docs: Update example resources and improve README (#231)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docs/configuration.md

@@ -60,7 +60,7 @@ The selected compute engine will be running all the async jobs.
 
 #### Local engine
 
-The following table describes the options to configure the Docling Serve KFP engine.
+The following table describes the options to configure the Docling Serve local engine.
 
 | ENV | Default | Description |
 |-----|---------|-------------|

docs/deploy-examples/docling-model-cache-deployment.yaml

@@ -22,8 +22,8 @@ spec:
         - name: api
           resources:
             limits:
-              cpu: 500m
-              memory: 2Gi
+              cpu: 2
+              memory: 4Gi
             requests:
               cpu: 250m
               memory: 1Gi

docs/deploy-examples/docling-serve-oauth.yaml

@@ -85,7 +85,7 @@ spec:
           resources:
             limits:
               cpu: 2000m
-              memory: 2Gi
+              memory: 4Gi
             requests:
               cpu: 800m
               memory: 1Gi

docs/deploy-examples/docling-serve-replicas-w-sticky-sessions.yaml

@@ -60,8 +60,8 @@ spec:
         - name: api
           resources:
             limits:
-              cpu: 500m
-              memory: 2Gi
+              cpu: 1
+              memory: 4Gi
             requests:
               cpu: 250m
               memory: 1Gi

docs/deploy-examples/docling-serve-simple.yaml

@@ -40,8 +40,8 @@ spec:
         - name: api
           resources:
             limits:
-              cpu: 500m
-              memory: 2Gi
+              cpu: 1
+              memory: 4Gi
               nvidia.com/gpu: 1  # Limit to one GPU
             requests:
               cpu: 250m