{"id":34108954,"url":"https://github.com/retab-dev/retab","last_synced_at":"2026-03-27T04:09:20.121Z","repository":{"id":271410244,"uuid":"911375734","full_name":"retab-dev/retab","owner":"retab-dev","description":"The developper starter pack for document processing","archived":false,"fork":false,"pushed_at":"2026-03-20T21:04:53.000Z","size":79795,"stargazers_count":41,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-03-21T12:17:51.619Z","etag":null,"topics":["api","document-analysis","llm","openai","structured-generation"],"latest_commit_sha":null,"homepage":"https://www.retab.com","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/retab-dev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-01-02T21:44:02.000Z","updated_at":"2026-03-21T10:29:30.000Z","dependencies_parsed_at":"2025-02-28T10:49:07.729Z","dependency_job_id":"84ce1012-21eb-42a4-87d2-345110aba11e","html_url":"https://github.com/retab-dev/retab","commit_stats":null,"previous_names":["uiform/uiform","retab-dev/retab"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/retab-dev/retab","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retab-dev%2Fretab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retab-dev%2Fretab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retab-dev%2Fretab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retab-dev%2Fretab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/retab-dev","download_url":"https://codeload.github.com/retab-dev/retab/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/retab-dev%2Fretab/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31018555,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-27T03:51:26.850Z","status":"ssl_error","status_checked_at":"2026-03-27T03:51:09.693Z","response_time":164,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["api","document-analysis","llm","openai","structured-generation"],"created_at":"2025-12-14T18:24:22.379Z","updated_at":"2026-03-27T04:09:20.117Z","avatar_url":"https://github.com/retab-dev.png","language":"Jupyter Notebook","readme":"\u003cdiv align=\"center\" style=\"margin-bottom: 1em;\"\u003e\n\n\u003cimg src=\"https://raw.githubusercontent.com/Retab-dev/retab/refs/heads/main/assets/visuals/retab-logo.png\" alt=\"Retab Logo\" width=\"150\"\u003e\n\n# Retab\n\n*The AI Automation Platform*\n\nMade with love by the team at [Retab](https://retab.com) 🩷.\n\n[Our Website](https://retab.com) | [Documentation](https://docs.retab.com/get-started/introduction) | [Discord](https://discord.com/invite/vc5tWRPqag) | [Twitter](https://x.com/retabdev)\n\n\u003c/div\u003e\n\n---\n\n### What is Retab?\n\n[Retab](https://retab.com) is the complete developer platform and SDK for shipping state-of-the-art document processing in the age of LLMs. \n\nWe want you to use Retab for a defined purpose: get **SHIP FAST** automations to get **STRUCTURED** \u0026 **QUALITY** data.\n\nFor this mission, we provide the best-in-class preprocessing, help you generate prompts \u0026 extraction schemas that fit your preferred model providers, iterate \u0026 evaluate the accuracy of your configuration, and ship fast your automation directly in your code.\n\n### Why did we build Retab?\n\nBecause of **a new, lighter paradigm**\n\nLarge Language Models collapse entire layers of legacy OCR pipelines into a single, elegant abstraction. When a model can read, reason, and structure text natively, we no longer need brittle heuristics, handcrafted parsers, or heavyweight ETL jobs. Instead, we can expose a small, principled API: \"give me the document, tell me the schema, and get back structured truth.\" Complexity evaporates, reliability rises, speed follows, and costs fall—because every component you remove is one that can no longer break. \n\nLLM‑first design lets us focus less on plumbing and more on the questions we actually want answered—Retab stands here. We help you **unlock these capabilities**, offering you all the software-defined primitives to build your own document processing solutions. We see it as **Stripe** for document processing.\n\nCheck our [documentation](https://docs.retab.com/overview/introduction).\n\nJoin our [Discord](https://discord.com/invite/vc5tWRPqag) and share your feedback.\n\n---\n\n## API Key\n\nTo use the API, you need to sign up on [Retab](https://www.retab.com/).\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./assets/visuals/API-key.png\" alt=\"API Key\" width=\"800\"\u003e\n\u003c/p\u003e\n\n---\n\n## SDK\n\n1. Install the SDK\n```python\npip install retab\n```\n\n2. Generate a Schema\n```python\nfrom pathlib import Path\nfrom retab import Retab\nclient = Retab(api_key=\"YOUR_RETAB_API_KEY\")\n\nresponse = client.schemas.generate(\n    documents=[\"Invoice.pdf\"],\n    model=\"retab-small\",\n)\n```\n\n3. Extract Data\n```python\nfrom pathlib import Path\nfrom retab import Retab\n\nfrom retab import Retab\nclient = Retab()\n\nresponse = client.documents.extract(\n    json_schema = \"Invoice_schema.json\",\n    document = \"Invoice.pdf\",\n    model=\"retab-small\",\n)\n\nprint(response)\n```\n\n---\n\n## Projects\n\nOn the [Platform](https://www.retab.com/), *Projects* provide a systematic way to test and validate your extraction schemas against known ground truth data. Think of it as evals for document AI. You can measure accuracy, compare different models, and optimize your extraction pipelines with confidence.\n\nThe project workflow for schema optimization:\n1. Run initial project → identify low-accuracy fields\n2. Refine descriptions and add reasoning prompts → re-run project\n3. Compare accuracy improvements → iterate until satisfied\n4. Deploy optimized schema to production\n\n```python\nfrom retab import Retab\n\nclient = Retab()\n\n# Submit a single document\ncompletion = client.projects.extract(\n    project_id=\"eval_***\",\n    document=\"path/to/document.pdf\"\n)\n\nprint(completion)\n```\n\nProjects give you an easy-to-use automation engine that's easy to integrate in your codebase and workflows.\n\nCheck our [documentation](https://docs.retab.com/core-concepts/Projects).\n\n---\n\n\n## Community\n\nLet's create the future of document processing together.\n\nJoin our [Discord](https://discord.com/invite/vc5tWRPqag) to share your journey, discuss best practices, and give your feedback. You can also follow us on [X (Twitter)](https://x.com/retabdev) at us.\n\nWe can't wait to see how you'll use Retab.\n\n* [Discord](https://discord.com/invite/vc5tWRPqag)\n* [Twitter](https://x.com/retabdev)\n\n---\n\n## Useful Links\n\n* [x] **API**: [Documentation](https://docs.retab.com/api-reference/introduction)\n* [x] **SDKs**: [Python \u0026 JavaScript SDK](https://docs.retab.com/overview/quickstart)\n\n* [OpenAI](https://platform.openai.com/docs/guides/structured-outputs), [Google](https://ai.google.dev/gemini-api/docs/structured-output), [xAI](https://docs.x.ai/docs/guides/structured-outputs), [Outlines](https://dottxt-ai.github.io/outlines/latest/reference/generation/structured_generation_explanation/) on structured generation\n* [Structured generation Starter Pack](https://github.com/retab-dev/structured-generation-starter-pack)\n* [Quickstart](/get-started/quickstart)\n* [API Reference](/api-reference/introduction)\n* [Github Repository](https://github.com/retab-dev/retab)\n\n---","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fretab-dev%2Fretab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fretab-dev%2Fretab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fretab-dev%2Fretab/lists"}