docs: alinear modelos a qwen2.5:7b + bge-m3 (iGPU activa)
Build & Deploy ResearchOwl / build-and-push (push) Successful in 14s

Generación 3B→7B y embeddings a bge-m3 en README, CLAUDE.md, .env.example y
k8s/deployment.yaml. Corregido el default buggy de config.py: ollama_embed_model
era qwen2.5:3b (un modelo de chat) → bge-m3. Añadido OLLAMA_EMBED_MODEL donde
faltaba. Nota del host público de ollama ahora tras Authentik.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
ChemaVX
2026-07-23 09:54:58 +00:00
co-authored by Claude Opus 4.8
parent 6029bebae5
commit 9653898366
5 changed files with 12 additions and 9 deletions
+2 -2
View File
@@ -17,8 +17,8 @@ class Settings(BaseSettings):
# Ollama
ollama_url: str = Field("http://ollama.chemavx.xyz")
ollama_model: str = Field("qwen2.5:3b")
ollama_embed_model: str = Field("qwen2.5:3b")
ollama_model: str = Field("qwen2.5:7b")
ollama_embed_model: str = Field("bge-m3")
# Claude fallback (optional)
anthropic_api_key: Optional[str] = Field(None)