SEC Filing Section Chunker
Pricing
$5.00 / 1,000 document with useful outputs
SEC Filing Section Chunker
Deterministically extract requested 10-K Items 1, 1A, 7, and 7A into citation-ready JSON chunks.
Pricing
$5.00 / 1,000 document with useful outputs
Rating
0.0
(0)
Developer
Dakota Myers
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
4 days ago
Last modified
Categories
Share
Give me raw 10-K plain text, or a public HTTP(S) URL that returns plain text, and I reliably return deterministic citation-ready chunks from requested Items 1, 1A, 7, and 7A only. Each dataset record preserves source identity, document and chunk hashes, section identity, offsets, and order. A failed input yields a failed documentOutcomes entry without removing successful records.
Submit one or more filings through the items array. rawText takes precedence over sourceUrl or fileUrl. requestedItems, chunkSize, and overlap are deterministic parameters that materially affect output.
Example input: {"items":[{"sourceName":"acme-10k","rawText":"ITEM 1. BUSINESS...","requestedItems":["1","1A"],"chunkSize":1500,"overlap":150}]}.
Output and repeatability
The default dataset contains section-aware chunks with stable documentId, chunkId, SHA-256 hashes, section identity, offsets, chunk order, and the chunking parameters used to produce them. Identical input text and semantic parameters produce the same useful records and stable IDs.
The default key-value store record SUMMARY contains aggregate run status, submitted-document count, total chunk count, per-document outcomes, and a UTC processedAt timestamp. processedAt is volatile metadata and does not participate in stable chunk identity.
Limitations: acceptance covers realistic plain-text 10-K structure and adversarial table-of-contents headings. HTML must be converted to plain text before submission. The Actor does not claim EDGAR retrieval, XBRL parsing, filing-type verification, HTML layout reconstruction, or support outside the four listed Items.
Billing and limits
One document-converted event is charged only after a document produces supported output saved to the dataset. Empty or failed documents are not charged. Platform costs are included; no start or automatic dataset-item charge. Up to 25 documents, 2 MB UTF-8 text per document, and a 120-second run timeout. The Actor stops at the spending limit. Public text downloads must be accessible without credentials.
