From a011a16b5cde849b3c49ecf076669e955d17d444 Mon Sep 17 00:00:00 2001 From: Nameet Potnis Date: Sun, 26 Apr 2026 00:40:32 +0530 Subject: [PATCH 1/2] Add pdfmux to Parsers, OCR and extraction --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index d4143c8..73b4249 100644 --- a/README.md +++ b/README.md @@ -37,6 +37,7 @@ - [Iteration Layer](https://iterationlayer.com) - An AI-powered API that extracts structured data from PDFs, images, DOCX, and text files. - [LiteParse](https://github.com/run-llama/liteparse) - An open-source standalone PDF parser that provides spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. - [PDF Oxide](https://github.com/yfedoseev/pdf_oxide) - Fast Rust PDF library and CLI for text and image extraction and markdown conversion, with bindings for Python, Go, JS, .NET, Java, PHP, Ruby, and WASM. +- [pdfmux](https://github.com/NameetP/pdfmux) - Python PDF-to-Markdown extraction library with per-page confidence scoring and self-healing fallback. Re-extracts low-confidence pages automatically; built for RAG pipelines. Built-in MCP server, LangChain + LlamaIndex loaders. #2 on opendataloader-bench. MIT licensed. ## Creation and production From 4012dafec631f15c23207df2c622996011e7e06d Mon Sep 17 00:00:00 2001 From: Alessio Date: Sun, 26 Jul 2026 11:23:30 +0200 Subject: [PATCH 2/2] Adapt description to pattern --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 73b4249..9036fbb 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ - [Iteration Layer](https://iterationlayer.com) - An AI-powered API that extracts structured data from PDFs, images, DOCX, and text files. - [LiteParse](https://github.com/run-llama/liteparse) - An open-source standalone PDF parser that provides spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. - [PDF Oxide](https://github.com/yfedoseev/pdf_oxide) - Fast Rust PDF library and CLI for text and image extraction and markdown conversion, with bindings for Python, Go, JS, .NET, Java, PHP, Ruby, and WASM. -- [pdfmux](https://github.com/NameetP/pdfmux) - Python PDF-to-Markdown extraction library with per-page confidence scoring and self-healing fallback. Re-extracts low-confidence pages automatically; built for RAG pipelines. Built-in MCP server, LangChain + LlamaIndex loaders. #2 on opendataloader-bench. MIT licensed. +- [pdfmux](https://github.com/NameetP/pdfmux) - Python PDF-to-Markdown extraction library with per-page confidence scoring and self-healing fallback. ## Creation and production