedding AWS Bedrock credentials
+    embedding_access_key: maskSensitiveKey(connectionData.embeddingAccessKey) || "",
+    embedding_secret_key: maskSensitiveKey(connectionData.embeddingSecretKey) || "",
+    // Embedding Azure credentials
+    embedding_deployment_name: connectionData.embeddingDeploymentName || "",
+    embedding_target_uri: connectionData.embeddingTargetUri || "",
+    embedding_azure_api_key: maskSensitiveKey(connectionData.embeddingAzureApiKey) || "",
   });
-  
+
   const connection = data?.response;
-  
+
   // After successful database creation, store secrets in vault
   if (connection && connection.id) {
     try {
@@ -205,7 +259,7 @@ export async function createLLMConnection(connectionData: LLMConnectionFormData)
       // The connection is already created in the database
     }
   }
-  
+
   return connection;
 }
 
@@ -233,22 +287,30 @@ export async function updateLLMConnection(
     secret_key: maskSensitiveKey(connectionData.secretKey) || "",
     access_key: maskSensitiveKey(connectionData.accessKey) || "",
     // Embedding model credentials
-    embedding_model_api_key: maskSensitiveKey(connectionData.embeddingModelApiKey) || "",
+    // Embedding AWS Bedrock credentials
+    embedding_access_key: maskSensitiveKey(connectionData.embeddingAccessKey) || "",
+    embedding_secret_key: maskSensitiveKey(connectionData.embeddingSecretKey) || "",
+    // Embedding Azure credentials
+    embedding_deployment_name: connectionData.embeddingDeploymentName || "",
+    embedding_target_uri: connectionData.embeddingTargetUri || "",
+    embedding_azure_api_key: maskSensitiveKey(connectionData.embeddingAzureApiKey) || "",
   });
-  
+
   const connection = data?.response;
-  
-  // After successful database update, update secrets in vault
-  if (connection) {
+
+  if (connection && (connectionData.secretKey && !connectionData.secretKey?.includes('*') 
+    || connectionData.accessKey && !connectionData.accessKey?.includes('*') 
+    || connectionData.apiKey && !connectionData.apiKey?.includes('*') 
+    || connectionData.embeddingAccessKey && !connectionData.embeddingAccessKey?.includes('*') 
+    || connectionData.embeddingSecretKey && !connectionData.embeddingSecretKey?.includes('*') 
+    || connectionData.embeddingAzureApiKey && !connectionData.embeddingAzureApiKey?.includes('*'))) {
     try {
       await createVaultSecret(id.toString(), connectionData);
     } catch (vaultError) {
       console.error('Failed to update secrets in vault:', vaultError);
-      // Note: We don't throw here to avoid breaking the connection update flow
-      // The connection is already updated in the database
     }
   }
-  
+
   return connection;
 }
 
@@ -260,12 +322,12 @@ export async function deleteLLMConnection(id: string | number): Promise<void> {
   } catch (error) {
     console.error('Failed to get connection data before deletion:', error);
   }
-  
+
   // Delete from database
   await apiDev.post(llmConnectionsEndpoints.DELETE_LLM_CONNECTION(), {
     connection_id: id,
   });
-  
+
   // After successful database deletion, delete secrets from vault
   if (connectionToDelete) {
     try {
@@ -293,9 +355,9 @@ export async function checkBudgetStatus(): Promise<BudgetStatus | null> {
     return null;
   }
 }
-  
+
 export async function updateLLMConnectionStatus(
-  id: string | number, 
+  id: string | number,
   status: 'active' | 'inactive'
 ): Promise<LLMConnection> {
   const { data } = await apiDev.post(llmConnectionsEndpoints.UPDATE_LLM_CONNECTION_STATUS(), {
diff --git a/GUI/src/utils/queryKeys.ts b/GUI/src/utils/queryKeys.ts
index e004497..e10462e 100644
--- a/GUI/src/utils/queryKeys.ts
+++ b/GUI/src/utils/queryKeys.ts
@@ -1,5 +1,5 @@
 import { PaginationState, SortingState } from '@tanstack/react-table';
-import { LLMConnectionFilters, LegacyLLMConnectionFilters } from 'services/llmConnections';
+import { LLMConnectionFilters, LegacyLLMConnectionFilters, ProductionConnectionFilters } from 'services/llmConnections';
 import { InferenceRequest } from 'services/inference';
 
 
@@ -30,7 +30,7 @@ export const llmConnectionsQueryKeys = {
   details: () => [...llmConnectionsQueryKeys.all(), 'detail'] as const,
   detail: (id: string | number) => [...llmConnectionsQueryKeys.details(), id] as const,
   budgetStatus: () => [...llmConnectionsQueryKeys.all(), 'budget-status'] as const,
-  production: () => [...llmConnectionsQueryKeys.all(), 'production'] as const,
+  production: (filters?: ProductionConnectionFilters) => [...llmConnectionsQueryKeys.all(), 'production', filters] as const,
 };
 
 export const inferenceQueryKeys = {
diff --git a/endpoints.md b/endpoints.md
index 6bd4fc9..262e81a 100644
--- a/endpoints.md
+++ b/endpoints.md
@@ -357,12 +357,41 @@ GET /ruuter-private/llm/connections/list
 | `llmPlatform` | `string` | Filter by LLM platform |
 | `llmModel` | `string` | Filter by LLM model |
 | `deploymentEnvironment` | `string` | Filter by environment (Testing / Production) |
+| `pageNumber` | `number` | Page number (1-based) |
+| `pageSize` | `number` | Number of items per page |
+| `sortBy` | `string` | Field to sort by |
+| `sortOrder` | `string` | Sort order: 'asc' or 'desc' |
 
 ### Example Request
 ```http
 GET /ruuter-private/llm/connections/list?llmPlatform=OpenAI&deploymentEnvironment=Testing&model=GPT4
 ```
 
+---
+
+## 5. Get Production LLM Connection (with filters)
+
+### Endpoint
+```http
+GET /ruuter-private/llm/connections/production
+```
+
+### Query Parameters (Optional for filtering)
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `llmPlatform` | `string` | Filter by LLM platform |
+| `llmModel` | `string` | Filter by LLM model |
+| `embeddingPlatform` | `string` | Filter by embedding platform |
+| `embeddingModel` | `string` | Filter by embedding model |
+| `connectionStatus` | `string` | Filter by connection status |
+| `sortBy` | `string` | Field to sort by |
+| `sortOrder` | `string` | Sort order: 'asc' or 'desc' |
+
+### Example Request
+```http
+GET /ruuter-private/llm/connections/production?llmPlatform=OpenAI&connectionStatus=active
+```
+
 ### Response (200 OK)
 ```json
 [
diff --git a/pyproject.toml b/pyproject.toml
index 760dbb7..774f8af 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -34,6 +34,7 @@ dependencies = [
     "anthropic>=0.69.0",
     "nemoguardrails>=0.16.0",
     "tiktoken>=0.11.0",
+    "langfuse>=3.8.1",
 ]
 
 [tool.pyright]
diff --git a/src/contextual_retrieval/contextual_retriever.py b/src/contextual_retrieval/contextual_retriever.py
index e76165a..8ab5d24 100644
--- a/src/contextual_retrieval/contextual_retriever.py
+++ b/src/contextual_retrieval/contextual_retriever.py
@@ -14,7 +14,7 @@
 from loguru import logger
 import asyncio
 import time
-
+from langfuse import observe
 from contextual_retrieval.config import ConfigLoader, ContextualRetrievalConfig
 
 # Type checking import to avoid circular dependency at runtime
@@ -126,6 +126,7 @@ def _clear_session_cache(self):
             logger.debug("Clearing session LLM service cache")
             self._session_llm_service = None
 
+    @observe(name="retrieve_contextual_chunks", as_type="retriever")
     async def retrieve_contextual_chunks(
         self,
         original_question: str,
diff --git a/src/llm_orchestration_service.py b/src/llm_orchestration_service.py
index 08f3596..b5d5f7d 100644
--- a/src/llm_orchestration_service.py
+++ b/src/llm_orchestration_service.py
@@ -5,6 +5,7 @@
 import asyncio
 import os
 from loguru import logger
+from langfuse import Langfuse, observe
 
 from llm_orchestrator_config.llm_manager import LLMManager
 from models.request_models import (
@@ -28,6 +29,36 @@
 from src.contextual_retrieval import ContextualRetriever
 
 
+class LangfuseConfig:
+    """Configuration for Langfuse integration."""
+
+    def __init__(self):
+        self.langfuse_client: Optional[Langfuse] = None
+        self._initialize_langfuse()
+
+    def _initialize_langfuse(self):
+        """Initialize Langfuse client with Vault secrets."""
+        try:
+            from llm_orchestrator_config.vault.vault_client import VaultAgentClient
+
+            vault = VaultAgentClient()
+            if vault.is_vault_available():
+                langfuse_secrets = vault.get_secret("langfuse/config")
+                if langfuse_secrets:
+                    self.langfuse_client = Langfuse(
+                        public_key=langfuse_secrets.get("public_key"),
+                        secret_key=langfuse_secrets.get("secret_key"),
+                        host=langfuse_secrets.get("host", "http://langfuse-web:3000"),
+                    )
+                    logger.info("Langfuse client initialized successfully")
+                else:
+                    logger.warning("Langfuse secrets not found in Vault")
+            else:
+                logger.warning("Vault not available, Langfuse tracing disabled")
+        except Exception as e:
+            logger.warning(f"Failed to initialize Langfuse: {e}")
+
+
 class LLMOrchestrationService:
     """
     Service class for handling LLM orchestration with integrated guardrails.
@@ -39,8 +70,9 @@ class LLMOrchestrationService:
 
     def __init__(self) -> None:
         """Initialize the orchestration service."""
-        pass
+        self.langfuse_config = LangfuseConfig()
 
+    @observe(name="orchestration_request", as_type="agent")
     def process_orchestration_request(
         self, request: OrchestrationRequest
     ) -> Union[OrchestrationResponse, TestOrchestrationResponse]:
@@ -82,6 +114,38 @@ def process_orchestration_request(
 
             # Log final costs and return response
             self._log_costs(costs_dict)
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                total_costs = calculate_total_costs(costs_dict)
+
+                total_input_tokens = sum(
+                    c.get("total_prompt_tokens", 0) for c in costs_dict.values()
+                )
+                total_output_tokens = sum(
+                    c.get("total_completion_tokens", 0) for c in costs_dict.values()
+                )
+
+                langfuse.update_current_generation(
+                    model=components["llm_manager"]
+                    .get_provider_info()
+                    .get("model", "unknown"),
+                    usage_details={
+                        "input": total_input_tokens,
+                        "output": total_output_tokens,
+                        "total": total_costs.get("total_tokens", 0),
+                    },
+                    cost_details={
+                        "total": total_costs.get("total_cost", 0.0),
+                    },
+                    metadata={
+                        "total_calls": total_costs.get("total_calls", 0),
+                        "cost_breakdown": costs_dict,
+                        "chat_id": request.chatId,
+                        "author_id": request.authorId,
+                        "environment": request.environment,
+                    },
+                )
+                langfuse.flush()
             return response
 
         except Exception as e:
@@ -89,9 +153,20 @@ def process_orchestration_request(
                 f"Error processing orchestration request for chatId: {request.chatId}, "
                 f"error: {str(e)}"
             )
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    metadata={
+                        "error": str(e),
+                        "error_type": type(e).__name__,
+                        "response_type": "technical_issue",
+                    }
+                )
+                langfuse.flush()
             self._log_costs(costs_dict)
             return self._create_error_response(request)
 
+    @observe(name="initialize_service_components", as_type="span")
     def _initialize_service_components(
         self, request: OrchestrationRequest
     ) -> Dict[str, Any]:
@@ -212,6 +287,7 @@ def _log_generator_status(self, components: Dict[str, Any]) -> None:
         except Exception as e:
             logger.warning(f" Generator: Status check failed - {str(e)}")
 
+    @observe(name="execute_orchestration_pipeline", as_type="span")
     def _execute_orchestration_pipeline(
         self,
         request: OrchestrationRequest,
@@ -262,6 +338,7 @@ def _execute_orchestration_pipeline(
             components["guardrails_adapter"], generated_response, request, costs_dict
         )
 
+    @observe(name="safe_initialize_guardrails", as_type="span")
     def _safe_initialize_guardrails(
         self, environment: str, connection_id: Optional[str]
     ) -> Optional[NeMoRailsAdapter]:
@@ -275,6 +352,7 @@ def _safe_initialize_guardrails(
             logger.warning("Continuing without guardrails protection")
             return None
 
+    @observe(name="safe_initialize_contextual_retriever", as_type="span")
     def _safe_initialize_contextual_retriever(
         self, environment: str, connection_id: Optional[str]
     ) -> Optional[ContextualRetriever]:
@@ -292,6 +370,7 @@ def _safe_initialize_contextual_retriever(
             logger.warning("Continuing without chunk retrieval capabilities")
             return None
 
+    @observe(name="safe_initialize_response_generator", as_type="span")
     def _safe_initialize_response_generator(
         self, llm_manager: LLMManager
     ) -> Optional[ResponseGeneratorAgent]:
@@ -449,6 +528,7 @@ def _create_out_of_scope_response(
             content=OUT_OF_SCOPE_MESSAGE,
         )
 
+    @observe(name="initialize_guardrails", as_type="span")
     def _initialize_guardrails(
         self, environment: str, connection_id: Optional[str]
     ) -> NeMoRailsAdapter:
@@ -479,6 +559,7 @@ def _initialize_guardrails(
             logger.error(f"Failed to initialize Guardrails adapter: {str(e)}")
             raise
 
+    @observe(name="check_input_guardrails", as_type="span")
     def _check_input_guardrails(
         self,
         guardrails_adapter: NeMoRailsAdapter,
@@ -503,7 +584,26 @@ def _check_input_guardrails(
 
             # Store guardrail costs
             costs_dict["input_guardrails"] = result.usage
-
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    input=user_message,
+                    metadata={
+                        "guardrail_type": "input",
+                        "allowed": result.allowed,
+                        "verdict": result.verdict,
+                        "blocked_reason": result.reason if not result.allowed else None,
+                        "error": result.error if result.error else None,
+                    },
+                    usage_details={
+                        "input": result.usage.get("total_prompt_tokens", 0),
+                        "output": result.usage.get("total_completion_tokens", 0),
+                        "total": result.usage.get("total_tokens", 0),
+                    },  # type: ignore
+                    cost_details={
+                        "total": result.usage.get("total_cost", 0.0),
+                    },
+                )
             logger.info(
                 f"Input guardrails check completed: allowed={result.allowed}, "
                 f"cost=${result.usage.get('total_cost', 0):.6f}"
@@ -513,6 +613,15 @@ def _check_input_guardrails(
 
         except Exception as e:
             logger.error(f"Input guardrails check failed: {str(e)}")
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    metadata={
+                        "error": str(e),
+                        "error_type": type(e).__name__,
+                        "guardrail_type": "input",
+                    }
+                )
             # Return conservative result on error
             return GuardrailCheckResult(
                 allowed=False,
@@ -522,6 +631,7 @@ def _check_input_guardrails(
                 usage={},
             )
 
+    @observe(name="check_output_guardrails", as_type="span")
     def _check_output_guardrails(
         self,
         guardrails_adapter: NeMoRailsAdapter,
@@ -546,7 +656,28 @@ def _check_output_guardrails(
 
             # Store guardrail costs
             costs_dict["output_guardrails"] = result.usage
-
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    input=assistant_message[:500],  # Truncate for readability
+                    output=result.verdict,
+                    metadata={
+                        "guardrail_type": "output",
+                        "allowed": result.allowed,
+                        "verdict": result.verdict,
+                        "reason": result.reason if not result.allowed else None,
+                        "error": result.error if result.error else None,
+                        "response_length": len(assistant_message),
+                    },
+                    usage_details={
+                        "input": result.usage.get("total_prompt_tokens", 0),
+                        "output": result.usage.get("total_completion_tokens", 0),
+                        "total": result.usage.get("total_tokens", 0),
+                    },  # type: ignore
+                    cost_details={
+                        "total": result.usage.get("total_cost", 0.0),
+                    },
+                )
             logger.info(
                 f"Output guardrails check completed: allowed={result.allowed}, "
                 f"cost=${result.usage.get('total_cost', 0):.6f}"
@@ -556,6 +687,15 @@ def _check_output_guardrails(
 
         except Exception as e:
             logger.error(f"Output guardrails check failed: {str(e)}")
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    metadata={
+                        "error": str(e),
+                        "error_type": type(e).__name__,
+                        "guardrail_type": "output",
+                    }
+                )
             # Return conservative result on error
             return GuardrailCheckResult(
                 allowed=False,
@@ -631,6 +771,7 @@ def _log_costs(self, costs_dict: Dict[str, Dict[str, Any]]) -> None:
         except Exception as e:
             logger.warning(f"Failed to log costs: {str(e)}")
 
+    @observe(name="initialize_llm_manager", as_type="span")
     def _initialize_llm_manager(
         self, environment: str, connection_id: Optional[str]
     ) -> LLMManager:
@@ -660,6 +801,7 @@ def _initialize_llm_manager(
             logger.error(f"Failed to initialize LLM Manager: {str(e)}")
             raise
 
+    @observe(name="refine_user_prompt", as_type="chain")
     def _refine_user_prompt(
         self,
         llm_manager: LLMManager,
@@ -725,7 +867,32 @@ def _refine_user_prompt(
                 raise ValueError(
                     f"Prompt refinement validation failed: {str(validation_error)}"
                 ) from validation_error
-
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                refinement_applied = (
+                    original_message.strip()
+                    != validated_output.original_question.strip()
+                )
+                langfuse.update_current_generation(
+                    model=llm_manager.get_provider_info().get("model", "unknown"),
+                    input=original_message,
+                    usage_details={
+                        "input": usage_info.get("total_prompt_tokens", 0),
+                        "output": usage_info.get("total_completion_tokens", 0),
+                        "total": usage_info.get("total_tokens", 0),
+                    },
+                    cost_details={
+                        "total": usage_info.get("total_cost", 0.0),
+                    },
+                    metadata={
+                        "num_calls": usage_info.get("num_calls", 0),
+                        "num_refined_questions": len(
+                            validated_output.refined_questions
+                        ),
+                        "refinement_applied": refinement_applied,
+                        "conversation_history_length": len(history),
+                    },  # type: ignore
+                )
             output_json = validated_output.model_dump()
             logger.info(
                 f"Prompt refinement output: {json.dumps(output_json, indent=2)}"
@@ -738,9 +905,19 @@ def _refine_user_prompt(
             raise
         except Exception as e:
             logger.error(f"Prompt refinement failed: {str(e)}")
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    metadata={
+                        "error": str(e),
+                        "error_type": type(e).__name__,
+                        "refinement_failed": True,
+                    }
+                )
             logger.error(f"Failed to refine message: {original_message}")
             raise RuntimeError(f"Prompt refinement process failed: {str(e)}") from e
 
+    @observe(name="initialize_contextual_retriever", as_type="span")
     def _initialize_contextual_retriever(
         self, environment: str, connection_id: Optional[str]
     ) -> ContextualRetriever:
@@ -774,6 +951,7 @@ def _initialize_contextual_retriever(
             logger.error(f"Failed to initialize contextual retriever: {str(e)}")
             raise
 
+    @observe(name="initialize_response_generator", as_type="span")
     def _initialize_response_generator(
         self, llm_manager: LLMManager
     ) -> ResponseGeneratorAgent:
@@ -800,6 +978,7 @@ def _initialize_response_generator(
             logger.error(f"Failed to initialize response generator: {str(e)}")
             raise
 
+    @observe(name="generate_rag_response", as_type="generation")
     def _generate_rag_response(
         self,
         llm_manager: LLMManager,
@@ -867,7 +1046,27 @@ def _generate_rag_response(
                 },
             )
             costs_dict["response_generator"] = generator_usage
-
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    model=llm_manager.get_provider_info().get("model", "unknown"),
+                    usage_details={
+                        "input": generator_usage.get("total_prompt_tokens", 0),
+                        "output": generator_usage.get("total_completion_tokens", 0),
+                        "total": generator_usage.get("total_tokens", 0),
+                    },
+                    cost_details={
+                        "total": generator_usage.get("total_cost", 0.0),
+                    },
+                    metadata={
+                        "num_calls": generator_usage.get("num_calls", 0),
+                        "question_out_of_scope": question_out_of_scope,
+                        "num_chunks_used": len(relevant_chunks)
+                        if relevant_chunks
+                        else 0,
+                    },
+                    output=answer,
+                )
             if question_out_of_scope:
                 logger.info("Question determined out-of-scope – sending fixed message.")
                 if request.environment == "test":
@@ -910,6 +1109,16 @@ def _generate_rag_response(
 
         except Exception as e:
             logger.error(f"RAG Response generation failed: {str(e)}")
+            if self.langfuse_config.langfuse_client:
+                langfuse = self.langfuse_config.langfuse_client
+                langfuse.update_current_generation(
+                    metadata={
+                        "error": str(e),
+                        "error_type": type(e).__name__,
+                        "response_type": "technical_issue",
+                        "refinement_failed": False,
+                    }
+                )
             # Standardized technical issue; no second LLM call, no citations
             if request.environment == "test":
                 logger.info(
@@ -933,7 +1142,7 @@ def _generate_rag_response(
     # ========================================================================
     # Vector Indexer Support Methods (Isolated from RAG Pipeline)
     # ========================================================================
-
+    @observe(name="create_embeddings_for_indexer", as_type="span")
     def create_embeddings_for_indexer(
         self,
         texts: List[str],
diff --git a/src/llm_orchestrator_config/context_manager.py b/src/llm_orchestrator_config/context_manager.py
index d1e0358..a14447e 100644
--- a/src/llm_orchestrator_config/context_manager.py
+++ b/src/llm_orchestrator_config/context_manager.py
@@ -6,6 +6,7 @@
 
 from src.llm_orchestrator_config.llm_manager import LLMManager
 from src.models.request_models import ContextGenerationRequest
+from langfuse import observe
 
 
 class ContextGenerationManager:
@@ -30,6 +31,7 @@ def __init__(self, llm_manager: LLMManager) -> None:
         # Cache structure prepared for future prompt caching implementation
         self._cache: Dict[str, Any] = {}
 
+    @observe(name="generate_context_with_caching", as_type="generation")
     def generate_context_with_caching(
         self, request: ContextGenerationRequest
     ) -> Dict[str, Any]:
diff --git a/uv.lock b/uv.lock
index 8653912..5f79bf1 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1104,6 +1104,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/58/0d/41a51b40d24ff0384ec4f7ab8dd3dcea8353c05c973836b5e289f1465d4f/langchain_text_splitters-0.3.11-py3-none-any.whl", hash = "sha256:cf079131166a487f1372c8ab5d0bfaa6c0a4291733d9c43a34a16ac9bcd6a393", size = 33845, upload-time = "2025-08-31T23:02:57.195Z" },
 ]
 
+[[package]]
+name = "langfuse"
+version = "3.8.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "backoff" },
+    { name = "httpx" },
+    { name = "openai" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-exporter-otlp-proto-http" },
+    { name = "opentelemetry-sdk" },
+    { name = "packaging" },
+    { name = "pydantic" },
+    { name = "requests" },
+    { name = "wrapt" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ca/0b/81f9c6a982f79c112b7f10bfd6f3a4871e6fa3e4fe8d078b6112abfd3c08/langfuse-3.8.1.tar.gz", hash = "sha256:2464ae3f8386d80e1252a0e7406e3be4121e792a74f1b1c21d9950f658e5168d", size = 197401, upload-time = "2025-10-22T13:35:52.572Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b2/f9/538af0fc4219eb2484ba319483bce3383146f7a0923d5f39e464ad9a504b/langfuse-3.8.1-py3-none-any.whl", hash = "sha256:5b94b66ec0b0de388a8ea1f078b32c1666b5825b36eab863a21fdee78c53b3bb", size = 364580, upload-time = "2025-10-22T13:35:50.597Z" },
+]
+
 [[package]]
 name = "langsmith"
 version = "0.4.37"
@@ -1499,6 +1520,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/28/f0/bd831afbdba74ca2ce3982142a2fad707f8c487e8a3b6fef01f1d5945d1b/opentelemetry_exporter_otlp_proto_grpc-1.38.0-py3-none-any.whl", hash = "sha256:7c49fd9b4bd0dbe9ba13d91f764c2d20b0025649a6e4ac35792fb8d84d764bc7", size = 19695, upload-time = "2025-10-16T08:35:35.053Z" },
 ]
 
+[[package]]
+name = "opentelemetry-exporter-otlp-proto-http"
+version = "1.38.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "googleapis-common-protos" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-exporter-otlp-proto-common" },
+    { name = "opentelemetry-proto" },
+    { name = "opentelemetry-sdk" },
+    { name = "requests" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/81/0a/debcdfb029fbd1ccd1563f7c287b89a6f7bef3b2902ade56797bfd020854/opentelemetry_exporter_otlp_proto_http-1.38.0.tar.gz", hash = "sha256:f16bd44baf15cbe07633c5112ffc68229d0edbeac7b37610be0b2def4e21e90b", size = 17282, upload-time = "2025-10-16T08:35:54.422Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e5/77/154004c99fb9f291f74aa0822a2f5bbf565a72d8126b3a1b63ed8e5f83c7/opentelemetry_exporter_otlp_proto_http-1.38.0-py3-none-any.whl", hash = "sha256:84b937305edfc563f08ec69b9cb2298be8188371217e867c1854d77198d0825b", size = 19579, upload-time = "2025-10-16T08:35:36.269Z" },
+]
+
 [[package]]
 name = "opentelemetry-proto"
 version = "1.38.0"
@@ -2083,6 +2122,7 @@ dependencies = [
     { name = "dspy" },
     { name = "fastapi" },
     { name = "hvac" },
+    { name = "langfuse" },
     { name = "loguru" },
     { name = "nemoguardrails" },
     { name = "numpy" },
@@ -2114,6 +2154,7 @@ requires-dist = [
     { name = "dspy", specifier = ">=3.0.3" },
     { name = "fastapi", specifier = ">=0.116.1" },
     { name = "hvac", specifier = ">=2.3.0" },
+    { name = "langfuse", specifier = ">=3.8.1" },
     { name = "loguru", specifier = ">=0.7.3" },
     { name = "nemoguardrails", specifier = ">=0.16.0" },
     { name = "numpy", specifier = ">=2.3.2" },
@@ -2663,23 +2704,21 @@ wheels = [
 
 [[package]]
 name = "wrapt"
-version = "2.0.0"
+version = "1.17.3"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/49/19/5e5bcd855d808892fe02d49219f97a50f64cd6d8313d75df3494ee97b1a3/wrapt-2.0.0.tar.gz", hash = "sha256:35a542cc7a962331d0279735c30995b024e852cf40481e384fd63caaa391cbb9", size = 81722, upload-time = "2025-10-19T23:47:54.07Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/3c/28/7f266b5bf50c3ad0c99c524d99faa0f7d6eecb045d950e7d2c9e1f0e1338/wrapt-2.0.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:73c6f734aecb1a030d9a265c13a425897e1ea821b73249bb14471445467ca71c", size = 78078, upload-time = "2025-10-19T23:45:58.855Z" },
-    { url = "https://files.pythonhosted.org/packages/06/0c/bbdcad7eb535fae9d6b0fcfa3995c364797cd8e2b423bba5559ab2d88dcf/wrapt-2.0.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b4a7f8023b8ce8a36370154733c747f8d65c8697cb977d8b6efeb89291fff23e", size = 61158, upload-time = "2025-10-19T23:46:00.096Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/8a/bba3e7a4ebf4d1624103ee59d97b78a1fbb08fb5753ff5d1b69f5ef5e863/wrapt-2.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a1cb62f686c50e9dab5983c68f6c8e9cbf14a6007935e683662898a7d892fa69", size = 61646, upload-time = "2025-10-19T23:46:01.279Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/0c/0f565294897a72493dbafe7b46229b5f09f3776795a894d6b737e98387de/wrapt-2.0.0-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:43dc0550ae15e33e6bb45a82a5e1b5495be2587fbaa996244b509921810ee49f", size = 121442, upload-time = "2025-10-19T23:46:04.287Z" },
-    { url = "https://files.pythonhosted.org/packages/da/80/7f03501a8a078ad79b19b1a888f9192a9494e62ddf8985267902766a4f30/wrapt-2.0.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:39c5b45b056d630545e40674d1f5e1b51864b3546f25ab6a4a331943de96262e", size = 123018, upload-time = "2025-10-19T23:46:06.052Z" },
-    { url = "https://files.pythonhosted.org/packages/37/6b/ad0e1ff98359f13b4b0c2c52848e792841146fe79ac5f56899b9a028fc0d/wrapt-2.0.0-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:804e88f824b76240a1b670330637ccfd2d18b9efa3bb4f02eb20b2f64880b324", size = 117369, upload-time = "2025-10-19T23:46:02.53Z" },
-    { url = "https://files.pythonhosted.org/packages/ac/6c/a90437bba8cb1ce2ed639af979515e09784678c2a7f4ffc79f2cf7de809e/wrapt-2.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:c2c476aa3fc2b9899c3f7b20963fac4f952e7edb74a31fc92f7745389a2e3618", size = 121453, upload-time = "2025-10-19T23:46:07.747Z" },
-    { url = "https://files.pythonhosted.org/packages/2c/a9/b3982f9bd15bd45857a23c48b7c36e47d05db4a4dcc5061c31f169238845/wrapt-2.0.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:8d851e526891216f89fcb7a1820dad9bd503ba3468fb9635ee28e93c781aa98e", size = 116250, upload-time = "2025-10-19T23:46:09.385Z" },
-    { url = "https://files.pythonhosted.org/packages/73/e2/b7a8b1afac9f791d8f5eac0d9726559f1d7ec4a2b5a6b4e67ac145b007a5/wrapt-2.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b95733c2360c4a8656ee93c7af78e84c0bd617da04a236d7a456c8faa34e7a2d", size = 120575, upload-time = "2025-10-19T23:46:11.882Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/0f/37920eeea96094f450ae35505d39f1135df951a2cdee0d4e01d4f843396a/wrapt-2.0.0-cp312-cp312-win32.whl", hash = "sha256:ea56817176834edf143df1109ae8fdaa087be82fdad3492648de0baa8ae82bf2", size = 58175, upload-time = "2025-10-19T23:46:15.678Z" },
-    { url = "https://files.pythonhosted.org/packages/f0/db/b395f3b0c7f2c60d9219afacc54ceb699801ccf2d3d969ba556dc6d3af20/wrapt-2.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:3c7d3bee7be7a2665286103f4d1f15405c8074e6e1f89dac5774f9357c9a3809", size = 60415, upload-time = "2025-10-19T23:46:12.913Z" },
-    { url = "https://files.pythonhosted.org/packages/86/22/33d660214548af47fc59d9eec8c0e0693bcedc5b3a0b52e8cbdd61f3b646/wrapt-2.0.0-cp312-cp312-win_arm64.whl", hash = "sha256:680f707e1d26acbc60926659799b15659f077df5897a6791c7c598a5d4a211c4", size = 58911, upload-time = "2025-10-19T23:46:13.889Z" },
-    { url = "https://files.pythonhosted.org/packages/00/5c/c34575f96a0a038579683c7f10fca943c15c7946037d1d254ab9db1536ec/wrapt-2.0.0-py3-none-any.whl", hash = "sha256:02482fb0df89857e35427dfb844319417e14fae05878f295ee43fa3bf3b15502", size = 43998, upload-time = "2025-10-19T23:47:52.858Z" },
+sdist = { url = "https://files.pythonhosted.org/packages/95/8f/aeb76c5b46e273670962298c23e7ddde79916cb74db802131d49a85e4b7d/wrapt-1.17.3.tar.gz", hash = "sha256:f66eb08feaa410fe4eebd17f2a2c8e2e46d3476e9f8c783daa8e09e0faa666d0", size = 55547, upload-time = "2025-08-12T05:53:21.714Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9f/41/cad1aba93e752f1f9268c77270da3c469883d56e2798e7df6240dcb2287b/wrapt-1.17.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:ab232e7fdb44cdfbf55fc3afa31bcdb0d8980b9b95c38b6405df2acb672af0e0", size = 53998, upload-time = "2025-08-12T05:51:47.138Z" },
+    { url = "https://files.pythonhosted.org/packages/60/f8/096a7cc13097a1869fe44efe68dace40d2a16ecb853141394047f0780b96/wrapt-1.17.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:9baa544e6acc91130e926e8c802a17f3b16fbea0fd441b5a60f5cf2cc5c3deba", size = 39020, upload-time = "2025-08-12T05:51:35.906Z" },
+    { url = "https://files.pythonhosted.org/packages/33/df/bdf864b8997aab4febb96a9ae5c124f700a5abd9b5e13d2a3214ec4be705/wrapt-1.17.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6b538e31eca1a7ea4605e44f81a48aa24c4632a277431a6ed3f328835901f4fd", size = 39098, upload-time = "2025-08-12T05:51:57.474Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/81/5d931d78d0eb732b95dc3ddaeeb71c8bb572fb01356e9133916cd729ecdd/wrapt-1.17.3-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:042ec3bb8f319c147b1301f2393bc19dba6e176b7da446853406d041c36c7828", size = 88036, upload-time = "2025-08-12T05:52:34.784Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/38/2e1785df03b3d72d34fc6252d91d9d12dc27a5c89caef3335a1bbb8908ca/wrapt-1.17.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3af60380ba0b7b5aeb329bc4e402acd25bd877e98b3727b0135cb5c2efdaefe9", size = 88156, upload-time = "2025-08-12T05:52:13.599Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/8b/48cdb60fe0603e34e05cffda0b2a4adab81fd43718e11111a4b0100fd7c1/wrapt-1.17.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0b02e424deef65c9f7326d8c19220a2c9040c51dc165cddb732f16198c168396", size = 87102, upload-time = "2025-08-12T05:52:14.56Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/51/d81abca783b58f40a154f1b2c56db1d2d9e0d04fa2d4224e357529f57a57/wrapt-1.17.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:74afa28374a3c3a11b3b5e5fca0ae03bef8450d6aa3ab3a1e2c30e3a75d023dc", size = 87732, upload-time = "2025-08-12T05:52:36.165Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/b1/43b286ca1392a006d5336412d41663eeef1ad57485f3e52c767376ba7e5a/wrapt-1.17.3-cp312-cp312-win32.whl", hash = "sha256:4da9f45279fff3543c371d5ababc57a0384f70be244de7759c85a7f989cb4ebe", size = 36705, upload-time = "2025-08-12T05:53:07.123Z" },
+    { url = "https://files.pythonhosted.org/packages/28/de/49493f962bd3c586ab4b88066e967aa2e0703d6ef2c43aa28cb83bf7b507/wrapt-1.17.3-cp312-cp312-win_amd64.whl", hash = "sha256:e71d5c6ebac14875668a1e90baf2ea0ef5b7ac7918355850c0908ae82bcb297c", size = 38877, upload-time = "2025-08-12T05:53:05.436Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/48/0f7102fe9cb1e8a5a77f80d4f0956d62d97034bbe88d33e94699f99d181d/wrapt-1.17.3-cp312-cp312-win_arm64.whl", hash = "sha256:604d076c55e2fdd4c1c03d06dc1a31b95130010517b5019db15365ec4a405fc6", size = 36885, upload-time = "2025-08-12T05:52:54.367Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/f6/a933bd70f98e9cf3e08167fc5cd7aaaca49147e48411c0bd5ae701bb2194/wrapt-1.17.3-py3-none-any.whl", hash = "sha256:7171ae35d2c33d326ac19dd8facb1e82e5fd04ef8c6c0e394d7af55a55051c22", size = 23591, upload-time = "2025-08-12T05:53:20.674Z" },
 ]
 
 [[package]]
diff --git a/vault/agent-out/pidfile b/vault/agent-out/pidfile
deleted file mode 100644
index e69de29..0000000