GOT-OCR v2

Free.ai · ocr · ~500 tokens per page

Tlosa faele mona kapa tobetsa ho sheba

~500 tokens per page
E sebetsa ka ho feletseng ka GPUs tsa rona. Ho ntlafatsa bakeng sa GOT-OCR v2 →

GOT-OCR v2 ke a Mofuta oa OCR. Routed through external models - ~500 tokens ka leqephe (50% markup over upstream cost).

Ho sebelisa ka API

REST API e lumellanang le OpenAI. E etsa konopo'me e bitsa mofuta ona ka metsotsoana.

curl -X POST https://api.free.ai/v1/ocr/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"premium/got-ocr/v2","prompt":"your prompt here"}'
Litokomane tsa API Fumana konopo ea API

Lipotso tse botsoang khafetsa

GOT-OCR v2 e tlosa mongolo ho tloha lifoto le PDFs. Kopitsa leqephe le scanned, a screenshot, kapa a photo ea lengolo-tsoibila le GOT-OCR v2 e khutlisa mongolo - ho boloka line breaks le (ka li-engine tse ka khonehang) li-table, formulas, le struct.

GOT-OCR v2 e sebetsana le li-scripts tse ngata - Latin, Cyrillic, CJK, Arabic, Devanagari, le tse ling. / ocr / landing e na le lethathamo le felletseng la lipuo ka engine.

E-na le ho ngola ka letsoho ka mokhoa o hlophisitsoeng; cursive le shorthand li thata. TrOCR le li-engine tse nang le li-transformer tse ncha li ntle haholo ho feta Tesseract ea khale ho ngola ka letsoho.

Li-engine tse tsebang ho hlophisa (GOT-OCR, Marker, Florence-2) li khutlisa li-table tsa Markdown/HTML le LaTeX bakeng sa li-formula. Li-engine tsa mongolo o hlakileng li khutlisa mongolo o se nang sebopeho - hlahloba mokhoa oa ho tsoa oa mofuta ona.

GOT-OCR v2 ke mochini oa OCR oa premium. Ka li-tokens tsa ~ 500-1,500 ka leqephe, tse bonts'itsoeng ka ho hlaka pele o etsa. OCR e hlophisitsoeng ka boeona e sebetsa ka botlalo ka 30,000-token ea hau ea letsatsi le letsatsi; li-models tsa premium li lefa-ka-ho-e-na le-go, le top-ups ho tloha $ 1.

PNG, JPG, WebP, HEIC, BMP, le li-PDF tse nang le leqephe leng leng ho fihlela ho 50 MB. Li-page tse otlolohileng kapa tse otlolohileng li ntlafatsoa ka ho toba pele ho ho tsoa.

Ho nepahala ha li-character ho ka ba >98% ho li-page tse ngotsoeng ka nepo, ho felloa ke lifoto tse nang le bophahamo bo tlase, ho scans tse sa nepahalang haholo, kapa li-fonts tse sa tloaelehang. Bapisa li-engine ho /ocr/compare/ ha ho hlokahala ho nepahala.

Ee - /batch/ e amohela foldara ea li-images/PDFs. Ho tlosoa ka bobeli ho tla ka /account/?tab=history. Ho boloka moqhaka oa foldara, sebelisa API.

Ea - POST faele ea hau ho /v1/ocr/ le model="GOT-OCR v2". E khutlisa JSON le mongolo + (ha e tšehetsoa) moralo + li-boxes tsa ho qeta ka lentsoe. /api/ e na le ho ngolisoa ka ho feletseng.

Li-model tse sebete li boloka faele ea hau ka GPUs tsa rona; premium e tsamaea ka DPA. Litokomane li tlosoa ka mor'a ho arolelana-fenoa. Re sa koetlise ka ho kenya ha hao.

Yeah - Free.ai e fana ka ts'ebeliso ea khoebo ea ho tlosoa ha mongolo. U hloka litokelo ho lengolo-tsoibila la mohloli.

1-5 metsotsoana ka leqephe ka kakaretso. Layout-aware engines (tablets, mathematics) nka nako e telele. Multi-page PDFs scale roughly linearly.

U rata Free.ai? Reka ho ba lelapa la hao!

Litlhaku tsa leqephe lena