NuExtract3 has crossed 1M+ downloads this month!
    Skip to content
    Resources/Markdown for RAG

    Turn document content into
    OCR Markdown.

    Explore OCR results from scanned and mixed-layout documents, ready to use as text in retrieval and AI workflows.

    JSON templatesDocument imagesMultilingual extraction
    Invoice ScanSupplied example
    Invoice Scan source document

    Explore the complete source and result below.

    YOUR DOCUMENT OUTPUT

    Document content in Markdown

    NuExtract3 OCR converts document images to Markdown. Its output format includes headings and paragraphs, HTML tables, LaTeX mathematics and figure descriptions.

    The supplied examples pair each source image with its OCR Markdown. Switch between the formatted view and raw Markdown to explore the result. The NuExtract3 release describes OCR as a document preprocessing step for LLM and RAG workflows.

    Learn more: NuExtract3 OCR format, NuExtract3 release.

    Explore the supplied examples

    Source documents, templates and results from the supplied NuExtract examples.

    Invoice ScanOCR → Markdown

    Explore the invoice scan source document and its supplied OCR Markdown result.

    SOURCE DOCUMENT
    Source document for the Invoice Scan example
    Open the source document at full size.

    CASCADE UTILITIES COMMISSION

    BILLING STATEMENT

    Invoice No.CU-91-07823
    Contract Code87-42N-19
    Invoice Date07/16/91
    Dept. CodePW-34

    BILL TO:

    Northwest Environmental Consultants

    ATTN: Accounts Payable

    2211 Westlake Avenue, Suite 500

    Seattle, WA 98121-3012

    Agency Ref. No.91-2W66-772
    Request No.RQ-73841
    Due Date08/15/91
    DescriptionApproved BudgetCumulative TotalPrevious BilledCurrent TotalBalance Remaining
    Salaries — Project Staff236,700.00123,562.4781,344.3142,218.16113,137.5
    Fringe Benefits56,230.0029,636.8619,872.129,764.7426,593.1
    Travel & Per Diem18,950.007,984.225,413.472,570.7510,965.7
    Field Services
    — Field Surveys34,800.0014,225.609,110.355,115.2520,574.4
    — Water Sampling22,450.009,866.156,210.603,655.5512,583.8
    — Geological Testing16,700.006,707.804,329.102,378.709,992.2
    Materials & Supplies11,250.004,227.982,914.331,313.657,022.0
    Subcontractors
    — Hydrologic Modeling48,000.0021,575.0014,375.007,200.0026,425.0
    — Vegetation Analysis19,500.008,190.005,460.002,730.0011,310.0
    Equipment Rental23,100.0010,114.656,741.003,373.6512,985.3
    Software & Licences9,600.005,142.503,402.501,740.004,457.5
    Communications6,420.002,475.681,642.33833.353,944.3
    Permits & Fees5,800.001,802.151,201.65600.503,997.8
    Subtotal Direct Costs505,500.00245,516.86167,617.3977,899.65259,983.1
    Indirect Costs (Overhead)101,100.0050,438.2533,625.5016,812.7550,661.7
    GRAND TOTAL606,600.00295,955.11201,242.8994,712.40310,644.8

    Notes:

    1. Please reference Invoice No. on payment.

    2. For questions call (206) 555-2172.

    Mixed LayoutOCR → Markdown

    Explore the mixed layout source document and its supplied OCR Markdown result.

    SOURCE DOCUMENT
    Source document for the Mixed Layout example
    Open the source document at full size.

    SUMMIT INDUSTRIAL SYSTEMS

    1847 North Harbor Avenue, Suite 410

    Milwaukee, WI 53202, United States

    Phone: +1 (414) 555-0276

    Email: documents@summitindsys.com

    Vendor ID: SIS-44-02918

    Document RefSD-2406-1187
    Issue DateJune 03, 2024
    Account CodeAC-77841
    CurrencyUSD
    TermsNet 21
    PO ReferencePO-90413
    LoggedJune 07, 2024

    MATERIAL REGISTER — SECTION A

    Item CodeDescriptionAmount (USD)
    3101Nitrile gloves, powder-free, box of 100$82.00
    3102Safety goggles, anti-fog, clear lens$126.40
    3103Absorbent pads, industrial grade, pack of 50$174.00
    3104Caution cones, reflective, 28 in$268.50
    3105Lockout tags, weatherproof, set of 25$61.25
    3106Cable markers, heat resistant, assorted set$94.80
    3107Utility blades, heavy duty, pack of 100$58.00
    3108Hand cleaner, citrus formula, 4 L$72.90
    3109Floor degreaser concentrate, 5 gal$188.40
    3110Disposable coveralls, XL, case of 25$241.75
    3111Respirator cartridges, organic vapor pair$153.60
    3112Barrier chain, yellow-black, 25 m reel$87.50
    3113Extension leads, 12/3 industrial, 50 ft$219.30
    3114Steel toe overshoes, universal fit$133.20
    3115Inspection flashlight, magnetic base$104.85
    3116Spill socks, absorbent, case of 12$166.40
    3117Warehouse labels, laminated, roll of 500$49.60
    3118Dust masks, fold-flat, box of 50$63.90
    3119First aid refill modules, standard kit$145.00
    3120Hand truck wheels, non-marking pair$96.30
    3121Stretch wrap, 80 gauge, case of 4$112.80
    3122Packing list envelopes, carton of 1000$54.70
    Item CodeDescriptionAmount (USD)
    3123Shelf bin labels, removable adhesive$38.50
    3124Anti-slip matting, black, 6 m roll$129.40
    3125Forklift checklist books, duplicate format$44.10
    3126Paint marker set, white and yellow$51.60
    3127Rechargeable work light, slim profile$118.90
    3128Pallet corner boards, 48 in, bundle$69.20
    3129Tamper seals, numbered, pack of 500$77.75
    3130Warehouse brooms, 24 in push type$92.00
    3131Sanitizing wipes, canister carton$86.40

    Remittance Details

    Summit Industrial Systems

    Northern Trust Bank

    Account No.: 902771540

    Routing No.: 071000088

    SWIFT: CNORUS44

    RECEIVED stamp

    JUN 07 2024

    Scanned PDFOCR → Markdown

    Explore the scanned pdf source document and its supplied OCR Markdown result.

    SOURCE DOCUMENT
    Source document for the Scanned PDF example
    Open the source document at full size.

    ARCH 3: 1944 341

    Court behind it. It has voided laws creating Negro districts in cities, but upheld those compelling separate railroad accommodations, declaring that segregation is not discrimination when the facilities offered both races are substantially the same. Taking the same ground, the Interstate Commerce Commission recently dismissed a complaint filed by eighteen Negro seamen against the Atlantic Coast Line. The men asked for a bold declaration that segregation in and of itself today must be regarded as constituting an unlawful discrimination. That puts the Negro attitude on segregation in nutshell. The Court, on the other hand, "What complainants asked us to decide is in its essence a social question and not a question of inequality of treatment."

    This makes it lawful, if somewhat grotesque, for incidents like the following to happen. On a crowded troop train going through Texas the colored soldiers were fed behind a Jim Crow curtain at one end of the dining car. In the main section, along with the white folks, a group of German war prisoners dined—and no doubt felt their illusions of race superiority on that Jim Crow curtain.

    4.

    The assignment of Negro units in the Army to menial jobs is a widespread practice. Colored inductees go to camp for military training and find themselves assigned to service units—cooking, shoveling coal, waiting on the white officers. Entering service, they may find themselves building the Burma Road, or African bases, or encountering winter temperatures of 50 degrees below zero backing the Alaska Highway or the Canal pipeline out of the Canadian wilderness. The white units trained at the same time are in the fighting war, where the Negro longs to be. "The sight of masses of Negro soldiers constantly blocked off into separate groups and assigned to menial jobs," a white officer writes, "generates in the mind of the average soldier a powerful feeling of superiority and of being different."

    A highly trained Negro technologist turned up in the psychotic ward of a hospital. His Army service was picking up papers around the officers' quarters in a Southern camp. When he was transferred to radio work his mental troubles vanished. Another inductee, a brilliant biochemist, had a fantastic Army career. At the reception center on the Pacific Coast the officers proposed to use his years of medical training to be the Navy's advance. He was sent to Camp A for training and assigned to a post in the biological laboratory. Before he could start work he was shipped further east to Camp B, and enrolled for technical training as an officer. He passed this course with high honors, and was promptly shipped to Camp C, further west—classed as corporal and assigned to the Air Forces. A week later he found himself in Camp D in the Southwest, assigned to labor detail. That meant losing his corporal's stripes gained in another division. He wrote his wife:

    I find that this post is the "Fort of Lost Hope." . . . Merciful God, I have not been so close to loss of faith as I am at this moment. . . . All this build-up for something more than to be treated like a brainless gorilla fit for nothing more than a post-hole digger and a stripper of wire, a yard bird. . . . I swear if this was Guadalcanal or Australia or North Africa I would expect nothing and would give everything, even my life. . . . It is mockery, let no one tell you differently, this sudden opening up of the so-called exclusive branches of the services to Negroes. We are trained, become skilled—and then the oblivion of common labor.

    It is no secret that the Air Corps wished no Negro inductees. But it was forced to let the color bar down late in 1940 and created ten "Aviation Squadrons (Separate)" which served no specific military need and were assigned to whatever odd jobs of common labor the various air fields could offer. There was no equivalent white organization and these Negro units would probably never have come into existence but for the necessity of making some provision for the Negroes enlisted in the Air Forces.

    The Air Corps began by training Negroes for combat aviation in only one branch—pursuit flying. A segregated base was set up near Tuskegee Institute and advanced training was at Selfridge Field. Pursuit flying is the most difficult type of combat aviation. Perhaps the Air Corps was paying tribute to the Negro; possibly it was trying to discourage him. In any event, the pursuit flyers not only made good in training, but the Ninety-ninth Squadron, the first and only one sent abroad, has won special praise from Secretary of War Stimson and others for its fine spirit and the specialized dive bombing the men were called upon unexpectedly to perform when the squadron was on loan to the British Eighth Army in Italy.

    In 1943, schools for bombardiers and navigators were opened to Negroes and the first squadron, known as Squadron 332, was graduated on February 26, 1944, at Hondo, Texas, and will now receive training as bombardiers.

    In some respects the Navy, with its ancient and Southern-gentleman traditions, tallies with the policy of the modern Air Command. Between 1922 and 1942 Negroes were excluded from the Navy, serving as stewards, chefs and messboys. Several months after Pearl Harbor the Navy broke down and admitted colored men as apprentice seamen with the chance of becoming petty officers. It has let down the bars to women—but not dark-skinned women. There are no colored Waves, Spars or Marine Corps Auxiliaries. And since no Negro was commissioned until a few weeks ago, there are no Negro chaplains in the Navy.

    Complex TableOCR → Markdown

    Explore the complex table source document and its supplied OCR Markdown result.

    SOURCE DOCUMENT
    Source document for the Complex Table example
    Open the source document at full size.

    Generalitat de Catalunya

    Departament d'Educació

    Institut Gallecs

    Curs 2021-22

    - Els llibres de color blau indiquen que es manté respecte al curs anterior.

    - Els llibres de color groc indiquen que es tracta d'un canvi per a aquest curs.

    - Els llibres de color vermell indiquen que no s'han de comprar perquè van a càrrec del centre.

    - Matèries sense llibre: Dossiers, llicències i el Kit de tecnologia s'hauran de pagar i de recollir a través de l'AMPA a partir de setembre.

    1 ESO

    MATÈRIATÍTOLAUTOREDITORIALISBN
    LLENGUA CATALANAPunt VolatCastellnou (Didacta +)9788417803124
    Duna, Diari d'un estiu.Muriel VillanuevaBabulinka Books EditorialCol·lecció: Petites Joies per a Grans Lectors. 20169788494159077
    El nen que xatejava amb Jack Sparrow.Francesc PuigpelatBromera Col·lecció: L'Elefant. 20159788490264072
    LLENGUA CASTELLANAProyecto AsteriscoCastellnou (Didacta +)9788417803186
    Manzanas rojasLuis MatillaEd. Anaya978846673989
    Fàbulas de EsopoJerry PinkneyVicens Vives978843671648
    ANGLÈSThink Ahead ESO 1. Student's book. Think Ahead ESO 1. Workbook (cat).Burlington Books9789925300662
    Burlington Books9789925300686

    Generalitat de Catalunya

    Departament d'Educació

    Institut Gallecs

    Curs 2021-22

    MATÈRIATÍTOLAUTOREDITORIALISBN
    FRANCÈSNouvelle Génération A1-A2Santillana9788490494745
    CIÈNCIES EXPERIMENTALSScience Bits ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE9788412213485 (llicència digital)
    MATEMÀTIQUESProjecte MOTIMATS-ONMAT (llicència digital) Tekman Books ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE
    TECNOLOGIATecnologia 1 ESOTEIDE9788430783175
    VISUAL I PLÀSTICASENSE LLIBRE-KIT DE MATERIAL
    CIÈNCIES SOCIALSSENSE LLIBRE-dossier

    Codi: 04imp02

    Responsable: Coordinador Qualitat

    Versió: 5

    Full d'informació a l'alumnat i famílies

    Aquest document pot quedar obsolet una vegada imprès | Pàgina 1 de 2

    Codi: 04imp02

    Responsable: Coordinador Qualitat

    Versió: 5

    Full d'informació a l'alumnat i famílies

    Aquest document pot quedar obsolet una vegada imprès | Pàgina 2 de 2

    From a document to your project

    1. Create a project. Set up a workspace for your extraction task.
    2. Define the template. Name the fields and choose their types. The template can include nested objects and lists.
    3. Add examples. Use document and output pairs in the project’s Example Set.
    4. Run in the Playground. Upload a document to see the extraction result.
    5. Connect your application. Find the project ID and integration details in the API tab.

    Learn more: NuExtract user guide.

    Product documentation

    Learn more: NuExtract user guide, NuExtract3 model card, NuExtract3 release.

    YOUR DOCUMENT WORKFLOW

    Bring your documents.
    Choose your output.

    Explore JSON extraction, OCR Markdown and deployment options with the NuExtract team.

    Book a NuExtract demo