Skip to main content
Model configuration loader. Reads model definition YAML files from the configs/ directory and builds ModelSpec instances. This is the single source of truth for all model specifications.

​
EndpointPaths

@dataclass(frozen=True)
class EndpointPaths()
Parsed endpoint routes for a model. Each field corresponds to an optional endpoint type declared in the model’s YAML config under endpoints:.

​
ModelConfig

@dataclass(frozen=True)
class ModelConfig()
A fully parsed model configuration. Combines the ModelSpec with routing metadata that is not part of the spec itself.

​
endpoint_path

@property
def endpoint_path() -> str
Primary endpoint path (backward compatibility).

​
genes_endpoint_path

@property
def genes_endpoint_path() -> str | None
Genes/metadata endpoint path (backward compatibility).

​
load_model_config

def load_model_config(path: Path) -> ModelConfig
Loads a single model config YAML file.
​
path
Path
required
Path to the YAML file.
​
returns
ModelConfig
A ModelConfig with the parsed spec and routing.

​
load_all_model_configs

def load_all_model_configs(
        configs_dir: Path | None = None) -> Dict[str, ModelConfig]
Discovers and loads all model configs from a directory. Scans for *.yaml files and returns a dict keyed by model_name.
​
configs_dir
Path | None
Directory to scan. Defaults to the package-bundled configs/ directory.
​
returns
Dict[str, ModelConfig]
Mapping of model name to ModelConfig.