Helm tuning (#1553)

backend/danswer/search/search_nlp_models.py

@@ -24,6 +24,7 @@ transformer_logging.set_verbosity_error()
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"
+os.environ["TRANSFORMERS_NO_ADVISORY_WARNINGS"] = "1"
 
 logger = setup_logger()
 

deployment/helm/values.yaml

@@ -194,17 +194,17 @@ api:
     type: ClusterIP
     port: 8080
 
-  resources:
+  resources: {}
   # We usually recommend not to specify default resources and to leave this as a conscious
   # choice for the user. This also increases chances charts run on environments with little
   # resources, such as Minikube. If you do want to specify resources, uncomment the following
   # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
-    requests:
-      cpu: 500m
-      memory: 128Mi
-    limits:
-      cpu: 900m
-      memory: 512Mi
+  #  requests:
+  #    cpu: 1000m  # Requests 1 CPU core
+  #    memory: 1Gi  # Requests 1 GiB of memory
+  #  limits:
+  #    cpu: 2000m  # Limits to 2 CPU cores
+  #    memory: 2Gi  # Limits to 2 GiB of memory
 
   autoscaling:
     enabled: false
@@ -254,17 +254,17 @@ background:
     # runAsNonRoot: true
     # runAsUser: 1000
   enableMiniChunk: "true"
-  resources:
+  resources: {}
   # We usually recommend not to specify default resources and to leave this as a conscious
   # choice for the user. This also increases chances charts run on environments with little
   # resources, such as Minikube. If you do want to specify resources, uncomment the following
   # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
-    requests:
-      cpu: 500m
-      memory: 500Mi
-    limits:
-      cpu: 900m
-      memory: 800Mi
+  #  requests:
+  #    cpu: 1000m  # Requests 1 CPU core
+  #    memory: 1Gi  # Requests 1 GiB of memory
+  #  limits:
+  #    cpu: 2000m  # Limits to 2 CPU cores
+  #    memory: 2Gi  # Limits to 2 GiB of memory
 
   autoscaling:
     enabled: false

deployment/kubernetes/postgres-service-deployment.yaml

@@ -54,4 +54,4 @@ spec:
       resources:
         requests:
           # Adjust the storage request size as needed.
-          storage: 1Gi
+          storage: 5Gi

deployment/kubernetes/vespa-service-deployment.yaml

@@ -60,4 +60,4 @@ spec:
       resources:
         requests:
           # Adjust the storage request size as needed.
-          storage: 1Gi
+          storage: 5Gi