Files
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

51 lines
1.6 KiB
YAML

{{- if .Values.vectorDatabases.qdrant.enabled -}}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "skill-seekers.fullname" . }}-qdrant
labels:
{{- include "skill-seekers.labels" . | nindent 4 }}
app.kubernetes.io/component: qdrant
spec:
replicas: {{ .Values.vectorDatabases.qdrant.replicaCount }}
selector:
matchLabels:
{{- include "skill-seekers.selectorLabels" . | nindent 6 }}
app.kubernetes.io/component: qdrant
template:
metadata:
labels:
{{- include "skill-seekers.selectorLabels" . | nindent 8 }}
app.kubernetes.io/component: qdrant
spec:
containers:
- name: qdrant
image: "{{ .Values.vectorDatabases.qdrant.image.repository }}:{{ .Values.vectorDatabases.qdrant.image.tag }}"
imagePullPolicy: {{ .Values.vectorDatabases.qdrant.image.pullPolicy }}
ports:
- name: http
containerPort: 6333
protocol: TCP
- name: grpc
containerPort: 6334
protocol: TCP
env:
- name: QDRANT__SERVICE__HTTP_PORT
value: "6333"
- name: QDRANT__SERVICE__GRPC_PORT
value: "6334"
resources:
{{- toYaml .Values.vectorDatabases.qdrant.resources | nindent 12 }}
volumeMounts:
- name: data
mountPath: /qdrant/storage
volumes:
- name: data
{{- if .Values.vectorDatabases.qdrant.persistence.enabled }}
persistentVolumeClaim:
claimName: {{ include "skill-seekers.fullname" . }}-qdrant-data
{{- else }}
emptyDir: {}
{{- end }}
{{- end }}