chandra

Datalab

State of the Art models for Document Intelligence

---

# Chandra OCR 2 Chandra OCR 2 is a state of the art OCR model that converts images and PDFs into structured HTML/Markdown/JSON while preserving layout information. ## Try Chandra on Datalab 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. 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. Get started with **$5 in free credits** — [sign up](https://www.datalab.to/?utm_source=gh-chandra) — takes under 30 seconds — or try Chandra in our [public playground](https://www.datalab.to/playground?utm_source=gh-chandra). Commercial self-hosting requires a license — see [Commercial usage](#commercial-usage). For on-prem licensing, [contact us](https://www.datalab.to/contact?utm_source=gh-chandra-onprem). ## News - 3/2026 - Chandra 2 is here with significant improvements to math, tables, layout, and multilingual OCR - 10/2025 - Chandra 1 launched ## Features - Tops external olmocr benchmark and significant improvement in internal multilingual benchmarks - Convert documents to markdown, html, or json with detailed layout information - Support for 90+ languages ([benchmark below](#multilingual-benchmark-table)) - Excellent handwriting support - Reconstructs forms accurately, including checkboxes - Strong performance with tables, math, and complex layouts - Extracts images and diagrams, and adds captions and structured data - Two inference modes: local (HuggingFace) and remote (vLLM server) ## Quickstart The easiest way to start is with the CLI tools: ```shell pip install chandra-ocr # With vLLM (recommended, lightweight install) chandra_vllm chandra input.pdf ./output # With HuggingFace (requires torch) pip install chandra-ocr[hf] chandra input.pdf ./output --method hf # Interactive streamlit app pip install chandra-ocr[app] chandra_app ``` ## Benchmarks 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. See full scores [below](#multilingual-benchmark-table). We also have a [full 90-language benchmark](FULL_BENCHMARKS.md). We also benchmarked Chandra 2 with the widely accepted olmocr benchmark: See full scores [below](#benchmark-table). ## Examples | Type | Name | Link | |------|--------------------------|-------------------------------------------------------------------------------------------------------------| | Math | CS229 Textbook | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/math/cs229.png) | | Math | Handwritten Math | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/math/handwritten_math.png) | | Math | Chinese Math | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/math/chinese_math.png) | | Tables | Statistical Distribution | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/tables/complex_tables.png) | | Tables | Financial Table | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/tables/financial_table.png) | | Forms | Registration Form | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/forms/handwritten_form.png) | | Forms | Lease Form | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/forms/lease_filled.png) | | Handwriting | Cursive Writing | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/handwriting/cursive_writing.png) | | Handwriting | Handwritten Notes | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/handwriting/handwritten_notes.png) | | Languages | Arabic | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/languages/arabic.png) | | Languages | Japanese | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/languages/japanese.png) | | Languages | Hindi | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/languages/hindi.png) | | Languages | Russian | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/languages/russian.png) | | Other | Charts | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/other/charts.png) | | Other | Chemistry | [View](https://github.com/datalab-to/chandra/blob/master/assets/examples/other/chemistry.png) | ## Installation ### Package ```bash # Base install (for vLLM backend) pip install chandra-ocr # With HuggingFace backend (includes torch, transformers) pip install chandra-ocr[hf] # With all extras pip install chandra-ocr[all] ``` If you're using the HuggingFace method, we also recommend installing [flash attention](https://github.com/Dao-AILab/flash-attention) for better performance. ### From Source ```bash git clone https://github.com/datalab-to/chandra.git cd chandra uv sync source .venv/bin/activate ``` ## Usage ### CLI Process single files or entire directories: ```bash # Single file, with vllm server (see below for how to launch vllm) chandra input.pdf ./output --method vllm # Process all files in a directory with local model chandra ./documents ./output --method hf ``` **CLI Options:** - `--method [hf|vllm]`: Inference method (default: vllm) - `--page-range TEXT`: Page range for PDFs (e.g., "1-5,7,9-12") - `--max-output-tokens INTEGER`: Max tokens per page - `--max-workers INTEGER`: Parallel workers for vLLM - `--include-images/--no-images`: Extract and save images (default: include) - `--include-headers-footers/--no-headers-footers`: Include page headers/footers (default: exclude) - `--batch-size INTEGER`: Pages per batch (default: 28 for vllm, 1 for hf) **Output Structure:** Each processed file creates a subdirectory with: - `.md` - Markdown output - `.html` - HTML output - `_metadata.json` - Metadata (page info, token count, etc.) - Extracted images are saved directly in the output directory ### Streamlit Web App Launch the interactive demo for single-page processing: ```bash chandra_app ``` ### vLLM Server (Optional) For production deployments or batch processing, use the vLLM server: ```bash chandra_vllm ``` This launches a Docker container with optimized inference settings. Configure via environment variables: - `VLLM_API_BASE`: Server URL (default: `http://localhost:8000/v1`) - `VLLM_MODEL_NAME`: Model name for the server (default: `chandra`) - `VLLM_GPUS`: GPU device IDs (default: `0`) You can also start your own vllm server with the `datalab-to/chandra-ocr-2` model. ### Configuration Settings can be configured via environment variables or a `local.env` file: ```bash # Model settings MODEL_CHECKPOINT=datalab-to/chandra-ocr-2 MAX_OUTPUT_TOKENS=12384 # vLLM settings VLLM_API_BASE=http://localhost:8000/v1 VLLM_MODEL_NAME=chandra VLLM_GPUS=0 ``` # Commercial usage This code is Apache 2.0, and our model weights use a modified OpenRAIL-M license (free for research, personal use, and startups under $2M funding/revenue, cannot be used competitively with our API). To remove the OpenRAIL license requirements, or for broader commercial licensing, visit our pricing page [here](https://www.datalab.to/pricing?utm_source=gh-chandra). # Benchmark table | **Model** | ArXiv | Old Scans Math | Tables | Old Scans | Headers and Footers | Multi column | Long tiny text | Base | Overall | Source | |:--------------------------|:--------:|:--------------:|:--------:|:---------:|:-------------------:|:------------:|:--------------:|:--------:|:--------------:|:--------------:| | Datalab API | **90.4** | **90.2** | 90.7 | **54.6** | 91.6 | 83.7 | 92.3 | **99.9** | **86.7 ± 0.8** | Own benchmarks | | Chandra 2 | 86.9 | 89.1 | **92.1** | 51.1 | 91.4 | 82.1 | **93.7** | **99.9** | 85.8 ± 0.8 | Own benchmarks | | dots.ocr 1.5 | 85.9 | 85.5 | 90.7 | 48.2 | 94.0 | **85.3** | 81.6 | 99.7 | 83.9 | dots.ocr repo | | Chandra 1 | 82.2 | 80.3 | 88.0 | 50.4 | 90.8 | 81.2 | 92.3 | **99.9** | 83.1 ± 0.9 | Own benchmarks | | olmOCR 2 | 83.0 | 82.3 | 84.9 | 47.7 | **96.1** | 83.7 | 81.9 | 99.6 | 82.4 | olmocr repo | | dots.ocr | 82.1 | 64.2 | 88.3 | 40.9 | 94.1 | 82.4 | 81.2 | 99.5 | 79.1 ± 1.0 | dots.ocr repo | | olmOCR v0.3.0 | 78.6 | 79.9 | 72.9 | 43.9 | 95.1 | 77.3 | 81.2 | 98.9 | 78.5 ± 1.1 | olmocr repo | | Datalab Marker v1.10.0 | 83.8 | 69.7 | 74.8 | 32.3 | 86.6 | 79.4 | 85.7 | 99.6 | 76.5 ± 1.0 | Own benchmarks | | Deepseek OCR | 75.2 | 72.3 | 79.7 | 33.3 | **96.1** | 66.7 | 80.1 | 99.7 | 75.4 ± 1.0 | Own benchmarks | | Mistral OCR API | 77.2 | 67.5 | 60.6 | 29.3 | 93.6 | 71.3 | 77.1 | 99.4 | 72.0 ± 1.1 | olmocr repo | | GPT-4o (Anchored) | 53.5 | 74.5 | 70.0 | 40.7 | 93.8 | 69.3 | 60.6 | 96.8 | 69.9 ± 1.1 | olmocr repo | | Qwen 3 VL 8B | 70.2 | 75.1 | 45.6 | 37.5 | 89.1 | 62.1 | 43.0 | 94.3 | 64.6 ± 1.1 | Own benchmarks | | Gemini Flash 2 (Anchored) | 54.5 | 56.1 | 72.1 | 34.2 | 64.7 | 61.5 | 71.5 | 95.6 | 63.8 ± 1.2 | olmocr repo | # Multilingual benchmark table The table below covers the 43 most common languages, benchmarked across multiple models. For a comprehensive evaluation across 90 languages (Chandra 2 vs Gemini 2.5 Flash only), see the [full 90-language benchmark](#full-90-language-benchmark-table). | Language | Datalab API | Chandra 2 | Chandra 1 | Gemini 2.5 Flash | GPT-5 Mini | |---|:---:|:---:|:---:|:---:|:---:| | ar | 67.6% | 68.4% | 34.0% | 84.4% | 55.6% | | bn | 85.1% | 72.8% | 45.6% | 55.3% | 23.3% | | ca | 88.7% | 85.1% | 84.2% | 88.0% | 78.5% | | cs | 88.2% | 85.3% | 84.7% | 79.1% | 78.8% | | da | 90.1% | 91.1% | 88.4% | 86.0% | 87.7% | | de | 93.8% | 94.8% | 83.0% | 88.3% | 93.8% | | el | 89.9% | 85.6% | 85.5% | 83.5% | 82.4% | | es | 91.8% | 89.3% | 88.7% | 86.8% | 97.1% | | fa | 82.2% | 75.1% | 69.6% | 61.8% | 56.4% | | fi | 85.7% | 83.4% | 78.4% | 86.0% | 84.7% | | fr | 93.3% | 93.7% | 89.6% | 86.1% | 91.1% | | gu | 73.8% | 70