The NeumVector is the object used to organize data extracted for a given data source. It is analogous to similar constructs (i.e. Document) used in frameworks like Langchain and LlamaIndex.

The goal of this interface is to abstract three properties:

  • id (str): This is a unique identifier for a given vector. The id is constructed throughout the pre-processing of the data and used as the vector id within the vector database. It is used at synchronization to ensure vectors are not being re-computed and duplicated.
  • score (float): This score is represents the similarity score calculated between the query and the retrieved value.
  • metadata (dict): This value contains the attached metadata for a retrieved vector. This can include values extracted from the data source or loader, as well as any calculated values. Metadata includes the content from the NeumDocument.


from neumai.Shared.NeumSearchResult import NeumSearchResult
neum_search_result = NeumSearchResult(
    id = "abc", 
    score = 0.8421,
    metadata = {'text':'Hello', 'createdDate':'2023-01-01'}