jerryjliu/docjev
A very fast document classifier/splitter using Jev
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Document classification and splitting with Jev, LiteParse, and optional LlamaParse. Give the Python library, CLI, or local app a PDF, DOCX, or PPTX and natural-language category rules. LiteParse extracts complete page text locally; Jev predicts the document category or the boundaries between its component documents. Optional LlamaParse tiers provide cloud OCR for difficult inputs. The real-document demo uses original IRS, Treasury, BEA, and SEC publications. Its 15-page packet contains two adjacent Treasury auction results with the same category. The splitter identifies them as separate documents and keeps a ten-page BEA release—including its dense statistical tables—together. This is an independent open-source implementation. It does not call LlamaIndex's hosted Classify or Split APIs or use their implementation. LlamaParse is used only for optional OCR. Jev is a hosted service; local OCR does not make inference offline. [](https://jerryjliu.github.io/docjev/) Explore the visual report — browse all 40 documents, compare packet boundaries, replay recorded median…
Read the full README ↗ · Preview checked 2026-09-23T12:37:25.228Z
Inside the original README — Document outline
- DocJev
- Quick start
- Local visual app and videos
- Rules and results
- Python API
- OCR options
- Small real-document accuracy benchmark
- Earlier real-document timing pilot
- Sources and evaluation data
- Development and limitations
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
- ![DocJev visual benchmark report: 40 real PDFs, eight packets, Jev and Luna accuracy and decision la
- Explore the visual report
- TypeSafe API key
- DocJev
- .env.example
- compatibility and page contracts
- Classification
- Splitting
- Thumbnails, captions, exact timings, and run evidence
- Publication inbox
- 15-page packet
- actual split PDFs and result JSON
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
A very fast document classifier/splitter using Jev
Repository facts
- Owner
- jerryjliu
- Primary language
- Python
- Stars
- 352
- Forks
- 25
- Open issues + pull requests
- 1
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-19T17:17:03.000Z
- Last push
- 2026-09-21T22:40:31.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-23T12:03:29.066Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer