claudeandClaude Opus 5.5
dd5f03f074
LOCALAI_WATCHDOG_BUSY had no matching timeout setting, so the role could only ever use LocalAI's built-in 5 minutes. On the throttled Tesla T4 a legitimate request can take more than 6 minutes, so default to 10 minutes, which also matches the ingress proxy-read-timeout. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
25 lines
858 B
YAML
25 lines
858 B
YAML
#SPDX-License-Identifier: MIT-0
|
|
---
|
|
# defaults file for ansible-role-localai
|
|
localai_disable_webui: "false"
|
|
localai_api_keys:
|
|
- "123abc"
|
|
- "abc123"
|
|
localai_watchdog_idle: "false"
|
|
localai_watchdog_idle_timeout: "15m"
|
|
localai_watchdog_busy: "true"
|
|
localai_watchdog_busy_timeout: "10m"
|
|
localai_image_tag: latest-gpu-nvidia-cuda-13
|
|
localai_debug: "false"
|
|
localai_p2p: "false"
|
|
localai_federated: "false"
|
|
# Persistent state lives on the models PVC (mounted at /models).
|
|
localai_data_path: /models/.localai/data
|
|
localai_config_dir: /models/.localai/configuration
|
|
localai_backends_path: /models/.backends
|
|
localai_agent_pool_default_model: ornith-1.5-9b-q8
|
|
localai_agent_pool_embedding_model: granite-embedding-107m-multilingual
|
|
localai_host_network: true
|
|
# Name of a Secret holding LOCALAI_P2P_TOKEN; empty skips the patch.
|
|
localai_p2p_token_secret: localai-p2p
|