Files
skill-seekers-reference/helm/skill-seekers/templates/pvc.yaml
yusyus 8b3f31409e fix: Enforce min_chunk_size in RAG chunker
- Filter out chunks smaller than min_chunk_size (default 100 tokens)
- Exception: Keep all chunks if entire document is smaller than target size
- All 15 tests passing (100% pass rate)

Fixes edge case where very small chunks (e.g., 'Short.' = 6 chars) were
being created despite min_chunk_size=100 setting.

Test: pytest tests/test_rag_chunker.py -v
2026-02-07 20:59:03 +03:00

111 lines
3.4 KiB
YAML

{{- if .Values.persistence.data.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "skill-seekers.fullname" . }}-data
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.persistence.data.accessMode }}
{{- if .Values.persistence.data.storageClass }}
storageClassName: {{ .Values.persistence.data.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.persistence.data.size }}
{{- end }}
---
{{- if .Values.persistence.output.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "skill-seekers.fullname" . }}-output
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.persistence.output.accessMode }}
{{- if .Values.persistence.output.storageClass }}
storageClassName: {{ .Values.persistence.output.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.persistence.output.size }}
{{- end }}
---
{{- if .Values.persistence.configs.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "skill-seekers.fullname" . }}-configs
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.persistence.configs.accessMode }}
{{- if .Values.persistence.configs.storageClass }}
storageClassName: {{ .Values.persistence.configs.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.persistence.configs.size }}
{{- end }}
---
{{- if and .Values.vectorDatabases.weaviate.enabled .Values.vectorDatabases.weaviate.persistence.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "skill-seekers.fullname" . }}-weaviate-data
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
app.kubernetes.io/component: weaviate
spec:
accessModes:
- ReadWriteOnce
{{- if .Values.vectorDatabases.weaviate.persistence.storageClass }}
storageClassName: {{ .Values.vectorDatabases.weaviate.persistence.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.vectorDatabases.weaviate.persistence.size }}
{{- end }}
---
{{- if and .Values.vectorDatabases.qdrant.enabled .Values.vectorDatabases.qdrant.persistence.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "skill-seekers.fullname" . }}-qdrant-data
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
app.kubernetes.io/component: qdrant
spec:
accessModes:
- ReadWriteOnce
{{- if .Values.vectorDatabases.qdrant.persistence.storageClass }}
storageClassName: {{ .Values.vectorDatabases.qdrant.persistence.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.vectorDatabases.qdrant.persistence.size }}
{{- end }}
---
{{- if and .Values.vectorDatabases.chroma.enabled .Values.vectorDatabases.chroma.persistence.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "skill-seekers.fullname" . }}-chroma-data
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
app.kubernetes.io/component: chroma
spec:
accessModes:
- ReadWriteOnce
{{- if .Values.vectorDatabases.chroma.persistence.storageClass }}
storageClassName: {{ .Values.vectorDatabases.chroma.persistence.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.vectorDatabases.chroma.persistence.size }}
{{- end }}