From 27ba97e5860e38a1de3eaf276724671aecab3f42 Mon Sep 17 00:00:00 2001 From: OG T Date: Thu, 16 Apr 2026 03:01:31 +0800 Subject: [PATCH] =?UTF-8?q?fix(ollama):=20=E6=B8=85=E9=99=A4=E6=89=80?= =?UTF-8?q?=E6=9C=89=E7=A1=AC=E5=AF=AB=20188:11434=20fallback=20=E2=80=94?= =?UTF-8?q?=20=E5=85=A8=E9=83=A8=E6=94=B9=E6=8C=87=E5=90=91=20111=20GPU?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - decision_manager.py: 兩處 getattr fallback 188 → 111 - routes/agent.py: OLLAMA_BASE_URL 188 → 111 - knowledge_extractor_service.py: _OLLAMA_BASE 188 → 111 config.py 預設早已是 111，此次清掉 code 層殘留的 188 硬寫值。 Co-Authored-By: Claude Sonnet 4.6 --- apps/api/src/routes/agent.py | 2 +- apps/api/src/services/decision_manager.py | 4 ++-- apps/api/src/services/knowledge_extractor_service.py | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/apps/api/src/routes/agent.py b/apps/api/src/routes/agent.py index 3a869e48..25dcc3f2 100644 --- a/apps/api/src/routes/agent.py +++ b/apps/api/src/routes/agent.py @@ -19,7 +19,7 @@ router = APIRouter() logger = logging.getLogger(__name__) # ==================== Ollama Config ==================== -OLLAMA_BASE_URL = "http://192.168.0.188:11434" +OLLAMA_BASE_URL = "http://192.168.0.111:11434" OLLAMA_MODEL = "llama3.2:latest" # 可根據實際部署調整 OLLAMA_TIMEOUT = 120.0 # 串流超時 diff --git a/apps/api/src/services/decision_manager.py b/apps/api/src/services/decision_manager.py index 72bad999..20eb19e8 100644 --- a/apps/api/src/services/decision_manager.py +++ b/apps/api/src/services/decision_manager.py @@ -402,7 +402,7 @@ async def _nemoclaw_second_opinion(incident: "Incident", primary_result: dict) - import httpx as _httpx from src.services.model_registry import get_model as _get_model - ollama_url = getattr(settings, "OLLAMA_URL", "http://192.168.0.188:11434") + ollama_url = getattr(settings, "OLLAMA_URL", "http://192.168.0.111:11434") # D1 集中化 2026-04-11: 從 models.json providers.ollama.models.nemoclaw 讀取 model = _get_model("ollama", "nemoclaw") @@ -495,7 +495,7 @@ async def _generate_playbook_draft_if_new(incident: "Incident") -> None: ) from src.services.model_registry import get_model as _get_model - ollama_url = getattr(settings, "OLLAMA_URL", "http://192.168.0.188:11434") + ollama_url = getattr(settings, "OLLAMA_URL", "http://192.168.0.111:11434") # D1 集中化 2026-04-11: 從 models.json providers.ollama.models.playbook_draft 讀取 _pb_model = _get_model("ollama", "playbook_draft") async with _httpx.AsyncClient(timeout=45.0) as client: diff --git a/apps/api/src/services/knowledge_extractor_service.py b/apps/api/src/services/knowledge_extractor_service.py index aa37fce6..43190693 100644 --- a/apps/api/src/services/knowledge_extractor_service.py +++ b/apps/api/src/services/knowledge_extractor_service.py @@ -15,7 +15,7 @@ import structlog logger = structlog.get_logger(__name__) -_OLLAMA_BASE = "http://192.168.0.188:11434" +_OLLAMA_BASE = "http://192.168.0.111:11434" _EXTRACT_MODEL = "llama3.2:3b" _EXTRACT_TIMEOUT = 30.0 # 秒，容忍慢速