feat(stt): support multi-model STT with parallel execution and consensus NLU extraction

This commit is contained in:
2026-09-29 02:10:03 +03:30
parent da68fc683f
commit 0a7db5ebe9
4 changed files with 171 additions and 31 deletions
+67 -3
View File
@@ -37,9 +37,30 @@ class Settings(BaseSettings):
LLM_MODEL: str = "gpt-4o-mini"
LLM_TIMEOUT_SECONDS: float = 60.0
# STT provider — any OpenAI-compatible /audio/transcriptions endpoint.
# Falls back to the LLM provider when unset. Note: some providers
# (e.g. DeepSeek) have no audio API — voice stays disabled gracefully.
# STT providers — support multiple models/APIs in parallel.
# 1. JSON list: [{"name": "m1", "base_url": "...", "api_key": "...", "model": "..."}, ...]
STT_PROVIDERS_JSON: str = ""
# 2. Individual provider variables (up to 3 distinct STT models)
STT_PROVIDER_1_NAME: str = "model-1"
STT_PROVIDER_1_BASE_URL: str = ""
STT_PROVIDER_1_API_KEY: str = ""
STT_PROVIDER_1_MODEL: str = ""
STT_PROVIDER_1_LANGUAGE: str = "fa"
STT_PROVIDER_2_NAME: str = "model-2"
STT_PROVIDER_2_BASE_URL: str = ""
STT_PROVIDER_2_API_KEY: str = ""
STT_PROVIDER_2_MODEL: str = ""
STT_PROVIDER_2_LANGUAGE: str = "fa"
STT_PROVIDER_3_NAME: str = "model-3"
STT_PROVIDER_3_BASE_URL: str = ""
STT_PROVIDER_3_API_KEY: str = ""
STT_PROVIDER_3_MODEL: str = ""
STT_PROVIDER_3_LANGUAGE: str = "fa"
# Legacy single STT provider fallback:
STT_BASE_URL: str = ""
STT_API_KEY: str = ""
STT_MODEL: str = "whisper-1"
@@ -53,6 +74,49 @@ class Settings(BaseSettings):
def stt_api_key(self) -> str:
return self.STT_API_KEY or self.AI_API_KEY
@property
def stt_providers(self) -> list[dict]:
import json
if self.STT_PROVIDERS_JSON:
try:
data = json.loads(self.STT_PROVIDERS_JSON)
if isinstance(data, list) and len(data) > 0:
return data
except Exception:
pass
# Check explicit STT_PROVIDER_1 / 2 / 3
custom_list: list[dict] = []
for idx in (1, 2, 3):
b_url = getattr(self, f"STT_PROVIDER_{idx}_BASE_URL")
key = getattr(self, f"STT_PROVIDER_{idx}_API_KEY")
model = getattr(self, f"STT_PROVIDER_{idx}_MODEL")
name = getattr(self, f"STT_PROVIDER_{idx}_NAME")
lang = getattr(self, f"STT_PROVIDER_{idx}_LANGUAGE") or "fa"
if b_url and key:
custom_list.append({
"name": name or f"model-{idx}",
"base_url": b_url,
"api_key": key,
"model": model or self.STT_MODEL,
"language": lang,
"timeout": 30.0,
})
if custom_list:
return custom_list
# Fallback to single legacy STT provider if set
if self.stt_base_url and self.stt_api_key:
return [{
"name": "default",
"base_url": self.stt_base_url,
"api_key": self.stt_api_key,
"model": self.STT_MODEL,
"language": self.STT_LANGUAGE,
"timeout": 30.0,
}]
return []
# PostgreSQL — same instance/database as the api service.
DATABASE_URL: str = "postgresql+asyncpg://postgres:postgres@localhost:5432/procurement"