From b2aea8330874f06f75d3f1a1c318ded8a3bd69c6 Mon Sep 17 00:00:00 2001 From: Vik Paruchuri Date: Thu, 9 Apr 2026 18:40:20 -0400 Subject: [PATCH 1/2] Add pagination --- chandra/scripts/cli.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/chandra/scripts/cli.py b/chandra/scripts/cli.py index c2be63c..e7d0d83 100755 --- a/chandra/scripts/cli.py +++ b/chandra/scripts/cli.py @@ -71,6 +71,11 @@ def save_merged_output( all_markdown.append(result.markdown) all_html.append(result.html) + # Ensure page separation in merged output + if not paginate_output and page_num < len(results) - 1: + all_markdown.append("\n\n") + all_html.append("\n\n") + # Accumulate metadata total_tokens += result.token_count total_chunks += len(result.chunks) From 8ad8d796b0baf13fd56c0df96a34352d7aae9ab8 Mon Sep 17 00:00:00 2001 From: ashish uppala Date: Wed, 22 Apr 2026 15:49:48 -0400 Subject: [PATCH 2/2] update readme --- README.md | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 4389217..9e37d62 100644 --- a/README.md +++ b/README.md @@ -10,6 +10,11 @@ Model License Discord

+

+ Homepage + Docs + Public Playground +

@@ -17,6 +22,16 @@ 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 @@ -35,11 +50,6 @@ Chandra OCR 2 is a state of the art OCR model that converts images and PDFs into -## Hosted API - -- We have a hosted API for Chandra [here](https://www.datalab.to/), which is more accurate and faster. -- There is a free playground [here](https://www.datalab.to/playground) if you want to try Chandra without installing. - ## Quickstart The easiest way to start is with the CLI tools: