Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat/Option to flatten metadata extraction #2432

Open
ron-unstructured opened this issue Jan 19, 2024 · 0 comments
Open

feat/Option to flatten metadata extraction #2432

ron-unstructured opened this issue Jan 19, 2024 · 0 comments
Labels
enhancement New feature or request

Comments

@ron-unstructured
Copy link
Contributor

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.

@ron-unstructured ron-unstructured added the enhancement New feature or request label Jan 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant