The proposed functional data service framework provides a way of making heterogeneous data sources more accessible to applications and manageable to developers by integrating a service-oriented architecture, a functional data model, the semantic web, and other related technologies. With the supports of the proposed mechanism, different data sources with their supporting programming technologies are annotated with semantics to facilitate data advertisement and discovery. The data and their relationships in the proposed framework are modelled as a number of functions to form functional data models and these models are realised as web services, so the interfaces for accessing these data can be published. Semantic web services and ontologies are used to describe the characteristics and facets of data sources. This paper describes the structure of the proposed framework and its advantages in integrating heterogeneous data sources. The paper includes an example to illustrate the main characteristics of the proposed framework.