gcloud-lab/apps/base/customer1/hermes-db/rag-init-job.yaml
Hermes Agent 4df7450461 feat(customer1): add pgvector RAG knowledge base with embedding service
- Custom PostgreSQL 15.2 image with pgvector 0.8.0 extension
- Updated pg-cluster-hermes.yaml: custom image, sharedPreloadLibraries, maintenance_work_mem
- RAG schema: documents table with vector(768) embeddings + HNSW index
- RAG init job: ConfigMap + Job to apply schema to agent_memory db
- Embedding service: FastAPI with nomic-embed-text-v1.5
  - OpenAI-compatible /v1/embeddings endpoint
  - Deployment (1 replica, 2Gi-4Gi memory) + Service manifests
- Updated kustomization.yaml to include new resources
2026-05-24 20:31:59 +00:00

41 lines
1.1 KiB
YAML

# Job to initialize RAG schema in agent_memory database
# Runs once after the cluster is available with pgvector
apiVersion: batch/v1
kind: Job
metadata:
name: init-rag-schema
namespace: customer1
annotations:
"helm.sh/hook": post-install,post-upgrade
"helm.sh/hook-delete-policy": hook-succeeded
spec:
template:
spec:
restartPolicy: Never
containers:
- name: psql
image: ghcr.io/cloudnative-pg/postgresql:15.2
command:
- /bin/sh
- -c
- |
PGPASSWORD=$(cat /run/secrets/postgresql/password) psql \
-h hermes-pgdb-rpostgres.customer1.svc.cluster.local \
-p 5432 \
-U memory \
-d agent_memory \
-f /sql/rag-db-init.sql
env:
- name: PGPASSWORD
valueFrom:
secretKeyRef:
name: memory-db-credentials
key: password
volumeMounts:
- name: rag-sql
mountPath: /sql
volumes:
- name: rag-sql
configMap:
name: rag-init-sql