[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:chandra":3},"\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdatalab-to\u002Fchandra\u002FHEAD\u002Fassets\u002Fdatalab-logo.png\" alt=\"Datalab Logo\" width=\"150\" \u002F>\n\u003C\u002Fp>\n\u003Ch1>Datalab\u003C\u002Fh1>\n\u003Cp align=\"center\">\n  \u003Cstrong>State of the Art models for Document Intelligence\u003C\u002Fstrong>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fopensource.org\u002Flicenses\u002FApache-2.0\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCode%20License-Apache_2.0-green.svg\" alt=\"Code License\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.datalab.to\u002Fpricing\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FModel%20License-OpenRAIL--M-blue.svg\" alt=\"Model License\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FKuZwXNGnfH\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20us-5865F2?logo=discord&logoColor=white\" alt=\"Discord\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.datalab.to\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHomepage-datalab.to-blue\" alt=\"Homepage\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdocumentation.datalab.to\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocs-Read%20the%20docs-blue\" alt=\"Docs\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.datalab.to\u002Fplayground\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlayground-Try%20it-orange\" alt=\"Public Playground\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Chr \u002F>\u003Ch1>Chandra OCR 2\u003C\u002Fh1>\n\u003Cp>Chandra OCR 2 is a state of the art OCR model that converts images and PDFs into structured HTML\u002FMarkdown\u002FJSON while preserving layout information.\u003C\u002Fp>\n\u003Ch2>Try Chandra on Datalab\u003C\u002Fh2>\n\u003Cp>Our managed platform runs an improved Chandra with higher accuracy than the open weights, zero data retention by default, SOC 2 Type 2, and custom BAAs.\u003C\u002Fp>\n\u003Cp>If you have high volume workloads, we offer a batch processing service that has processed 200M+ pages per week — we manage the infrastructure so your workloads finish on time.\u003C\u002Fp>\n\u003Cp>Get started with \u003Cstrong>$5 in free credits\u003C\u002Fstrong> — \u003Ca href=\"https:\u002F\u002Fwww.datalab.to\u002F?utm_source=gh-chandra\" rel=\"nofollow ugc noopener\">sign up\u003C\u002Fa> — takes under 30 seconds — or try Chandra in our \u003Ca href=\"https:\u002F\u002Fwww.datalab.to\u002Fplayground?utm_source=gh-chandra\" rel=\"nofollow ugc noopener\">public playground\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cp>Commercial self-hosting requires a license — see \u003Ca href=\"#commercial-usage\" rel=\"nofollow ugc noopener\">Commercial usage\u003C\u002Fa>. For on-prem licensing, \u003Ca href=\"https:\u002F\u002Fwww.datalab.to\u002Fcontact?utm_source=gh-chandra-onprem\" rel=\"nofollow ugc noopener\">contact us\u003C\u002Fa>.\u003C\u002Fp>\n\u003Ch2>News\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>3\u002F2026 - Chandra 2 is here with significant improvements to math, tables, layout, and multilingual OCR\u003C\u002Fli>\n\u003Cli>10\u002F2025 - Chandra 1 launched\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Features\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>Tops external olmocr benchmark and significant improvement in internal multilingual benchmarks\u003C\u002Fli>\n\u003Cli>Convert documents to markdown, html, or json with detailed layout information\u003C\u002Fli>\n\u003Cli>Support for 90+ languages (\u003Ca href=\"#multilingual-benchmark-table\" rel=\"nofollow ugc noopener\">benchmark below\u003C\u002Fa>)\u003C\u002Fli>\n\u003Cli>Excellent handwriting support\u003C\u002Fli>\n\u003Cli>Reconstructs forms accurately, including checkboxes\u003C\u002Fli>\n\u003Cli>Strong performance with tables, math, and complex layouts\u003C\u002Fli>\n\u003Cli>Extracts images and diagrams, and adds captions and structured data\u003C\u002Fli>\n\u003Cli>Two inference modes: local (HuggingFace) and remote (vLLM server)\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdatalab-to\u002Fchandra\u002FHEAD\u002Fassets\u002Fexamples\u002Fmath\u002Fhandwritten_math.png\" width=\"600px\" \u002F>\u003Ch2>Quickstart\u003C\u002Fh2>\n\u003Cp>The easiest way to start is with the CLI tools:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-shell\">pip install chandra-ocr\n\n# With vLLM (recommended, lightweight install)\nchandra_vllm\nchandra input.pdf .\u002Foutput\n\n# With HuggingFace (requires torch)\npip install chandra-ocr[hf]\nchandra input.pdf .\u002Foutput --method hf\n\n# Interactive streamlit app\npip install chandra-ocr[app]\nchandra_app\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch2>Benchmarks\u003C\u002Fh2>\n\u003Cp>Multilingual performance was a focus for us with Chandra 2.  There isn't a good public multilingual OCR benchmark, so we made our own.  This tests tables, math, ordering, layout, and text accuracy.\u003C\u002Fp>\n\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdatalab-to\u002Fchandra\u002FHEAD\u002Fassets\u002Fbenchmarks\u002Fmultilingual.png\" width=\"600px\" \u002F>\u003Cp>See full scores \u003Ca href=\"#multilingual-benchmark-table\" rel=\"nofollow ugc noopener\">below\u003C\u002Fa>. We also have a \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fdatalab-to\u002Fchandra\u002Fblob\u002FHEAD\u002FFULL_BENCHMARKS.md\" rel=\"nofollow ugc noopener\">full 90-language benchmark\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cp>We also benchmarked Chandra 2 with the widely accepted olmocr benchmark:\u003C\u002Fp>\n\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdatalab-to\u002Fchandra\u002FHEAD\u002Fassets\u002Fbenchmarks\u002Fbench.png\" width=\"600px\" \u002F>\u003Cp>See full scores \u003Ca href=\"#benchmark-table\" rel=\"nofollow ugc noopener\">below\u003C\u002Fa>.\u003C\u002Fp>\n\u003Ch2>Examples\u003C\u002Fh2>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Type\u003C\u002Fth>\n\u003Cth>Name\u003C\u002Fth>\n\u003Cth>Link\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003C\u002Ftable>\n",1784240406346]