> ## Documentation Index > Fetch the complete documentation index at: https://docs.eigenpal.com/llms.txt > Use this file to discover all available pages before exploring further. # Split Document > Split a parsed document into named sections using an LLM. Consumes ai.parse output; emits per-section page ranges and text ready for downstream ai.extract via control.parallel_map. `ai.split`, Split a parsed document into named sections using an LLM. Consumes ai.parse output; emits per-section page ranges and text ready for downstream ai.extract via control.parallel\_map. ## Configuration Configuration goes inside the step's `with:` block. Template expression resolving to ai.parse output, e.g. "\{\{ steps.parse.output }}" Named sections to find in the document Stable id, used as the key in output and template references What this section looks like in the document. Use the document's own terminology (e.g. "Príloha 2 / Anlage 2") and visual cues. Multilingual variants belong here. If true, log a warn when this section is not found, and lean the LLM toward expecting it. Default: false (sections may be absent). Natural-language hints fed to the LLM about what marks the END of this section (e.g. \["PRÍPAD PORUŠENIA ZMLUVY", "*Koniec prílohy*"]). The LLM uses these as guidance, not a regex match, so casing variants, missing diacritics, and multilingual phrasings all close the section correctly. Optional natural-language rules appended to the system prompt. E.g. "End-of-section markers like *Koniec prílohy 2* close the current section." Provider ID from eigenpal.config.yaml (e.g. "openai-gpt5.4-mini"). Falls back to the tenant default LLM provider when omitted. Override the per-window token ceiling for this step. Defaults to env SPLIT\_WINDOW\_TOKEN\_BUDGET or 20000. Smaller windows give sharper anchors on contract-style documents (less competing context for the LLM to mis-anchor on); bump to 50k–100k when sections routinely exceed per-window page count. ## Output Sections found in the document, in page order. Absent sections are omitted. Section name from the config \[startIndex, endIndex] inclusive, 0-based page indices LLM confidence at the anchor page. Coarse enum (low | medium | high), numeric scores cluster meaninglessly at 0.85-0.95. LLM's justification for the anchor, useful for debugging Structured start-anchor evidence, parse this instead of regexing over `notes`. Verbatim heading text the LLM cited as the section start Page where start\_heading\_text appears Set when the LLM detected an end-of-section cue (matched against the section's `endHints` or an explicit closing marker). Absent when the section was closed by continuity-fill alone. LAST page of the section (inclusive) LLM's justification for the end. Pair with start `notes` for reconciliation. Joined per-page content for this section, ready for downstream ai.extract Raw per-page records covered by this split (in page order). Iterate when downstream needs per-page context (e.g. control.parallel\_map over section pages). Whether this page is direct LLM evidence (anchored) or continuity-filled (inferred) Pages with direct LLM evidence Pages assigned by deterministic continuity fill The same sections keyed by config name, so a downstream step can reference one directly: `{{ steps.<split>.output.sections.<name>.page_range }}`. Prefer this over filtering `splits`. On a duplicate name the last wins.