Skip to content

feat/Option to flatten metadata extraction #2432

Open
@ron-unstructured

Description

@ron-unstructured

Is your feature request related to a problem? Please describe.
When using mode=elements, the metadata is structured as a nested dictionary, such as {metadata: {coordinates: {nested dict}}}. This nested structure poses a compatibility problem with vector stores like Pinecone, which require metadata in primitive types.

Describe the solution you'd like
The ideal solution is to introduce a flat metadata structure option in Unstructured. This feature would allow users to select the desired metadata format, either nested or flat, at the creation time. Such an enhancement would improve the tool's compatibility with various data storage and retrieval systems, particularly those requiring primitive metadata.

Describe alternatives you've considered
An alternative approach could be the development of a separate utility to convert nested metadata into a flat format.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions