Extract and store document/chunk structure and relationships

[jacopo-chevallard]

Currently, document chunks are stored individually into our vector database (PGVector), i.e. the only relationship we record is the one between a chunk and its original document.

We should expand this to extract the document layout (headers, footers, table, image, caption, …) and the relationships (chunk --> page --> file, previous_chunk --> chunk --> next_chunk, …) and store them into a database, see our scheme.

[linear]

CORE-278 Extract and save document/chunk structure and relationships