Motsamaisi oa Libuka tsa Sekolo
Ho sebelisoa ka khoebo
380+ li-models
Ha ho letšoao la metsi
Ha ho hlokahale ho ngolisoa
Mofuta:
+ GPT-5, Claude, Gemini
Tlosa arXiv preprint, journal paper, kapa thesis chapter — AI e e fetola ho lengolo le hloekileng le nang le LaTeX-flavored. Li-equations tsa li-mathematics li lula li le li-equations, li-layout tsa li-colon tse ngata li tlosoa, li-citations li bolokiloe. E sebetsa ka Meta Nougat-base.
Ho bala li-equations + ho tlosa li-columns… ~10 sec/page
Likhetho tse tsoetseng pele
Bo_lemo
Tokens e tlase.
Fumana Token e eketsehileng
❤️ U rata Free.ai? Reka le metsoalle ea hau!
Register ho fumana sehokela sa ho u joetsa le ho fumana li-token tse 25 000 ka motsoalle.
U batla ho feta?
Ngola mahala bakeng sa 30K tokens / letsatsi + 10K bonus
Ngola mahala
Ho sebetsana le kopo ea hau...
E-ba le mongolo + li-equations ho tsoa li-papers tsa arXiv, li-journals, le li-thesis. Li-equations tsa li-mathematics li fetoloa ho LaTeX, li-layout tsa li-colon tse ngata li tlosoa, li-citations li bolokiloe. E sebetsa ka Meta Nougat. Ha ho hlokahale ho ngolisoa.
Mokhoa oa ho sebelisa Motsamaisi oa Libuka tsa Sekolo
1
Ke eng eo u e kentseng?
Tlatsa mongolo, kenya faele, kapa hlalosa seo u se batlang. Ha ho hlokahale ak'haonte.
2
Tobetsa ho theha
AI ea rona e sebetsana le kopo ea hau ka metsotsoana ka ho sebelisa li-models tse ntlehali tsa open-source.
3
Tlosa & & arolelana
Kopitsa, kenya kapa arolelana litlamorao tsa hau. Haholo-holo bakeng sa ho sebelisana le batho ba bang le ho rekisa.
Senya sesebelisoa ka API
E-ba le sesebelisoa sena ka ho iketsetsa ho tloha ho kotloloho. OpenAI-compatible REST endpoint, Bearer-token auth, ha ho hlokahale SDK e eketsehileng. Litheko tsa token li lumellana le interface ea webosaeteng.
curl -X POST https://api.free.ai/v1/chat/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model": "qwen7b", "messages": [{"role": "user", "content": "Use the Motsamaisi oa Libuka tsa Sekolo tool on: ..."}]}'Li-Tools tsa AI tse Bulehileng tse Bulehileng
Motsamaisi oa Libuka tsa Sekolo — FAQ
E-ba le PDF ea lingoliloeng tsa thuto / lipatlisiso - arXiv preprint, lingoliloeng tsa kopano, lingoliloeng tsa lingoliloeng, lingoliloeng tsa lingoliloeng -'me AI e e fetola ho lengolo le hlophisitsoeng ka LaTeX. Li-equations tsa lipalo li tsoa joalo ka LaTeX e nepahetseng, li-layout tsa li-colon tse ngata li hlahisoa ho latela ho bala,' me li-citations + li-reference lists li bolokiloe. E entsoe ka kotloloho bakeng sa mofuta oa litokomane tsa litsebi tse thata tsa pdftotext mangles.
Nougat-base ea Meta — mofuta oa ho lekanya-ho lekanya-ho lekanya o koetlisitsoeng ho limilione tsa lihlooho tsa arXiv. E sebetsana le leqephe le leng le le leng la PDF e le setšoantšo'me e hlahisa Markdown + LaTeX e hlophisitsoeng, e leng hobaneng li-equations li ka tsoa ka nepo le ha li etsoa e le li-glyphs tsa raster ho tsoa ho PDF.
Mochini oa Docling (PDF ho Markdown) o sebelisa IBM Granite-Docling - o potlakileng, o tsebahalang, o ntlafalitsoeng bakeng sa litokomane tsa khoebo ka kakaretso joalo ka litokomane, litokomane, litokomane. Nougat e potlakile empa e ntle haholo ho libuka tsa thuto hobane e ne e le ka ho khetheha ho ithuta ka liteko tsa lipalo + li-colon tse ngata tsa litsebi. Sebetsa Docling bakeng sa litokomane tsa khoebo, Nougat bakeng sa lipatlisiso.
Ea — ke e 'ngoe ea litšobotsi tse ntle. Lipalo-palo tsa kahare li khutlela joaloka '$...$', li-equations li bonts'itsoe joalo ka '$$...$$'. E ka bala li-equations tse entsoeng ka LaTeX ho tloha ho arXiv le li-equations tsa raster tse skened ho tloha li-papers tse fetileng. Boleng bo ka phatlalatsoa bakeng sa li-papers tse ngata.
Ee — Nougat e tlohela li-layouts tse nang le li-colon tse peli / tse tharo ho latela ho bala ka ho toba. Ha ho na ho feta ho qeta ho ngola ka har'a hlooho pakeng tsa li-colon. Litlhaku tsa morao li tlosoa ho li-block tsa litlhaku tsa morao qetellong ea karolo e ngoe le e ngoe.
Li-markers tsa ho ngola li `[12]` / `(Smith 2020)` li lula li le karolong. Li-reference lists ka morao li ka sebelisoa ka ho boloka ho hlophisoa ho sa senyehe, ka hona u ka kenya tlhahiso ho Zotero / Mendeley / ho ngola ho hlophisitsoeng.
Ka 8-15 lisegunete ka leqephe ka leng ka H200. Leqephe la 10 la lengolo la kopano le tsamaea ka metsotso e 2. Likarolo tsa lipotso tse telele (lihlooho tsa 50+) li nka metsotso e 8-12 - li romelle le ho tsamaea.
300 tokens per page (floor 600). A 10-page conference paper = 3,000 tokens. A 30-page thesis chapter = 9,000 tokens. The daily free pool covers most casual research-reading.
E tšoaea ka ChatGPT/Claude bakeng sa ho kopanya litokomane, ho theha RAG ea hau ka ho khetheha ka litokomane, ho batla ka ho khetheha likamore tsa hau tsa ho ngola, ho kopitsa li-equations ka kotloloho ho liprojekteng tsa LaTeX, kapa ho bala litokomane e le litokomane tse tloaelehileng ka mohala oa hau.
Ee — Nougat e etsa mohato oa eona oa OCR. Li-submissions tsa arXiv tse hlahisitsoeng ka boiketsetso li ntle haholo (ho etsa li-equation tse hloekileng); li-papers tse fetileng tse skewered li sebetsa hape empa ho nepahala ha lipalo ho fokotseha. Bakeng sa liphetho tse ntle ka ho fetisisa tsa lipalo ka li-scan, re-scan ka 300+ DPI pele o kenya.
Ho sebetsa kapele, ho bolokiloe tlhahiso ea mongolo oa LaTeX (24h e sa tsejoeng / 7d e lefa ho arolelana- ho kopanya ho fela), mohloli oa PDF o tlosoa kapele kamora ho tlosoa. Ha ho sebelisoa ho ithuta. /privacy/ bakeng sa melao e felletseng.
Ea - POST a multipart `faele` ho /v1/document/academic-pdf /. Ho khutla {text_url, lihlooho, preview, tokens, share_url}. Bearer auth (sk-free-…) fana ka 10K tokens mahala / khoeli. /api / na le mohlala curl.
U tla lekola eng ka sesebelisoa sena?