Pass `TRUNCATE_PROMPT_LENGTH` to deployment, switch to `ghcr.io` image (#63)

Signed-off-by: Hung-Han (Henry) Chen <chenhungh@gmail.com>

charts/ialacol/Chart.yaml

 apiVersion: v2
-appVersion: 0.11.0
+appVersion: 0.11.1
 description: A Helm chart for ialacol
 name: ialacol
 type: application
-version: 0.11.0
+version: 0.11.1

charts/ialacol/templates/deployment.yaml

@@ -57,6 +57,8 @@ spec:
             value: {{ (.Values.deployment.env).GPU_LAYERS | quote }}
           - name: MODE_TYPE
             value: {{ (.Values.deployment.env).MODE_TYPE | quote }}
+          - name: TRUNCATE_PROMPT_LENGTH
+            value: {{ (.Values.deployment.env).TRUNCATE_PROMPT_LENGTH | quote }}
           volumeMounts:
           - mountPath: /app/models
             name: model

charts/ialacol/values.yaml

 replicas: 1
 
 deployment:
-  image: quay.io/chenhunghan/ialacol:latest
+  image: ghcr.io/chenhunghan/ialacol:latest
   # or use CUDA image `ghcr.io/chenhunghan/ialacol-cuda12:latest`
   # env:
     # DEFAULT_MODEL_HG_REPO_ID: TheBloke/Llama-2-7B-Chat-GGML