@@ -43,20 +43,6 @@ The core API service that provides OpenAI-compatible endpoints and manages all c
4343- Swagger/OpenAPI documentation
4444- Built-in pprof profiling with Grafana Pyroscope integration
4545
46- ### Jan Inference Model
47- The AI model serving service that handles model inference requests.
48-
49- ** Key Features:**
50- - Scalable model serving infrastructure
51- - Health monitoring and automatic failover
52- - Load balancing across multiple model instances
53- - Integration with various AI model backends
54-
55- ** Technology Stack:**
56- - Python-based model serving
57- - Docker containerization
58- - Kubernetes-native deployment
59-
6046### PostgreSQL Database
6147The persistent data storage layer with enterprise-grade features.
6248
@@ -149,10 +135,10 @@ If you plan to run real LLM models (not mock servers) and have an NVIDIA GPU:
149135
150136### Production Deployment
151137
152- For production deployments, modify the Helm values in ` charts/umbrella-chart /values.yaml ` and deploy using:
138+ For production deployments, modify the Helm values in ` charts/jan-server /values.yaml ` and deploy using:
153139
154140``` bash
155- helm install jan-server ./charts/umbrella-chart
141+ helm install jan-server ./charts/jan-server
156142```
157143
158144## ⚙️ Configuration
@@ -182,8 +168,6 @@ The system is configured through environment variables defined in the Helm value
182168
183169The system uses Helm charts for deployment configuration:
184170
185- - ** Umbrella Chart** : Main deployment chart that orchestrates all services
186- - ** Service Charts** : Individual charts for each service (API Gateway, Inference Model)
187171- ** Values Files** : Configuration files for different environments
188172
189173## 🔧 Development
@@ -200,8 +184,7 @@ jan-server/
200184│ ├── application/ # Python application code
201185│ └── Dockerfile # Container configuration
202186├── charts/ # Helm charts
203- │ ├── apps-charts/ # Individual service charts
204- │ └── umbrella-chart/ # Main deployment chart
187+ │ └── jan-server/ # Main deployment chart
205188├── scripts/ # Deployment and utility scripts
206189└── README.md # This file
207190```
@@ -276,13 +259,13 @@ kubectl port-forward svc/jan-server-jan-api-gateway 8080:8080
276259### Production Deployment
277260``` bash
278261# Update Helm dependencies
279- helm dependency update ./charts/umbrella-chart
262+ helm dependency update ./charts/jan-server
280263
281264# Deploy to production
282- helm install jan-server ./charts/umbrella-chart
265+ helm install jan-server ./charts/jan-server
283266
284267# Upgrade deployment
285- helm upgrade jan-server ./charts/umbrella-chart
268+ helm upgrade jan-server ./charts/jan-server
286269
287270# Uninstall
288271helm uninstall jan-server
@@ -337,14 +320,14 @@ kubectl logs jan-server-jan-inference-model-<POD_ID>
337320** Solutions** :
338321``` bash
339322# Update Helm dependencies
340- helm dependency update ./charts/umbrella-chart
323+ helm dependency update ./charts/jan-server
341324
342325# Check Helm status
343326helm list
344327
345328# Uninstall and reinstall
346329helm uninstall jan-server
347- helm install jan-server ./charts/umbrella-chart
330+ helm install jan-server ./charts/jan-server
348331```
349332
350333## 📚 API Documentation
0 commit comments