---
title: "PUT /inference-pipelines/{inferencePipelineId}/rows"
method: PUT
path: "/inference-pipelines/{inferencePipelineId}/rows"
tags: ["Monitoring"]
---

# PUT /inference-pipelines/{inferencePipelineId}/rows

`PUT /inference-pipelines/{inferencePipelineId}/rows`

Update an inference data point in an inference pipeline.

## Path parameters

- `inferencePipelineId` string, uuid, required

## Query parameters

- `inferenceId` string, required

## Request body

- object
  - `row` object, required
  - `config` DatastreamConfigUpdate
    - `inferenceIdColumnName` string, nullable — Name of the column with the inference ids. This is useful if you want to update rows at a later point in time. If not provided, a unique id is generated by Openlayer.
    - `latencyColumnName` string, nullable — Name of the column with the latencies.
    - `timestampColumnName` string, nullable — Name of the column with the timestamps. Timestamps must be in UNIX sec format. If not provided, the upload timestamp is used.
    - `groundTruthColumnName` string, nullable — Name of the column with the ground truths.
    - `humanFeedbackColumnName` string, nullable — Name of the column with human feedback.

## Response `200`

Status OK.

- object
  - `success` true, required

## Other responses

- `default` — Unexpected error.

---

[API](https://skmtc.net/openlayer/apis/openlayer-api.md) · [All operations](https://skmtc.net/openlayer/apis/openlayer-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/openlayer/openlayer-api/versions/d0e74f00c900/schema)