AI infrastructure

Inference belongs in the event path.

AI enrichment should not require a sidecar, a model-serving hop, and custom audit glue for every record. StreamKernel keeps ONNX inference, model labels, provenance, and delivery inside the pipeline boundary.

In-process enrichment

DJL + ONNX, MLflow governance, provenance, and destination delivery in one runtime.

The commercial differentiator is the AI path: model-aware operational movement without splitting every record across separate services and audit systems.

Inline ONNX inference before delivery.
MLflow registry support for promotion and rollback.
Model/version provenance on enriched output.
Kafka, MongoDB Vector, Postgres, Postgres Vector, Delta Lake, Snowflake, and custom sink paths.

In-process AI enrichment path

AI use cases

Operational enrichment paths the website should make easy to understand.

Kafka -> ONNX -> Kafka

Enrich events inline and republish without a sidecar model-serving hop.

Kafka -> ONNX -> MongoDB Vector

Generate embeddings and insert vector records from the same pipeline boundary.

Kafka -> ONNX -> Postgres Vector

Score or embed records in-process and write vector-ready rows to Postgres Vector targets.

Any source -> ONNX -> Postgres

Deliver scored records from Kafka, Pulsar, REST, or custom sources into a relational store.

Pulsar -> ONNX -> Delta Lake

Run transport-agnostic AI enrichment into a lakehouse destination.

MLflow -> Delta Lake

Bootstrap model artifacts from the registry and write enriched records.

Live model swap

Promote and roll back models without restarting the pipeline.

Vertical inference

The inference types buyers recognize before they care about the pipeline.

The same in-process ONNX path can serve fraud scoring, clinical classification, sensor anomaly detection, and embedding generation without sending records through an external model hop.

Fraud scoring

Transaction events can receive model scores before they leave controlled financial systems.

Clinical classification

HL7/FHIR and telemetry streams can be classified without sending PHI to an external endpoint.

Sensor anomaly detection

Defense and industrial sensor streams can be scored at the edge in disconnected deployments.

Embedding generation

Operational records can be converted into vector-search-ready output for MongoDB Vector or Postgres Vector.

AI proof strip

Evidence for the AI path starts with published local baselines.

The PRD calls for clear caveats, exact profiles, and reproducible evidence rather than a universal performance promise.

Kafka Bench NOOP

956K ops/sec Published local producer ceiling

Kafka ALO WireEvent

525K ops/sec 512-byte payload, at-least-once

mTLS + OPA

366K ops/sec TLSv1.3 + fail-closed policy

MongoDB Insert

163K docs/sec 95.5M document baseline

ONNX -> MongoDB Vector

337 eps 336.8 eps final run, zero record loss

Commercial path

Review the AI enrichment path against your models and destinations.

Bring the event source, model governance requirements, destination path, and audit expectations.

Request Commercial Demo Discuss OEM Licensing