Initial local translation API with persistent projects and batch jobs

local_translator/config.py

@@ -0,0 +1,54 @@
+from pathlib import Path
+import tomllib
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+
+
+class ProviderConfig(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+    base_url: str = "http://127.0.0.1:1234/v1"
+    model: str = ""
+    api_key_env: str = "LM_STUDIO_API_KEY"
+    timeout: float = Field(default=180, gt=0, le=3600)
+    temperature: float = Field(default=0.2, ge=0, le=2)
+    max_tokens: int = Field(default=4096, ge=1, le=131072)
+    prompt_style: Literal["generic", "hy_mt"] = "generic"
+    top_p: float | None = Field(default=None, gt=0, le=1)
+    top_k: int | None = Field(default=None, ge=0)
+    repetition_penalty: float | None = Field(default=None, gt=0, le=3)
+    autostart: bool = False
+    startup_timeout: float = Field(default=90, gt=0, le=600)
+    load_model: str = ""
+    load_context_length: int = Field(default=8192, ge=512, le=262144)
+
+    @field_validator("base_url")
+    @classmethod
+    def validate_url(cls, value: str) -> str:
+        from urllib.parse import urlsplit
+        url = urlsplit(value)
+        if url.scheme not in {"http", "https"} or not url.hostname or url.username or url.password or url.query or url.fragment:
+            raise ValueError("Expected an HTTP(S) base URL without credentials, query or fragment")
+        return value.rstrip("/")
+
+
+class Settings(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+    database: str = "data/translations.sqlite3"
+    port: int = Field(default=8787, ge=1, le=65535)
+    providers: dict[str, ProviderConfig] = Field(default_factory=lambda: {
+        "lmstudio": ProviderConfig(prompt_style="hy_mt", temperature=0.7, top_p=0.6, top_k=20, repetition_penalty=1.05)
+    })
+
+
+def load_settings(path: str = "config.toml") -> Settings:
+    config_path = Path(path).resolve()
+    if config_path.exists():
+        with config_path.open("rb") as stream:
+            settings = Settings.model_validate(tomllib.load(stream))
+    else:
+        settings = Settings()
+    db = Path(settings.database)
+    if not db.is_absolute():
+        settings.database = str(config_path.parent / db)
+    return settings