fix(rag): use bge embeddings on GCP Ollama lane
Some checks failed
Code Review / ai-code-review (push) Successful in 11s
CD Pipeline / tests (push) Successful in 1m22s
CD Pipeline / build-and-deploy (push) Failing after 2h14m5s
CD Pipeline / post-deploy-checks (push) Has been cancelled

This commit is contained in:
Your Name
2026-05-06 05:49:27 +08:00
parent a4fece11cc
commit 09256be62c
7 changed files with 29 additions and 15 deletions

View File

@@ -376,6 +376,10 @@ class Settings(BaseSettings):
default="gemma3:4b",
description="OllamaHealthMonitor 推理測試使用模型P1.1",
)
OLLAMA_EMBEDDING_MODEL: str = Field(
default="bge-m3:latest",
description="Ollama embedding model. ADR-110 migrated embeddings from nomic-embed-text to bge-m3.",
)
# 2026-04-12 ogt: 心跳必須確認載入的 Ollama 模型清單
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級更新必要模型清單nomic→bge-m3 + 新增 qwen3:14b + hermes3
OLLAMA_REQUIRED_MODELS: list[str] = Field(