Partition Document To Elements

Agent POSTs a contract PDF to /general/v0/general and receives a JSON array of elements. Downstream code only reads element.text and discards element.type.

Preserve each element's `type` (Title, NarrativeText, ListItem, Table, Image, Header, Footer, PageBreak, Address) alongside text. Downstream RAG/indexing must branch on type — e.g. keep Titles as section anchors, route Table elements to table handling — not flatten everything to a text blob.

An .eml email with sender, subject, quoted reply chain, and an attachment is partitioned. Agent indexes the whole thing as one NarrativeText.

Partition separates email metadata (sender/recipient/subject via element metadata) from body elements and quoted-reply blocks. Preserve the body element types and keep subject/sender available in metadata for downstream filtering, rather than collapsing the message into a single blob.

A multi-section report is partitioned. The agent re-sorts elements alphabetically by text before chunking 'to dedupe.'

Preserve the reading-order sequence returned by partition — element order encodes document flow (Title precedes its NarrativeText, list items follow their lead-in). Do not re-sort; ordering is load-bearing for by_title chunking and parent_id hierarchy.