Hosted service that parses PDFs and other documents into Markdown and JSON for LLM applications. LlamaIndexのクローズドな製品です。
| ツール | 置き換えの度合い | スター | ライセンス | 利用条件 | セルフホスト | 言語 | 最新リリース | 最終プッシュ |
|---|---|---|---|---|---|---|---|---|
| MinerU | 完全な置き換え | 81k | Other | ソースアベイラブル | 不可 | Python | mineru-4.0.10-released | 2026-10-06 |
| Docling | 完全な置き換え | 68k | MIT | オープンソース | 不可 | Python | v2.134.0 | 2026-10-06 |
| Marker | 完全な置き換え | 40k | Apache-2.0 | オープンソース | 不可 | Python | v2.0.0 | 2026-10-02 |
| MarkItDown | 部分的 | 189k | MIT | オープンソース | 不可 | Python | v0.1.8 | 2026-10-04 |
| Unstructured | 部分的 | 16k | Apache-2.0 | オープンソース | 不可 | HTML | 0.27.16 | 2026-10-06 |
代替5件
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Converts PDFs to Markdown and JSON, keeping formulas and tables.
Get your documents ready for gen AI
Parses PDF, DOCX, PPTX, HTML and images into Markdown or JSON with layout and table models.
Convert PDF to markdown + JSON quickly with high accuracy
Converts PDF, DOCX and images to Markdown, JSON or HTML, with optional LLM help.
Python tool for converting files and office documents to Markdown.
Converts office files, PDFs and more to Markdown, without layout models.
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
Partitions documents into typed elements for RAG pipelines, from Python.