switchboard
C

Chandra

by Datalab

Converts PDFs and images into Markdown, HTML or JSON with layout preserved, handling tables, forms, handwriting and 90+ languages, via a CLI with local or vLLM inference.

3
Skills
None
Auth
No
Streaming
No
Push

Skills

Layout-Preserving OCR

Converts images and PDFs into Markdown, HTML or JSON with detailed layout information, and extracts images and diagrams with captions.

Tables, Forms and Math

Reconstructs forms including checkboxes, complex tables, math and handwriting across 90+ languages from scanned or digital pages.

Local or vLLM Inference

Runs the model locally through HuggingFace with --method hf, or against a vLLM server launched with chandra_vllm, for single files or folders.

Data & AnalyticsInfrastructure & Opsocrpdf-parsingdocument-extractionlayout-analysishandwriting-recognitionvllmhuggingfacedatalab
Visit Agent

Related Agents

K

Keenable

Serves a hundred-billion-document web index built for agents rather than human search pages, returning dense structured…

Research & KnowledgeInfrastructure & Ops
APIMCP
3 skillsAPI Key
N

Netdata

Featured

Monitors infrastructure in real time at per-second granularity and exposes live metrics, logs, and alerts to agents thr…

Infrastructure & OpsData & Analytics
APICLIMCP
4 skillsAPI Key
A

Airbyte Agents

Context layer for AI agents: MCP server and Python SDK giving agents unified access to 50+ business data connectors wit…

Data & AnalyticsInfrastructure & Ops
APIMCP
3 skillsAPI Key
A

Arize Phoenix

Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemet…

Data & AnalyticsInfrastructure & Ops
APICLI
3 skillsNone
chandra-ocr
Converts PDFs and images into Markdown, HTML or JSON with layout preserved, handling tables, forms, handwriting and 90+ languages, via a CLI with local or vLLM inference.
fields
nameChandra
providerDatalab
urlhttps://github.com/datalab-to/chandra
categoriesdata-analytics · infrastructure
accesscli · api
authnone
streamingfalse
pushfalse
verifiedtrue
tagsocr, pdf-parsing, document-extraction, layout-analysis, handwriting-recognition, vllm, huggingface, datalab
skills
layout-ocrLayout-Preserving OCRConverts images and PDFs into Markdown, HTML or JSON wi…
tables-forms-mathTables, Forms and MathReconstructs forms including checkboxes, complex tables…
inference-modesLocal or vLLM InferenceRuns the model locally through HuggingFace with --metho…
→ https://github.com/datalab-to/chandra