Skip to content

Commit 80d7079

Browse files
Merge pull request #238287 from santiagxf/santiagxf/batch-patch-inputs
Santiagxf/batch patch inputs
2 parents 35844f8 + 28090d1 commit 80d7079

File tree

2 files changed

+2
-0
lines changed

2 files changed

+2
-0
lines changed

articles/machine-learning/how-to-access-data-batch-endpoints-jobs.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,8 @@ Batch endpoints can be used to perform long batch operations over large amounts
2727

2828
Batch endpoints provide a durable API that consumers can use to create batch jobs. The same interface can be used to indicate the inputs and the outputs your deployment expects. Use inputs to pass any information your endpoint needs to perform the job.
2929

30+
:::image type="content" source="./media/concept-endpoints/batch-endpoint-inputs-outputs.png" alt-text="Diagram showing how inputs and outputs are used in batch endpoints.":::
31+
3032
The number and type of inputs and outputs depend on the [type of batch deployment](concept-endpoints-batch.md#batch-deployments). Model deployments always require 1 data input and produce 1 data output. However, pipeline component deployments provide a more general construct to build endpoints. You can indicate any number of inputs and outputs.
3133

3234
The following table summarizes it:
97.8 KB
Loading

0 commit comments

Comments
 (0)