The NeumDocument 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 document. 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.
  • content (str): This value contains the content to be embdded. It can be a chunk / excerpt of the original text or can be a calculated value like a summary or entity extraction.
  • metadata (dict): This value contains the attached metadata for a given document. This can include values extracted from the data source or loader, as well as any calculated values.


from neumai.Shared.NeumDocument import NeumDocument
neum_document = NeumDocument(
    id = 'abc', 
    content = 'Hello',
    metadata = {'createdDate':'2023-01-01'}