tocmo0nlord/odoo-ai
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

fix: raise Ollama timeout to 300s, add model pre-warming, improve health check

Browse Source 
- OllamaBackend enforces _MIN_TIMEOUT=300s (overrides OLLAMA_TIMEOUT env var)
- warm_model() background task loads activeblue-chat into VRAM at startup
- health/detailed reports "warming" vs "ok" via Ollama ps() API
- README updated with May 2026 changes and test coverage details
This commit is contained in:
Carlos Garcia
2026-05-20 05:03:15 +00:00
parent 20a69313d7
commit 564f1a9479
5 changed files with 72 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
agent_service/config.py
View File

@@ -14,7 +14,7 @@ class Settings(BaseSettings):
# Ollama
ollama_url: str = 'http://localhost:11434'
ollama_model: str = 'activeblue-chat'
ollama_timeout: int = 120
ollama_timeout: int = 300
ollama_max_concurrent: int = 2
# Set to a vision-capable model (e.g. llama3.2-vision:11b) to use
# vision OCR for receipt images instead of Tesseract. Leave empty