194c87f53c
- Node Worker: replace swapper_vision with ollama_vision (direct Ollama API) - Node Worker: add NATS subjects for stt/tts/image (stubs ready) - Node Worker: remove SWAPPER_URL dependency from config - Router: vision calls go directly to Ollama /api/generate with images - Router: local LLM calls go directly to Ollama /api/generate - Router: add OLLAMA_URL and PREFER_NODE_WORKER=true feature flag - Router: /v1/models now uses NCS global capabilities pool - NCS: SWAPPER_URL="" -> skip Swapper probing (status=disabled) - Swapper configs: remove all hardcoded model lists, keep only runtime URLs, timeouts, limits - docker-compose.node1.yml: add OLLAMA_URL, PREFER_NODE_WORKER for router; SWAPPER_URL= for NCS; remove swapper-service from node-worker depends_on - docker-compose.node2-sofiia.yml: same changes for NODA2 Swapper service still runs but is NOT in the critical inference path. Source of truth for models is now NCS -> Ollama /api/tags. Made-with: Cursor
12 lines
556 B
Python
12 lines
556 B
Python
"""Node-worker configuration from environment."""
|
|
import os
|
|
|
|
NODE_ID = os.getenv("NODE_ID", "noda2")
|
|
NATS_URL = os.getenv("NATS_URL", "nats://dagi-nats:4222")
|
|
OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://host.docker.internal:11434")
|
|
DEFAULT_LLM = os.getenv("NODE_DEFAULT_LLM", "qwen3:14b")
|
|
DEFAULT_VISION = os.getenv("NODE_DEFAULT_VISION", "llava:13b")
|
|
MAX_CONCURRENCY = int(os.getenv("NODE_WORKER_MAX_CONCURRENCY", "2"))
|
|
MAX_PAYLOAD_BYTES = int(os.getenv("NODE_WORKER_MAX_PAYLOAD_BYTES", str(1024 * 1024)))
|
|
PORT = int(os.getenv("PORT", "8109"))
|