feat(jupyterhub): set postgres env-vars and add python packages

jupyterhub/images/datastack-cuda-notebook/Dockerfile

@@ -70,7 +70,9 @@ RUN mamba install --yes \
     'aif360' \
     'airflow' \
     'chromadb' \
+    'csvkit' \
     'dalex' \
+    'datafusion' \
     'dbt' \
     'dlt' \
     'duckdb' \
@@ -78,6 +80,7 @@ RUN mamba install --yes \
     'gitpython' \
     'grpcio-status' \
     'grpcio' \
+    'hvac' \
     'keras' \
     'langchain' \
     'langchain-ai21' \
@@ -112,6 +115,7 @@ RUN mamba install --yes \
     'pandas-profiling' \
     'pillow' \
     'polars' \
+    'psycopg2' \
     'pyarrow' \
     'qdrant-client' \
     'rapidfuzz' \
@@ -130,7 +134,6 @@ RUN pip install \
     agno \
     fastembed \
     feature-engine \
-    hvac \
     jupyter-ai \
     jupyter-ai-magics[all] \
     kreuzberg \

jupyterhub/images/datastack-notebook/Dockerfile

@@ -70,7 +70,9 @@ RUN mamba install --yes \
     'aif360' \
     'airflow' \
     'chromadb' \
+    'csvkit' \
     'dalex' \
+    'datafusion' \
     'dbt' \
     'dlt' \
     'duckdb' \
@@ -78,6 +80,7 @@ RUN mamba install --yes \
     'gitpython' \
     'grpcio-status' \
     'grpcio' \
+    'hvac' \
     'keras' \
     'langchain' \
     'langchain-ai21' \
@@ -112,6 +115,7 @@ RUN mamba install --yes \
     'pandas-profiling' \
     'pillow' \
     'polars' \
+    'psycopg2' \
     'pyarrow' \
     'qdrant-client' \
     'rapidfuzz' \
@@ -130,7 +134,6 @@ RUN pip install \
     agno \
     fastembed \
     feature-engine \
-    hvac \
     jupyter-ai \
     jupyter-ai-magics[all] \
     kreuzberg \

jupyterhub/jupyterhub-values.gomplate.yaml

@@ -49,6 +49,23 @@ hub:
 
       c.Spawner.pre_spawn_hook = pre_spawn_hook
 {{- end }}
+    02-postgres-integration: |
+      from functools import wraps
+
+      # Store the original pre_spawn_hook if it exists
+      original_hook = c.Spawner.pre_spawn_hook if hasattr(c.Spawner, 'pre_spawn_hook') else None
+
+      async def postgres_pre_spawn_hook(spawner):
+          """Add PostgreSQL connection information to notebook environment"""
+          # Call the original hook first if it exists
+          if original_hook:
+              await original_hook(spawner)
+
+          # Add PostgreSQL configuration
+          spawner.environment['POSTGRES_HOST'] = 'postgres-cluster-rw.postgres'
+          spawner.environment['POSTGRES_PORT'] = '5432'
+
+      c.Spawner.pre_spawn_hook = postgres_pre_spawn_hook
 
   podSecurityContext:
     fsGroup: {{ .Env.JUPYTER_FSGID }}
@@ -74,16 +91,16 @@ singleuser:
     KEYCLOAK_HOST: "{{ .Env.KEYCLOAK_HOST }}"
     KEYCLOAK_REALM: "{{ .Env.KEYCLOAK_REALM }}"
 
-  lifecycleHooks:
-    postStart:
-      exec:
-        command:
-          - /bin/bash
-          - -c
-          - |
-            # Install hvac for Vault integration
-            pip install --quiet hvac requests
-            echo "Vault integration ready"
+  # lifecycleHooks:
+  #   postStart:
+  #     exec:
+  #       command:
+  #         - /bin/bash
+  #         - -c
+  #         - |
+  #           # Install hvac for Vault integration
+  #           mamba install hvac requests
+  #           echo "Vault integration ready"
 {{- end }}
   networkPolicy:
     egress:

jupyterhub/justfile

@@ -5,7 +5,7 @@ export JUPYTERHUB_CHART_VERSION := env("JUPYTERHUB_CHART_VERSION", "4.2.0")
 export JUPYTERHUB_OIDC_CLIENT_ID := env("JUPYTERHUB_OIDC_CLIENT_ID", "jupyterhub")
 export JUPYTERHUB_NFS_PV_ENABLED := env("JUPYTERHUB_NFS_PV_ENABLED", "")
 export JUPYTERHUB_VAULT_INTEGRATION_ENABLED := env("JUPYTERHUB_VAULT_INTEGRATION_ENABLED", "")
-export JUPYTER_PYTHON_KERNEL_TAG := env("JUPYTER_PYTHON_KERNEL_TAG", "python-3.12-6")
+export JUPYTER_PYTHON_KERNEL_TAG := env("JUPYTER_PYTHON_KERNEL_TAG", "python-3.12-8")
 export KERNEL_IMAGE_BUUN_STACK_REPOSITORY := env("KERNEL_IMAGE_BUUN_STACK_REPOSITORY", "buun-stack-notebook")
 export KERNEL_IMAGE_BUUN_STACK_CUDA_REPOSITORY := env("KERNEL_IMAGE_BUUN_STACK_CUDA_REPOSITORY", "buun-stack-cuda-notebook")
 export JUPYTER_PROFILE_MINIMAL_ENABLED := env("JUPYTER_PROFILE_MINIMAL_ENABLED", "false")