5ee47827f3
Spoken (TTS) replies are 1-2 sentences, so an unbounded num_predict only exposes the worst case where the chat model rambles or loops. Add an ollama_num_predict config (default 512, 0 disables) wired into the reply loop's chat call on both the native- and text-tool paths. The 512-token headroom stays well above this app's short tool-call JSON, so capping never truncates a tool call. This keeps the user's quality model instead of downgrading it. Configurable in the container via OLLAMA_NUM_PREDICT. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
21 lines
693 B
JSON
21 lines
693 B
JSON
{
|
|
"db_path": "${JARVIS_DB_PATH}",
|
|
"sqlite_vss_path": null,
|
|
"ollama_base_url": "${OLLAMA_BASE_URL}",
|
|
"ollama_embed_model": "${OLLAMA_EMBED_MODEL}",
|
|
"ollama_chat_model": "${OLLAMA_CHAT_MODEL}",
|
|
"ollama_num_predict": "${OLLAMA_NUM_PREDICT}",
|
|
"intent_judge_model": "${OLLAMA_INTENT_MODEL}",
|
|
"tts_enabled": true,
|
|
"tts_engine": "${TTS_ENGINE}",
|
|
"tts_piper_model_path": "${TTS_PIPER_MODEL_PATH}",
|
|
"whisper_model": "${WHISPER_MODEL}",
|
|
"whisper_backend": "faster-whisper",
|
|
"whisper_device": "${WHISPER_DEVICE}",
|
|
"whisper_compute_type": "${WHISPER_COMPUTE_TYPE}",
|
|
"location_enabled": true,
|
|
"web_search_enabled": true,
|
|
"wikipedia_fallback_enabled": true,
|
|
"mcps": {}
|
|
}
|