Support word, powerpoint, excel, html, epub + math improvements

Support xlsx, docx, pptx, html, epub

Marker now has support for additional document formats. You have to run pip install marker-pdf[full] to install all the dependencies.

Improved text detection

OCR should now work better due to an improved text detection model.

Inline math improvements

• Better inline math detection with an improved model.
• Inline math lines are now inference.
• --redo-inline-math option to enable the highest quality math detection

Misc improvements

• Support for the claude model
• Improve benchmarking scripts
• Merge lines better with new text detection model

What's Changed

• Inline math by @VikParuchuri in #571
• Add Support for DOCX, PPTX, XLSX, HTML and Epub by @iammosespaulr in #501
• Fix character encoding issues when loading JSON configuration files by @vicenciomf2 in #574
• Dev by @VikParuchuri in #573

New Contributors

• @vicenciomf2 made their first contribution in #574

Full Changelog: v1.5.5...v1.6.0

Fix LLM layout relabeling bug

When text blocks were relabeled by the LLM in --use_llm mode, sometimes lines wouldn't merge into the blocks properly, resulting in missing text.

What's Changed

• Fix llm layout missing text by @VikParuchuri in #565

Full Changelog: v1.5.4...v1.5.5

Download models from r2; fix inline math

Download models from R2

• Models will now download from R2, which is fast and reliable

Inline math improvements

• Fix issues with inline math and escape characters

What's Changed

• Dev by @VikParuchuri in #564

Full Changelog: v1.5.3...v1.5.4

v1.5.3

Windows fixes

• Fix issue with streamlit app and permissions
• Fix torch classes issue

Memory leak fix

Fixed memory leak with repeatedly reusing the same converter.

Convert.py enhancements

• disable tqdm bars when converting multiple files

What's Changed

• Fix issue with reopening and deleting pdf file on Windows by @xiaoyao9184 in #463
• Fix SyntaxWarning: invalid escape sequence '\c' by using string r-prefix by @dantetemplar in #555
• Dev by @VikParuchuri in #560

New Contributors

• @xiaoyao9184 made their first contribution in #463
• @dantetemplar made their first contribution in #555

Full Changelog: v1.5.2...v1.5.3

Fix LLM service issue

Fix issue with initializing the LLM service with no default specified.

Fix OCR issue

Fix issue with OCRing documents with a mix of good and bad pages.

Inline math; speed up LLM calls; allow local models

Inline math

Marker will handle inline math if --use_llm is set. This makes reading scientific papers a lot nicer! The feature has been optimized for speed.

Local LLMs

We now support Ollama - when you're passing the --use_llm flag, you can select the Ollama inference service like this:

marker_single FILEPATH --use_llm --llm_service marker.services.ollama.OllamaService

You can set the options --ollama_base_url and --ollama_model. By default, it will use llama3.2-vision.

Batch LLM calls

LLM calls are now batched across processors for a significant speedup if you're passing --use_llm.

Misc fixes

• Biology PDFs now work a lot better - leading line numbers are stripped
• Improved OCR heuristics
• Updated the examples

What's Changed

• Batch together llm inference requests by @VikParuchuri in #536
• Add another heuristic to clean up line numbers by @iammosespaulr in #538
• Add Inline Math Support by @tarun-menta in #517
• Factor out llm services, enable local models by @VikParuchuri in #544
• Improve LLM speed; handle inline math; allow local models by @VikParuchuri in #537

Full Changelog: v1.4.0...v1.5.0

LLM fixes; new benchmarks

New benchmarks

Overall

Benchmark against llamaparse, docling, mathpix (see README for how to run benchmarks). Marker performs favorably against alternatives in speed, llm as judge scoring, and heuristic scoring.

Table

Benchmark tables against gemini flash:

Update gemini model

• Use the new genai library
• Update to gemini flash 2.0

Misc bugfixes

• Fix bug with OCR heuristics not being aggressive enough
• Fix bug with empty tables
• Ensure references get passed through in llm processors

What's Changed

• Add llm text support for references, superscripts etc by @iammosespaulr in #523
• Update overall benchmark by @VikParuchuri in #515
• Benchmarks by @VikParuchuri in #531

Full Changelog: v1.3.5...v1.4.0

Bump gemini version

When using the optional llm mode, there appears to be a bug with gemini flash 1.5. This release bumps the version to gemini flash 2.0, which appears to resolve the bug.

Fix pytorch bug

There was a bug with pytorch 2.6 and MPS that caused errors in inference - this has been fixed.