In this session, we present our experimental approach to creating DPK pipelines using agentic workflows. We will begin with a brief introduction to agentic workflows, followed by a walkthrough of two notebooks developed to support this work:

The first notebook shows a planner agent for Data-Prep-Kit tasks with code generation. The agent builds DPK pipeline that performs required tasks defined by a natural language.

The second notebook demonstrates how DPK transformers can be wrapped as tools within LangChain and LlamaIndex, along with examples of executing the transforms directly.

In this session, we present our experimental approach to creating DPK pipelines using agentic workflows. We will begin with a brief introduction to agentic workflows, followed by a walkthrough of two notebooks developed to support this work: The first notebook shows a planner agent for Data-Prep-Kit tasks with code generation. The agent builds DPK pipeline that performs required tasks defined by a natural language. The second notebook demonstrates how DPK transformers can be wrapped as tools within LangChain and LlamaIndex, along with examples of executing the transforms directly.

Overview: In this session, we present our experimental approach to creating DPK pipelines using agentic workflows. We will begin with a brief introduction to agentic workflows, followed by a walkthrough of two notebooks developed to support this work: the first notebook shows a planner agent for Data-Prep-Kit tasks with code generation, building DPK pipelines from natural language tasks; the second notebook demonstrates wrapping DPK transformers as tools within LangChain and LlamaIndex, with examples of executing the transforms directly.