jrmccluskey commented on code in PR #35066:
URL: https://github.com/apache/beam/pull/35066#discussion_r2123922103
##########
examples/notebooks/beam-ml/custom_remote_inference.ipynb:
##########
@@ -257,29 +255,35 @@
"\n",
"When you run remote inference, prepare to encounter, identify, and
handle failure as gracefully as possible. We recommend using the following
techniques:\n",
"\n",
- "* **Exponential backoff:** Retry failed remote calls with
exponentially growing pauses between retries. Using exponential backoff ensures
that failures don't lead to an overwhelming number of retries in quick
succession.\n",
+ "* **Exponential backoff:** Retry failed remote calls with
exponentially growing pauses between retries. Using exponential backoff ensures
that failures don't lead to an overwhelming number of retries in quick
succession. The `RemoteModelHandler` base class handles this logic, with the
`retry_fn` argument determining which errors are retryable. For this example we
will always retry. \n",
"\n",
"* **Dead-letter queues:** Route failed inferences to a separate
`PCollection` without failing the whole transform. Continue execution without
failing the job (batch jobs' default behavior) or retrying indefinitely
(streaming jobs' default behavior).\n",
Review Comment:
Did a quick and dirty "just print the failures separately" step, super
simple. Also linked to documentation
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
