In this paper we describe preparatory work for constructing a Treebank for Latvian as no such resource currently exists. Previously elaborated SemTi-Kamols hybrid dependency based grammar model has been extended to make it appropriate for broad coverage text annotation. We also have integrated extended SemTi-Kamols model with graphical tree editor TrEd and complementary toolkit, which originally was developed for Prague Dependency Treebank. Using the obtained environment we have annotated small amount of Latvian text.