Files
researchowl/k8s/deployment.yaml
T
ChemaVXandClaude Opus 4.8 9653898366
Build & Deploy ResearchOwl / build-and-push (push) Successful in 14s
docs: alinear modelos a qwen2.5:7b + bge-m3 (iGPU activa)
Generación 3B→7B y embeddings a bge-m3 en README, CLAUDE.md, .env.example y
k8s/deployment.yaml. Corregido el default buggy de config.py: ollama_embed_model
era qwen2.5:3b (un modelo de chat) → bge-m3. Añadido OLLAMA_EMBED_MODEL donde
faltaba. Nota del host público de ollama ahora tras Authentik.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-23 09:54:58 +00:00

99 lines
2.3 KiB
YAML

---
apiVersion: v1
kind: Namespace
metadata:
name: researchowl
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: researchowl-data
namespace: researchowl
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 10Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: researchowl
namespace: researchowl
labels:
app: researchowl
spec:
replicas: 1
selector:
matchLabels:
app: researchowl
template:
metadata:
labels:
app: researchowl
spec:
containers:
- name: researchowl
image: git.chemavx.xyz/chemavx/researchowl:latest
imagePullPolicy: Always
env:
- name: TELEGRAM_BOT_TOKEN
valueFrom:
secretKeyRef:
name: researchowl-secrets
key: telegram-bot-token
- name: TELEGRAM_ALLOWED_USERS
valueFrom:
secretKeyRef:
name: researchowl-secrets
key: telegram-allowed-users
- name: OLLAMA_URL
value: "http://ollama.chemavx.xyz"
- name: OLLAMA_MODEL
value: "qwen2.5:7b"
- name: OLLAMA_EMBED_MODEL
value: "bge-m3"
- name: DB_PATH
value: "/data/researchowl.db"
- name: MAX_SOURCES
value: "150"
- name: MAX_DEPTH
value: "3"
- name: QUALITY_THRESHOLD
value: "0.4"
volumeMounts:
- name: data
mountPath: /data
resources:
requests:
memory: "256Mi"
cpu: "100m"
limits:
memory: "1Gi"
cpu: "500m"
volumes:
- name: data
persistentVolumeClaim:
claimName: researchowl-data
imagePullSecrets:
- name: gitea-registry
---
# Secret template — fill with real values and apply manually
# kubectl create secret generic researchowl-secrets \
# --from-literal=telegram-bot-token=YOUR_TOKEN \
# --from-literal=telegram-allowed-users=YOUR_USER_ID \
# -n researchowl
apiVersion: v1
kind: Secret
metadata:
name: researchowl-secrets
namespace: researchowl
type: Opaque
stringData:
telegram-bot-token: "REPLACE_ME"
telegram-allowed-users: "REPLACE_ME"