After you have started to ingest streaming data into a deployed application you can view a stream's output.
Read stream outputs
After you have successfully created an application that saves results into a stream you can read a data source input stream or a model output stream.
Vertex AI Vision SDK
To send a request to read a model output stream you must install the Vertex AI Vision SDK .
Make the following variable substitutions:
- PROJECT_ID : Your Google Cloud project ID.
- LOCATION_ID
: Your location ID. For example,
us-central1. Supported regions . More information . - STREAM_ID
: The stream ID that you created in the cluster
For example,
application-output-1234abcd.
Print stream content:
#
This
will
print
packets
from
a
stream
to
stdout
.
#
This
will
work
for
*
any
*
stream
,
independent
of
the
data
type
.
vaictl
-
p
PROJECT_ID
\
-
l
LOCATION_ID
\
-
c
application
-
cluster
-
0
\
--
service
-
endpoint
visionai
.
googleapis
.
com
\ receive
streams
packets
STREAM_ID
Save video from a stream
Use the following command to save video stream output. This command reads the data from an ongoing live stream, and saves the video segments in an MP4 file format to the user specified output directory:
Vertex AI Vision SDK
To send a request to save video output from a stream you must install the Vertex AI Vision SDK .
Make the following variable substitutions:
- PROJECT_ID : Your Google Cloud project ID.
- LOCATION_ID
: Your location ID. For example,
us-central1. Supported regions . More information . - STREAM_ID
: The stream ID that you created in the cluster
For example,
application-output-1234abcd. - OUTPUT_PATH
: The output video path. The default value is
/tmp/.
vaictl -p PROJECT_ID
\
-l LOCATION_ID
\
-c application-cluster-0 \
--service-endpoint visionai.googleapis.com \
receive streams video-file STREAM_ID
--output OUTPUT_PATH
