7902b265a9
- Add comprehensive AI plans implementation documentation - Add LiteLLM gateway Kubernetes manifests - Update PostgreSQL and Forgejo deployment configs - Add build-from-binaries script
94 lines
2.8 KiB
YAML
94 lines
2.8 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: litellm-config
|
|
namespace: nxtgauge-ai
|
|
data:
|
|
config.yaml: |
|
|
model_list:
|
|
# === FAST MODEL (qwen3:4b) - 2.5GB ===
|
|
- model_name: askash-fast
|
|
litellm_params:
|
|
model: ollama/qwen3:4b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 60
|
|
|
|
- model_name: recommender
|
|
litellm_params:
|
|
model: ollama/qwen3:4b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 60
|
|
|
|
- model_name: messenger
|
|
litellm_params:
|
|
model: ollama/qwen3:4b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 60
|
|
|
|
- model_name: safety-check
|
|
litellm_params:
|
|
model: ollama/qwen3:4b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 60
|
|
|
|
- model_name: help-assistant
|
|
litellm_params:
|
|
model: ollama/qwen3:4b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 60
|
|
|
|
# === POWER MODEL (qwen3:8b) - 5.2GB ===
|
|
- model_name: askash-main
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: jd-generator
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: profile-writer
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: service-writer
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: requirement-writer
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: support-drafter
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: decision-support
|
|
litellm_params:
|
|
model: ollama/qwen3:8b
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 300
|
|
|
|
- model_name: ultra-fast
|
|
litellm_params:
|
|
model: ollama/gemma3:270m
|
|
api_base: http://ollama.nxtgauge-ai.svc.cluster.local:11434
|
|
timeout: 30
|
|
|
|
general_settings:
|
|
master_key: os.environ/LITELLM_MASTER_KEY
|
|
|
|
router_settings:
|
|
fallback_retries: 2
|
|
timeout: 300
|