PDF.chat API

Wepu PDF na chat na ya site na ngwa gị - jụọ ajụjụ ma nweta azịza ndị akọwapụtara na peeji, na asụsụ 100 +. Mepụtara na peeji, enweghị ihe ịga nke ọma.

Nlekọta

The PDF.chat API bụ a obere REST interfaịlụ. First ị POST Dọkumenti iji banye ya nakwa nweta ọrụ na ngwe nke dọkumenti ahụ nakwa n'ihuakwụkwọ ọbụla (ngwe, bọ́tị̀nụ̀ banye, n'aka). Mgbe ahụ ị ga-eme ya POST ajụjụ na-emegide na ọrụ na-enweta azịza n'ime akwụkwọ, ọ bụla na-ekwu na peeji nke ọ na-abịa site. ọrụ nke 5 peeji ma ọ bụ na-adịghị na-agbake inline; nnukwu ọrụ na-agbake n'oge na-adịghị na a pending ọnọdụ ị na-enyocha ruo mgbe done.

  • Ebe URL: https://pdf.chat
  • Dọkumenti na: PDF, nakwa Wụsọ, Powerpoint, ngwe, na inyogo (PNG, JPG, WEBP, GIF, BMP, TIFF)
  • Chat n'ime: Ndesịta azịza na ihuakwụkwọ n'ime; n'ime
  • ngwe ahụ émepụtara: txt, md, docx, pdf, csv, json
  • Ngụnye engine: cpu (n'ụzọ nkịtị, dócètị̀ mbipụta) na vlm (AI premium, handwriting, complex layout, mathematics)

Nkwenye

Nkwenye na Token API (nweta ya na Ihu ebentanet) dịka ihenhọrọ nke elu:

Authorization: Bearer YOUR_API_TOKEN

I nwere ike ịga ?api_token=… dịka paramita nchọgharị. Oji a na-emezigharị n'ebe n'ime ihuakwụkwọ akaụntụ gị.

Dọkumenti ọfụụ

POST /api/v1/ocr/, Ńkwádò multipart

curl -X POST https://pdf.chat/api/v1/ocr/ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -F "file=@invoice.pdf" \
  -F "tier=vlm" \
  -F "language=auto"

Na-eziga ọrụ ahụ. Maka ≤5-ihuakwụkwọ faịlụ ọ bụ nke ahụ done na ngwe; faịlụ ndị dị ukwuu na-abịa n'ihu pending/processing, pụọ́ n'ókèókè nke ọnọdụ ngwụcha.

{
  "uuid": "9f2c1b7e4a...",
  "status": "done",
  "tier": "vlm",
  "language": "auto",
  "page_count": 1,
  "mean_confidence": 0.98,
  "text": "INVOICE\nAcme Corp\nTotal: 215.00 USD",
  "markdown": "# INVOICE\n\n**Acme Corp** ...",
  "pages": [ { "index": 0, "text": "...", "blocks": [ { "text": "...", "bbox": [x0,y0,x1,y1], "confidence": 0.98 } ] } ]
}

Wepụta nsonaazụ

GET /api/v1/ocr/<uuid>/, pịa ruo mgbe status bụ done ma ọ bụ failed.

curl https://pdf.chat/api/v1/ocr/9f2c1b7e4a.../ \
  -H "Authorization: Bearer YOUR_API_TOKEN"

Bubata usoroiheomume

GET /api/v1/ocr/<uuid>/download/?format=md, wepụ ihenhọrọ ahụ. format otu n'ime txt, md, docx, pdf, csv, json.

curl -L "https://pdf.chat/api/v1/ocr/9f2c1b7e4a.../download/?format=docx" \
  -H "Authorization: Bearer YOUR_API_TOKEN" -o result.docx

Chat na dọkumenti

Nwere ajụjụ banyere ọrụ e mechara. Ajụjụ ndị ahụ bụ naanị n'ime ngwe ahụ e wepụtala ma ọ bụ n'ime ihuakwụkwọ isi. Ekwesịrị akaụntụ token, chat ihenhọrọ bụ akaụntụ-gated.

POST /api/v1/chat/<uuid>/, JSON body {"message": "your question"}.

curl -X POST https://pdf.chat/api/v1/chat/9f2c1b7e4a.../ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"message": "What is the invoice total and due date?"}'

Na-eziga ozi ndịna na-enye ya nzaghachi na ndesịta nke ihuakwụkwọ ndị ahụ:

{"conversation": "a1b2…", "message": {
   "role": "assistant",
   "content": "The total is $42, due on March 3 (p. 1).",
   "citations": [{"page": 1, "cited_text": "The invoice total is $42…", "document_id": "9f2c1b7e4a…"}]
}}

GET /api/v1/chat/<uuid>/history/, Wepụta n'ime

Nhazi kood

import requests, time

BASE = "https://pdf.chat/api/v1"
H = {"Authorization": "Bearer YOUR_API_TOKEN"}

# 1. Upload a PDF
with open("contract.pdf", "rb") as f:
    job = requests.post(BASE + "/ocr/", headers=H, files={"file": f}).json()

# 2. Wait until it's ready to chat
while job["status"] in ("pending", "processing"):
    time.sleep(2)
    job = requests.get(f"{BASE}/ocr/{job['uuid']}/", headers=H).json()

# 3. Ask questions — every answer is cited to the page
ans = requests.post(f"{BASE}/chat/{job['uuid']}/", headers=H,
    json={"message": "What is the termination notice period?"}).json()
print(ans["message"]["content"])
print(ans["message"]["citations"])
import fs from "fs";

const BASE = "https://pdf.chat/api/v1";
const H = { Authorization: "Bearer YOUR_API_TOKEN" };

// 1. Upload a PDF
const form = new FormData();
form.append("file", new Blob([fs.readFileSync("contract.pdf")]), "contract.pdf");
let job = await (await fetch(`${BASE}/ocr/`, { method: "POST", headers: H, body: form })).json();

// 2. Wait until it's ready to chat
while (["pending", "processing"].includes(job.status)) {
  await new Promise(r => setTimeout(r, 2000));
  job = await (await fetch(`${BASE}/ocr/${job.uuid}/`, { headers: H })).json();
}

// 3. Ask questions — every answer is cited to the page
const ans = await (await fetch(`${BASE}/chat/${job.uuid}/`, {
  method: "POST", headers: { ...H, "Content-Type": "application/json" },
  body: JSON.stringify({ message: "What is the termination notice period?" })
})).json();
console.log(ans.message.content, ans.message.citations);
# 1. Upload a PDF
curl -X POST https://pdf.chat/api/v1/ocr/ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -F "file=@contract.pdf"

# 2. Ask questions (use the uuid from step 1) — answers cited to the page
curl -X POST https://pdf.chat/api/v1/chat/UUID/ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"message": "What is the termination notice period?"}'

Paramita

_ÒkèỤdịNdesịta ozi ndị ahụ
filefileEkwesịrị ya. Inyogo mọọbụ PDF a ga-ewepụ.
tierstringcpu (dìfọ́ọ̀ltụ̀, n'ihi na/pịa) mọọbụ vlm (premium AI: handwriting, layout, mathematics).
languagestringauto (dìfọ́ọ̀ltụ̀) mọọbụ koodị asụsụ (en, ch, ja, ar,...
toolstringSlug tùlè nke n'aka (eg. summarize-pdf, ask-pdf) ka pre-frame the chat maka na ọrụ.

Ndehie na nkwụsị

_ỌdịdịNkọwa
400Faịlụ ọbụla, ụdị a na-akwadoghị, mọọbụ faịlụ dị ukwuu.
401Enweghị ma ọ bụ token API ọfụụ.
402N'ime ihuakwụkwọ, n'ụbọchị/ụbọchị ọbụla n'ime ọnwa, ọbụla n'ime kredit. Ogo na-agụnye used/cap.
404Ọrụ UUID achọpụtaghị.
409Nbudata achọrọ tupú ọrụ ahụ gwụchaa.

Ihu ebe ọbụla na-ejikwa ego kredit (1/ihu ebe n'ime ọsọ ọsọ, karịa na prímáị̀m). Nhazi ego na-eweta ihenhọrọ ihuakwụkwọ na-echekwa na-egbakwunye n'ime faịlụ. Gụọ price.

Ajụjụ ndị a na-ajụkarị

Kewapụta akaụntụ ọbụla na mepee gị Ihu ebentanet, token gị egosipụtara ebe ahụ na bọtịn ndebata.

Ya, faịlụ ndị ahụ nke 5 peeji ma ọ bụ karịa na-eziga nsonaazụ zuru ezu n'ime n'ime nzaghachi POST, yabụ enweghị polling chọrọ maka ọtụtụ inyogo na PDFs n'oge.

N'elu 100, gụnyere Latin, CJK, Arabic, Cyrillic na Indian scripts. Jiri language=auto iji chọpụta, mọọbụ banye koodị pụrụ iche.

Nbudata a na-eme ya naanị iji zaa ajụjụ gị nakwa ka a wepụ ya n'ụzọ nkịtị. Anyị anaghị ere, akwado, ma ọ bụ zụlite na dọkumenti gị.

Ọrụ a na-emezigharị n'ime ibe n'ime akaụntụ gị: ozi ndị a na-asị na ha enweghị aha na-enweta n'ime ụbọchị IP, akaụntụ n'efu na-abịa n'ime ọnwa, na-eji ego ego na-akwụ ụgwọ na-eji ego na-akwụ ụgwọ na-arị elu na-abịa n'ime faịlụ peeji nke na n'ime ihe n'ime. Mgbe ị na-apụ ị ga-enweta 402 na-eji na n'ime ihe n'ime ahụ.

I nwere ike iziga PNG, JPG, WEBP, GIF, BMP, TIFF, na multi-page PDF. Nhazi ahụ a ga-ebubata dịka txt, md, docx, pdf (n'enwe ike ịchọgharị), csv, mọọbụ json site na nbudata ngwụcha-ebe ahụ n'ụdị parameter.

400 bụ faịlụ echeghị ama, ụdị a na-akwadoghị ya, mọọbụ faịlụ dị ukwuu; 401 bụ faịlụ echeghị ama mọọbụ token a na-enweghị isi; 402 n'ime ihuakwụkwọ; 404 bụ ọrụ UUID a na-amaghị ama; na 409 bụ mbubata achọrọ tupú ọrụ ahụ gwụ. Nchegbu ahụ gụnyere ozi n'ime.

Ọrụ ọbjektị na ọnọdụ, tiiri, asụsụ, page_count, na mean_confidence, nakwa ngwe zuru ezu na mọọduụ. Ihu ndị ahụ arọisụ na-ewepụ ihuakwụkwọ ọbụla n'ime blọọgụ na ngwe ha, bọ́ọ̀tụ̀ọ̀tụ̀ (bbox), nakwa n'ime-blọọgụ nkwenye.

Jiri cpu (dìfọ́ọ̀ltụ̀) maka nghọta n'ụzọ

Kpụga ngwaọrụ na slug (dịka ọmụmaatụ summarize-pdf mọọbụ ask-pdf) ka ọbụla chat pụta n'ime ihenhọrọ ahụ, ka onyenhọrọ ahụ wee kọwaa ma ọ bụ zaa ajụjụ banyere dọkumenti ahụ.

Faịlụ nke 5 ihuakwụkwọ mọọbụ ihe na-erughị ya na-ebuli n'ime n'ime POST nzaghachi. Faịlụ ndị dị ukwuu na-ebuli n'ime nkeji dịka na-echere mọọbụ na-arụ ọrụ, na ị na-ebuli GET /api/v1/ocr/<uuid>/ ruo mgbe ọnọdụ ahụ e mechara ma ọ bụ e mehieela. Nhazi ndị a na-akwụ ụgwọ na-ebuga ihenhọrọ nke ibe faịlụ ọbụla.

API bụ REST dị mfe site na HTTPS, yabụ ọ na-arụ ọrụ site na asụsụ ọ bụla na HTTP kliịntị, hụ Python, Node.js, na cURL ihe atụ n'elu. Enweghị SDK iji wụnye; ụfọdụ ụzọ nke standard HTTP koodu bụ ihe niile ịchọrọ.