Whats the best way to use a pydantic object for in tree summarize?

is it possible to use: https://llamahub.ai/l/tools/llama-index-tools-duckduckgo?from= in a query pipeline?

Hi all, in this page: https://docs.llamaindex.ai/en/stable/examples/agent/openai_agent_query_plan/ where is the query plan actually applied?

What is the best way to group a list of nodes by similarity, creating a new parent node with a summary of all matched nodes and the original ones as child nodes