feat(talkbot): make translation output limit configurable

containers/talkbot/server.py

@@ -27,6 +27,7 @@ WHISPER_URL = os.environ.get("WHISPER_URL", "http://whisper:8080").rstrip("/")
 LLAMACPP_URL = os.environ.get("LLAMACPP_URL", "http://llamacpp:7000").rstrip("/")
 LLAMACPP_MODEL = os.environ.get("LLAMACPP_MODEL", "").strip()
 LLAMACPP_TIMEOUT = int(os.environ.get("LLAMACPP_TIMEOUT") or "600")
+LLAMACPP_MAX_TOKENS = int(os.environ.get("LLAMACPP_MAX_TOKENS") or "8192")
 LLAMACPP_ENABLE_THINKING = (
     os.environ.get("LLAMACPP_ENABLE_THINKING", "false").lower()
     in {"1", "true", "yes", "on"}
@@ -643,6 +644,7 @@ def translate(
             },
         ],
         "temperature": 0.1,
+        "max_tokens": LLAMACPP_MAX_TOKENS,
         "chat_template_kwargs": {
             "enable_thinking": LLAMACPP_ENABLE_THINKING,
         },

containers/talkbot/talkbot.container

@@ -35,6 +35,7 @@ Environment=NC_PASSWORD=changeme
 Environment=WHISPER_URL=http://whisper:8080
 Environment=LLAMACPP_URL=http://llamacpp:8090
 #Environment=LLAMACPP_MODEL=
+Environment=LLAMACPP_MAX_TOKENS=8192
 Environment=LLAMACPP_ENABLE_THINKING=false
 Environment=QWEN_TTS_URL=http://qwen-tts:8000