6c19f82a0a
- ai: remove reranker service (moved to Serenity at 10.5.1.5:9787) - ai: add LiteLLM reranker proxy entry for Serenity - ai: configure OpenWebUI to use LiteLLM for reranking - monitoring: add Grafana + Prometheus stack - mesh-mqtt-observer: add new service - automation, documents, meshtastic: misc updates
105 lines
2.7 KiB
YAML
105 lines
2.7 KiB
YAML
model_list:
|
|
# ---- Reranker (Serenity, 10.5.1.5) ----
|
|
- model_name: "reranker"
|
|
litellm_params:
|
|
model: "huggingface/BAAI/bge-reranker-v2-m3"
|
|
api_base: "http://10.5.1.5:9787"
|
|
# ---- ROCINANTE (RTX 4090, 24GB) — heavy reasoning ----
|
|
- model_name: "heavy"
|
|
litellm_params:
|
|
model: "ollama/qwen3.6:latest"
|
|
api_base: "http://10.5.1.112:11434"
|
|
timeout: 300
|
|
stream_timeout: 300
|
|
|
|
- model_name: "heavy"
|
|
litellm_params:
|
|
model: "ollama/qwen2.5:32b"
|
|
api_base: "http://10.5.1.112:11434"
|
|
timeout: 300
|
|
stream_timeout: 300
|
|
|
|
- model_name: "heavy"
|
|
litellm_params:
|
|
model: "ollama/gemma3:27b"
|
|
api_base: "http://10.5.1.112:11434"
|
|
timeout: 300
|
|
stream_timeout: 300
|
|
|
|
# ---- PlausibleDeniability (RTX 2080 Ti, 11GB) — general ----
|
|
- model_name: "medium"
|
|
litellm_params:
|
|
model: "ollama/qwen2.5:14b"
|
|
api_base: "http://host.docker.internal:11434"
|
|
timeout: 120
|
|
stream_timeout: 120
|
|
|
|
# ---- N.O.M.A.D. (GTX 1080, 8GB) — lightweight ----
|
|
- model_name: "light"
|
|
litellm_params:
|
|
model: "ollama/deepseek-r1"
|
|
api_base: "http://10.5.1.16:11434"
|
|
timeout: 60
|
|
stream_timeout: 60
|
|
|
|
- model_name: "light"
|
|
litellm_params:
|
|
model: "ollama/qwen2.5:3b"
|
|
api_base: "http://10.5.1.16:11434"
|
|
timeout: 60
|
|
stream_timeout: 60
|
|
|
|
# ---- Embeddings (N.O.M.A.D. has nomic-embed-text) ----
|
|
- model_name: "embed"
|
|
litellm_params:
|
|
model: "ollama/nomic-embed-text:v1.5"
|
|
api_base: "http://10.5.1.16:11434"
|
|
|
|
# ---- Direct model access (bypass tier routing) ----
|
|
- model_name: "ollama/qwen3.6:latest"
|
|
litellm_params:
|
|
model: "ollama/qwen3.6:latest"
|
|
api_base: "http://10.5.1.112:11434"
|
|
|
|
- model_name: "ollama/qwen2.5:32b"
|
|
litellm_params:
|
|
model: "ollama/qwen2.5:32b"
|
|
api_base: "http://10.5.1.112:11434"
|
|
|
|
- model_name: "ollama/gemma3:27b"
|
|
litellm_params:
|
|
model: "ollama/gemma3:27b"
|
|
api_base: "http://10.5.1.112:11434"
|
|
|
|
- model_name: "ollama/qwen2.5:14b"
|
|
litellm_params:
|
|
model: "ollama/qwen2.5:14b"
|
|
api_base: "http://host.docker.internal:11434"
|
|
|
|
- model_name: "ollama/deepseek-r1"
|
|
litellm_params:
|
|
model: "ollama/deepseek-r1"
|
|
api_base: "http://10.5.1.16:11434"
|
|
|
|
- model_name: "ollama/qwen2.5:3b"
|
|
litellm_params:
|
|
model: "ollama/qwen2.5:3b"
|
|
api_base: "http://10.5.1.16:11434"
|
|
|
|
- model_name: "ollama/nomic-embed-text:v1.5"
|
|
litellm_params:
|
|
model: "ollama/nomic-embed-text:v1.5"
|
|
api_base: "http://10.5.1.16:11434"
|
|
|
|
litellm_settings:
|
|
drop_params: true
|
|
set_verbose: false
|
|
request_timeout: 300
|
|
num_retries: 2
|
|
retry_after: 5
|
|
allowed_fails: 3
|
|
cooldown_time: 60
|
|
|
|
general_settings:
|
|
master_key: "os.environ/LITELLM_MASTER_KEY"
|