ydy0615/llm-in-text
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: sync full-stack Docker runtime and UI

Browse Source
This commit is contained in:
“ydy0615”
2026-06-27 22:22:42 +08:00
parent 356108e792
commit 23bfca51e4
50 changed files with 2750 additions and 2120 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/risk_config.py
+18 -4
View File
@@ -75,18 +75,25 @@ class RiskConfig:
pro_max_output_tokens: int
pro_temperature: float
web_search_model: str
speech_tts_model: str
speech_asr_model: str
web_search_max_input_chars: int
web_search_max_output_tokens: int
web_search_temperature: float
compress_max_input_chars: int
compress_max_output_tokens: int
ocr_max_input_bytes: int
speech_tts_max_input_chars: int
speech_asr_max_input_bytes: int
completion_input_cost_per_1k: float
completion_output_cost_per_1k: float
pro_input_cost_per_1k: float
pro_output_cost_per_1k: float
vision_input_cost_per_1k: float
vision_output_cost_per_1k: float
speech_tts_input_cost_per_1k_chars: float
speech_tts_output_cost_per_minute_audio: float
speech_asr_input_cost_per_mb: float
def load_risk_config() -> RiskConfig:
@@ -123,26 +130,33 @@ def load_risk_config() -> RiskConfig:
model_circuit_breaker_failures=_int_env("RISK_MODEL_CIRCUIT_FAILURES", 8),
model_circuit_ttl_seconds=_int_env("RISK_MODEL_CIRCUIT_TTL_SECONDS", 300),
enforce_redis_fail_closed=_bool_env("RISK_ENFORCE_REDIS_FAIL_CLOSED", False),
completion_model=_str_env("RISK_COMPLETION_MODEL", os.getenv("LLM_MODEL", "gpt-4.1-mini")),
pro_model=_str_env("RISK_PRO_MODEL", os.getenv("PRO_LLM_MODEL", os.getenv("LLM_MODEL", "gpt-4.1"))),
vision_model=_str_env("RISK_VISION_MODEL", os.getenv("VLM_MODEL", "gpt-4.1-mini")),
completion_model=_str_env("RISK_COMPLETION_MODEL", os.getenv("LLM_MODEL", "Nex-N2-mini-mlx-OptiQ-8bit-MTP")),
pro_model=_str_env("RISK_PRO_MODEL", os.getenv("PRO_LLM_MODEL", os.getenv("LLM_MODEL", "Nex-N2-mini-mlx-OptiQ-8bit-MTP"))),
vision_model=_str_env("RISK_VISION_MODEL", os.getenv("VLM_MODEL", "Nex-N2-mini-mlx-OptiQ-8bit-MTP")),
completion_max_input_chars=_int_env("RISK_COMPLETION_MAX_INPUT_CHARS", 24000),
completion_max_output_tokens=_int_env("RISK_COMPLETION_MAX_OUTPUT_TOKENS", 768),
completion_temperature=_float_env("RISK_COMPLETION_TEMPERATURE", 0.4),
pro_max_input_chars=_int_env("RISK_PRO_MAX_INPUT_CHARS", 48000),
pro_max_output_tokens=_int_env("RISK_PRO_MAX_OUTPUT_TOKENS", 2048),
pro_temperature=_float_env("RISK_PRO_TEMPERATURE", 0.6),
web_search_model=_str_env("RISK_WEB_SEARCH_MODEL", os.getenv("LLM_MODEL", "gpt-4.1-mini")),
web_search_model=_str_env("RISK_WEB_SEARCH_MODEL", os.getenv("LLM_MODEL", "Nex-N2-mini-mlx-OptiQ-8bit-MTP")),
speech_tts_model=_str_env("RISK_SPEECH_TTS_MODEL", "Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit"),
speech_asr_model=_str_env("RISK_SPEECH_ASR_MODEL", "Qwen3-ASR-0.6B-8bit"),
web_search_max_input_chars=_int_env("RISK_WEB_SEARCH_MAX_INPUT_CHARS", 128000),
web_search_max_output_tokens=_int_env("RISK_WEB_SEARCH_MAX_OUTPUT_TOKENS", 4096),
web_search_temperature=_float_env("RISK_WEB_SEARCH_TEMPERATURE", 0.4),
compress_max_input_chars=_int_env("RISK_COMPRESS_MAX_INPUT_CHARS", 128000),
compress_max_output_tokens=_int_env("RISK_COMPRESS_MAX_OUTPUT_TOKENS", 1536),
ocr_max_input_bytes=_int_env("RISK_OCR_MAX_INPUT_BYTES", 100 * 1024 * 1024),
speech_tts_max_input_chars=_int_env("RISK_SPEECH_TTS_MAX_INPUT_CHARS", 4096),
speech_asr_max_input_bytes=_int_env("RISK_SPEECH_ASR_MAX_INPUT_BYTES", 100 * 1024 * 1024),
completion_input_cost_per_1k=_float_env("RISK_COMPLETION_INPUT_COST_PER_1K", 0.0004),
completion_output_cost_per_1k=_float_env("RISK_COMPLETION_OUTPUT_COST_PER_1K", 0.0016),
pro_input_cost_per_1k=_float_env("RISK_PRO_INPUT_COST_PER_1K", 0.003),
pro_output_cost_per_1k=_float_env("RISK_PRO_OUTPUT_COST_PER_1K", 0.012),
vision_input_cost_per_1k=_float_env("RISK_VISION_INPUT_COST_PER_1K", 0.0008),
vision_output_cost_per_1k=_float_env("RISK_VISION_OUTPUT_COST_PER_1K", 0.0024),
speech_tts_input_cost_per_1k_chars=_float_env("RISK_SPEECH_TTS_INPUT_COST_PER_1K_CHARS", 0.0),
speech_tts_output_cost_per_minute_audio=_float_env("RISK_SPEECH_TTS_OUTPUT_COST_PER_MINUTE_AUDIO", 0.0),
speech_asr_input_cost_per_mb=_float_env("RISK_SPEECH_ASR_INPUT_COST_PER_MB", 0.0),
)