domains / families / software-engineering / nemo-fabric-integrate

nemo-fabric-integrate

separate

Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating the consumer's own application, job, or deployment config into an in-memory FabricConfig, choosing the single-invocation convenience API or an explicitly started runtime, validating with plan and doctor, and consuming normalized results, artifacts, and telemetry.

When to use

• Integrating NeMo Fabric into consumer applications
• Translating consumer config into FabricConfig
• Choosing single-invocation or started runtime APIs
• Validating with plan and doctor
• Consuming normalized results, artifacts, and telemetry
• Managing adapter selection and runtime lifecycle

When not to use

• Importing _native or adapter-internal modules
• Reimplementing start, invoke, or stop logic
• Managing adapter threads, sessions, or processes directly
• Parsing or reusing runtime_id, invocation_id, or request_id
• Installing harnesses or credentials at run time

Skill page

Source