PDF ki te Markdown
Whakama ā-pūnaha OK
380+ tauira
Kāore he tohu wai
Kāore he kōwhiringa e hiahiatia ana
Kāhua:
+ GPT-5, Claude, Gemini
Ka tangohia he PDF — Ka tahuri te AI ki te Markdown mārama GitHub-takaro me ngā taitara, ngā waeine, ngā rārangi, ngā ripanga, me ngā kōwae waehere katoa i tiakina. Ka whakahaua e IBM Granite-Docling-258M (Apache 2.0). Āhua kē atu + he mārama ake i te whakawāteatanga kupu pūnoa.
E whakawātea ana i te Markdown mātauranga-whakahaere... ~5-10 sekon/pāpāho
Ko ngā kōwhiringa hōhonu
Whakamutunga
Kua iti te tohu.
Ka whiwhi atu ētahi atu tohu
❤️ E hiahia ana ki te Free.ai? Whakapāpāho ki ōna hoa!
Kaituhi ki kia whiwhi ai i tētahi pātahitanga tohutoro, ā, ka whiwhi i ngā tohu 25,000 ia hoa.
E hiahiatia ana ētahi atu?
Ka whakaingoatia te wāteatanga mo ngā tohu 30K / rā + tāpiri 10K
Ka whakaingoatia te pūkete
E whakapāpā ana i tō tātau tono...
Ka tahuri i tētahi PDF ki te Markdown mārama GitHub-tauri me ngā taitara, ngā ripanga, ngā rārangi, me ngā kōwae waehere i tiakina. Ka whakapūtātia e IBM Granite-Docling. Whakamahara, kāore i te whakawhāiti, kāore i te whakaingoatia.
He pēhea te whakamahi PDF ki te Markdown
1
Kei roto i tō tou tāuru
Type i te kupu, tuku i tētahi faila, whakaahua rānei i te mea e hiahiatia ana e koe. Kāore he tatau e hiahiatia ana.
2
Ka tirohia te whakatūnga
Ka tukatuka tātau AI i tō tātau tono i roto i ngā wā kotahi mā te whakamahi i ngā tauira pūtake tūwhera pai rawa.
3
Whakahua & tiritiri
Whakataki, tārua, tiritiri rānei i tōna hua. Whakatika noa iho mō te whakamahinga whaiaro, hokohoko rānei.
Ka whakamahia tēnei utauta mā te API
Ka whakamātautau tēnei utauta mai i tōtou waehere. Ko te wāhi mutunga o te REST e ōrite ana ki te OpenAI, te mana tohu-tokona, kāore he SDK tāpiri e hiahiatia ana. Ko ngā utu tohu e ōrite ana ki te whakawhitinga whatunga.
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 PDF ki te Markdown tool on: ..."}]}'E pā ana ki ngā utauta AI wātea
PDF ki te Markdown — FAQ
Ka whakatū i tētahi PDF me te AI e tahuri ana ki te Markdown-GitHub-tauri mārama - ka noho ngā taitara hei taitara, he ripanga hei ripanga, he rārangi hei rārangi, he kōwae waehere hei kōwae waehere. Ka haere i mua i te whakawāteatanga kupu noa; Ka tiakina te aroākapa hanganga o te tuhinga kia taea ai e koe te tuku i te huaputa ki tētahi pae tuhinga, ki tētahi pūwāhi LLM RAG, ki tētahi taupū rangahau rānei.
IBM Granite-Docling-258M (Apache 2.0). He tauira tirohanga-ki-whakatauira-ki te whakarerekētanga tuhinga ā-whakahaere - ka tere ake te PDF ki te kupu + he mātauranga kē atu i te whakahaere i tētahi tauira reo tirohanga noa iho i ia pātaka.
Ko te pdftotext he tūpāpaku matatini - ko ngā waeine me ngā ripanga e whakapeka ana ki roto i tētahi pakitara o ngā kupu. Adobe Export ki te Wā ka pupuri i te hoahoa engari ka whakaputaina.docx + ngā utu ~ $ 15 / mo. Ka pupuri te Docling i te hanganga SEMANTIC (ngā taumata whakahuahua, ngā rārangi hei rārangi, ngā ripanga hei ripanga Markdown) me ngā huaputa he āhuahira LLMs me ngā utauta dev ka taea e te tangata te whakapau.
LlamaParse me te kore i hangaia he taumata wātea, engari he whāinga / marama, ā, e hiahiatia ana he kī API. Docling-258M e haere ana i te pae i runga i tātau GPU + he Apache 2.0, kāore he tātaritanga i ia pātaka, kāore he whakaingoatanga kī. He āhua ā-whāinga te āhua me LlamaParse i ngā tuhinga paerewa.
He — ka hoki mai ngā ripanga hei ripanga pai o te Markdown. Ko ngā ripanga taumaha-tīwae / tīwae-tirohia e whakawāteatia ana kia nui ake te āhua o te āhua o te āhua o te āhua o te taupānga (he whakawhāititanga taketake o Markdown, ehara i te hapa o te tauira). Mō te tika o te ripanga tika, ka tautokona hoki e tātau a `format=html` mā te API e pupuri ana i te rowspan/colspan.
Ka mahi a Granite-Docling i te hipanga OCR anō — e mahi ana i ngā PDFs i whakawāteatia me te whakawāteatia. I whakawāteatia i te DPI iti iho (<150) ka ngaro ētahi tika o te kupu; ki te 200+ DPI mō ngā hua pai rawa.
Ko te nuinga o ngā whārite LaTeX-hoatu e puta ana hei pāngarau ā-waiere '$...$` Markdown. Mō ngā pukapuka rangahau me ngā pāngarau taumaha, ka tuku hoki mātau i te utauta whakahuahua-pāpāho-whakahuahua (Nougat) e hāngai ana mō ngā whārite me ngā whakahuahua.
Neke atu i te 5-10 ngā takiwā i ia pātaka i runga i a tātau H200. He pūrongo 30-pātaka ~3-5 ngā minu. Ko te tikanga o te tauira iti, he wātea ngā PDFs iti i te tauwāhi o ia rā.
200 ngā tohu i ia pātaka, me tētahi papa 500-tokena. He kānataraki 5-pātaka = 1,000 ngā tohu. He pūrongo 30-pātaka = 6,000 ngā tohu. Ko te 5K te pūtea wātea i ia rā e taupoki ana i te nuinga o te whakamahinga noa iho.
PDF — i whāia te whāinga-mātauranga + i whakawāteatia. Ko te whakaatatanga nui rawa o te 50 MB. Ko ētahi atu momo tuhinga (DOCX, EPUB, HTML, ērā atu) kei runga i te mahere huarahi; mō tēnei, ka whakataka-me te tahuri me te utauta tahuri pdf tuatahi.
I whakamātautia i te wā kotahi, ka pupuritia te huaputa Markdown (24h ā-waha / 7d whakamutua-whakahaere-whakahaere-whakahaere), ka tangohia te pūtake PDF i muri i te whakawāteatanga. Kāore i whakamahia mō te whakaakoranga. /privacy/ mō te kaupapahere katoa.
He — POST he 'draft' maha ki te /v1/document/pdf-to-markdown/. Ka hoki mai {markdown_url, ngā pātaka, te tirohanga, ngā tohu, te tiritiri_url}. Ko te mana whakahaere (sk-free-…) e hoatu ana i ngā tohu wātea 10K / mahina. He tauira a /api/ te kōpaka.
Ka whakaingoatia te wāteatanga mō ngā tohu 30,000
Ka waihanga tētahi pūkete wāteaKāore he kāri ā-pūtea e hiahiatia ana
He pēhea te whakawātea i tēnei utauta?