Skip to content

jarvis_direct

jarvis_direct

Jarvis Direct backend — engine-level inference for local and cloud models.

Classes

JarvisDirectBackend 

JarvisDirectBackend(engine_key: Optional[str] = None, telemetry: bool = False, gpu_metrics: bool = False)

Bases: InferenceBackend

Direct engine inference via SystemBuilder.

Works for both local models (Ollama, vLLM, etc.) and cloud models (OpenAI, Anthropic, Google) via the CloudEngine.

Source code in src/openjarvis/evals/backends/jarvis_direct.py 
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
def __init__(
    self,
    engine_key: Optional[str] = None,
    telemetry: bool = False,
    gpu_metrics: bool = False,
) -> None:
    from openjarvis.system import SystemBuilder

    self._telemetry = telemetry
    self._gpu_metrics = gpu_metrics

    builder = SystemBuilder()
    if engine_key:
        builder.engine(engine_key)
    self._system = builder.telemetry(telemetry).traces(telemetry).build()