Welcome to the Getting Started guide, This is what you will achieve by following the next steps:
Saga version 1.2.0 will be released soon. You'll be able to get it from here (Saga team in MS Teams).
It is a bundle containing:
In addition to Saga binaries you can also find:
Note |
---|
Creators and users of Saga are subscribed to this Saga team, so you can always publish a message to get some help if you have questions or comments. |
$> java -version
{SAGA_HOME}
.{SAGA_HOME}
in something like {SAGA_HOME}/Elasticsearch-7.5.1
. {SAGA_HOME}/Elasticsearch-7.510.1/bin
.Tip |
---|
If Saga executes with an empty ElasticSearch, it will generate all the necessary indexes with the minimum default data (base pipeline, executors,...); although you need to add new tags and resources. |
Once you have Saga in {SAGA_HOME}
validate the following:
There is a {SAGA_HOME}/lib
folder containing the following JARs:
saga-classification-trainer-stage-1.2.02
saga-faq-stage-1.2.02.jar
saga-googlelang-entitydetector-trainer-stage-1.2.02.jar
saga-google-knowledgename-trainer-stage-1.2.02.jar
saga-parts-langof-detectorspeech-stage-1.2.02.jar
saga-namesentence-trainerbreaker-stage-1.2.02.jar
saga-sentence-breakerspellchecking-stage-1.2.02.jar
Check the basic configuration on {SAGA_HOME}/config/config.json
:
"hostnamesAndPorts": ["elastic1:9200", "elastic2:9200", "elastic3:9200"],
If you have some valid "models" you'd like to include them on the server:
{SAGA-HOME}/nt-models
folder for "name trainers" and copy the model there.{SAGA-HOME}/ct-models
folder for "classification trainers" and copy the model there.{SAGA-HOME}/tf-models
folder for "FAQ" (uses TensorFlow) and copy the model there.To add datasets:
{SAGA-HOME}/datasets
folder.To run Saga:
Check that ElasticSearch is running.
Use the bundled startup script on {SAGA_HOME}/bin (either startup.bat
for Windows or startup.sh
for Linux).
If you didn't change the default port on the configuration, you should be able to access Saga UI at http://localhost:8080/.
If not, then check your configuration for the right port.
Saga has a python recognizer and python stage that can be used to process text using machine learning python models like Bert.
In case you need this, follow instruction on how to setup and run the python bridge here.