Compare commits

..

3 commits

Author SHA1 Message Date
sudoxreboot
a28b4ee672
Update README.md 2026-03-11 21:38:47 -05:00
sudoxreboot
84ee01f4ca
Update README.md 2026-03-11 21:38:19 -05:00
sudoxreboot
50a6a152c4
Update const.py 2026-03-11 21:38:00 -05:00
2 changed files with 2 additions and 9 deletions

View file

@ -49,7 +49,7 @@
## Quick Start
- Create a new groqd entry.
- Set your Groq API key.
- Pick a model (default: `meta-llama/llama-4-maverick-17b-128e-instruct`).
- Pick a model (default: `meta-llama/llama-4-scout-17b-16e-instruct`).
- Set a personality prompt if you want tone/style changes.
## Options
@ -62,13 +62,6 @@ Open **groqd → Options** to configure:
- Auto-fetch URLs in user messages
- Time format (12h / 24h)
## Recommended Prompt Additions
To make tone warmer and lyrical:
"""
Be warm, playful, and a bit lyrical. If the user quotes lyrics, continue one line then respond empathetically.
"""
## Notes
- TTS/STT are handled by Home Assistant and other integrations.
- Web search is optional and only used if enabled.

View file

@ -30,7 +30,7 @@ CONF_SEARXNG_LANGUAGE = "searxng_language"
CONF_AUTO_FETCH_URLS = "auto_fetch_urls"
CONF_TIME_FORMAT = "time_format"
DEFAULT_CHAT_MODEL = "meta-llama/llama-4-maverick-17b-128e-instruct"
DEFAULT_CHAT_MODEL = "meta-llama/llama-4-scout-17b-16e-instruct"
DEFAULT_CONTEXT_MESSAGES = 20
DEFAULT_MAX_TOKENS = 4096
DEFAULT_TEMPERATURE = 1.0