PDF.chat API

Àwọn Àkọ́gbègbè

PDF.chat API ní ojú-ìwé REST kékeré. Òjútó rẹ̀ POST Àkọsílẹ̀ láti fi pamọ́ sínú àti láti gba iṣẹ́ padà sínú àwọn àkọsílẹ̀ àti àwọn ojú-ìwé (àkọsílẹ̀, àwọn POST Àwọn ààyè lórí iṣẹ́ náà àti gba àwọn ààyè tí a dá nínú àkọsílẹ̀ náà, gbogbo wọn ní àwọn àkọsílẹ̀ ojú-ìwé tí wọn tì wa ní. Àwọn iṣẹ́ àwọn ojú-ìwé 5 àti àwọn tí kò ní ìbárá nínú àwọn iṣẹ́ nlà nígbà kan nípa pending ipo ti o bá fi àwọn àwọn ààyè pamọ́ done.

URL Ìdáràn: https://pdf.chat
Àwọn Àkọsílẹ̀ nínú: PDF, plus Word, PowerPoint, ọrọ, ati àwòrán (PNG, JPG, WEBP, GIF, BMP, TIFF)
Chat out: Àwọn àwọn
Àwọn àkọlé àwọn àkọlé txt, md, docx, pdf, csv, json
Àwọn ìṣàmúlò-ètò ìṣàfihàn: cpu (àkọ́lé àìpẹ́, àwọn àkọ́lé àìpíríǹtì) àti vlm (AI premium, kọ̀ọ̀kan, àwọn ààtò ìṣàfarawé, àwọn mátírika)

Àwọn Àmì-ìwé

Fi àwọn àmì-ìwé rẹ pamọ́ Àwọn àtòjọ-ètò API (wá o ní àwọn ààyè-iṣẹ́ rẹ Àwọn Àmì-ìwé Àwọn Àwọn Àkọ́lé) bí àwọn àkọlé àwọn àkọlé:

Authorization: Bearer YOUR_API_TOKEN

O lè fi pamọ́ ?api_token=… bí àwọn ààtò ìtàn. Àwọn ìlòjójútó ní pàtó láti gbọ́dọ̀ sí àwọn ojú-ìwé àwọn kọ́̀ǹpútà rẹ̀.

Fi àkọlé pamọ́

POST /api/v1/ocr/, Ìṣàfilọ́lẹ̀ àwọn fọọmu àwọn àwọn ààyè-iṣẹ́.

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"

Ń bọ́ iṣẹ́ padà. Fun àwọn fáìlì ojú-ìwé ≤5 o tí wa done pẹlú àkọ́lé; àwọn fáìlì nlà tí wọ́n sí pending/processing, wó àwọn ààtò ìtàn ìṣàfarawé.

{
  "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 } ] } ]
}

Gba àwọn àwọn àkóónú

GET /api/v1/ocr/<uuid>/, àwọn ààyè-iṣẹ́ status ní done tabi failed.

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

Àwọn ìṣàmúlò-ètò

GET /api/v1/ocr/<uuid>/download/?format=md, Ìjánu-ìtò format jẹ́ ọkan ninu 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 with a document

Ask questions about a finished job. Answers are grounded only in the extracted text and cite the source page. Requires an account token, the chat feature is account-gated.

POST /api/v1/chat/<uuid>/, Àwọn ààyè-iṣẹ́ {"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?"}'

Fi àkọlé àwòrán pamọ́ sí àwọn àgbèwọlé rẹ̀ àti àtòjọ àwọn ojú-ìwé tí a kọ̀ ní:

{"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/, gba àwọn àkọ́lé àwọn àkọ́lé fún iṣẹ́ kan.

Àwọn ààtòjú àwọn ìṣàmúlò-ètò

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?"}'

Àwọn Àtòjọ-ẹ̀yàn

Àwọn Ààyè	Àwọn Ìṣàmúlò-ètò	Àwọn Àkọ́lé
`file`	file	Tí a fẹ́. Àwòrán tàbí PDF láti ṣe ìṣàmúlò-ètò.
`tier`	string	`cpu` (òòró, ìṣàfarawé àwọn ààtòjútó) tàbí `vlm` (AI premium: ọwọ-itẹwe, oju-iwe, mathematics).
`language`	string	`auto` (pílẹ̀dà) tàbí ìṣàmúlò-ètò ìtàn (`en`, `ch`, `ja`, `ar`,...
`tool`	string	Àwọn àwọn àtòjọ-ẹ̀yàn àtòjọ-ẹ̀yàn (e.g. `summarize-pdf`, `ask-pdf`) lati fi fọọmu-ẹ̀yàn lọ́wọ́lọ́wọ́ chat fun iṣẹ́ náà.

Àwọn Àṣìṣe & Àwọn Ìgbà Ìgbà

Àwọn Àmì-ìwé	Ìtumọ̀
`400`	Kò ní fáìlì, irúfẹ́ tí a kò bá jẹ́, tàbí fáìlì tí o jú ìwọ̀n lọ.
`401`	Àwọn àyọkà API tí kò wà tàbí àwọn àyọkà API tí kò bá jẹ́.
`402`	Òkù àwọn ojú-ìwé, àwọn ìpamọ́ àwọn ojú-ìwé ọjọ́/óṣù, àti àwọn `used`/`cap`.
`404`	Kò rí iṣẹ́ UUID.
`409`	Àkọ́lé àwòrán

Àwọn ojú-ìwé ìṣàfarawé kọ̀ǹpútà (1/ ojú-ìwé nínú ìpelé ìsàlẹ̀-ilà, àwọn mìíràn nínú àwọn àwọn ìṣàmúlò-ilà. Àwọn àwọn ìṣàmúlò-ilà tí a fi pamọ́ ń fi àwọn ojú-ìwé àti àwọn ìṣàmúlò-ilà fáìlì kọ̀ǹpútà kọ̀ǹpútà pamọ́ pamọ́. Wò Ìṣàmúlò-ètò.

Àwọn Àtòjọ-ẹ̀yàn

Ṣẹ̀dá àwọn Àwọn Àmì-ìwé Àwọn Àwọn Àkọ́lé, àwọn àmì-ìwé rẹ̀ tí a fi hàn níbẹ̀ láti fi bọ́tìnì kọ́ọ̀kan hàn.

Ya, àwọn fáìlì àwọn ojú-ìwé 5 tàbí àwọn tí kò jú àwọn

Òjútó language=auto lati ṣàfihàn, tàbí fi àkóónú kan lọ́wọ́lọ́wọ́.

Àwọn ìṣàfilọ́lẹ̀ ní a ṣé nípa ìṣàfilọ́lẹ̀ àwọn ààtòjútó rẹ̀ nípa ìṣàfilọ́lẹ̀ àwọn ààtòjútó rẹ̀. A kò ráǹbára, kọ̀ọ̀kan, tàbí kọ́ọ̀kan àwọn àkọsílẹ̀ rẹ̀.

Àwọn ìlòjóò ní pàtó ojú-ìwé ní pàtó àwọn

O lè fi PNG, JPG, WEBP, GIF, BMP, TIFF, àti PDF ojú-ìwé àìdálẹ̀. Àwọn àwọn à

400 ni fáìlì tí kò wa, irúfẹ̀ tí kò bá jẹ́ ìdájú, tàbí fáìlì tí o jú ìwọ̀n lọ́wọ́lọ́wọ́; 401 fáìlì tí kò wa tàbí tokè tí kò bá jẹ́ òótọ́; 402 inú àwọn ojú-ìwé; 404 iṣẹ́ UUID tí a kò mọ́; àti 409 ìṣàmúlò-ètò tí a bí láti fi àwọn iṣẹ́ kù. Àwọn ẹ̀yàn àìpàdé ní àkọ́lé àwọn àmì-ìwé àìpàdé àìpàdé.

Àwọn àwọn àkóónú iṣẹ́ ní àwọn ìṣàmúlò-ètò, ìpele, ìtàn, àwọn àwọn ojú-ìwé, àti àwọn ààyè-iṣẹ́, àti àwọn àkọ́lé àti àwọn àmì-ìwé. Àwọn ojú-ìwé ààyè-iṣẹ́ náà ń pa ojú-ìwé fún àwọn ààyè-iṣẹ́ nínú àwọn àkọ́lé wọn, àwọn àwọn ààyè-iṣẹ́ àwọn

Ló cpu (ọ̀rọ̀ ìpèwọ̀n) fún ìṣàfihàn ààyè-iṣẹ́ àìdálẹ̀

Pass tool with a slug (for example summarize-pdf or ask-pdf) to pre-frame the chat for that task, so the assistant is tuned to summarize or answer questions about the document.

Àwọn fáìlì àwọn ojú-ìwé 5 tàbí àwọn tí kò jù lọ́wọ́lú nínú àwọn àkóónú POST. Àwọn fáìlì tí o jújú nígbà kan bí àwọn ààyè àti àwọn ìṣàfarawé, àtí ò fi GET /api/v1/ocr/ gbọ́<uuid>/ titi tí ipó náà bá jẹ́ ìṣẹ̀dà tàbí ìpàlẹ̀. Àwọn ìṣàmúlò-ètò tí a fi pamọ́ náà ń fi ojú-ìwé fún fáìlì kan.

API ní REST tí a tí gbọ́dọ̀ gbọ́dọ̀ lọ́wọ́lọ́wọ́, bẹ́ẹ̀ ní o tí n ṣiṣẹ́ nípa ìtàn wò nípa klìnẹ́tì HTTP, wòye àwọn àwọn ààyè Python, Node.js, àti cURL tí a tì fi pamọ́. Kò si SDK kan tí a fi pamọ́; àwọn à

PDF.chat API

Àwọn Àkọ́gbègbè

Àwọn Àmì-ìwé

Fi àkọlé pamọ́

Gba àwọn àwọn àkóónú

Àwọn ìṣàmúlò-ètò

Chat with a document

Àwọn ààtòjú àwọn ìṣàmúlò-ètò

Àwọn Àtòjọ-ẹ̀yàn

Àwọn Àṣìṣe & Àwọn Ìgbà Ìgbà

Àwọn Àtòjọ-ẹ̀yàn

Bawo ni mo ṣe lè gba tokè API?

Àwọn ààyè-iṣẹ́ àwọn ààyè-iṣẹ́

Àwọn ìrísí-lẹ́tà wo ní ìdájú?

Ó fi àwọn àkọsílẹ̀ mìí pamọ́?

Kini àwọn ìdájú àwọn ìdájú àti àwọn ìṣàmúlò-ètò?

Àwọn ìrísí-lẹ́tà ìṣàmúlò-ètò wo ní ìdájú?

Àwọn ìtumọ̀ àwọn àkóónú ìṣàmúlò-ètò náà?

Bawo ni àwọn ìṣàmúlò-ètò náà ṣe lè rí?

Nígbà ní mò óò lo tier=cpu lórí tier=vlm?

How do the tool and translate_to parameters work?

Ìgbà wo ní mò lè fi fáìlì kan ranṣẹ, àti bí a ṣè ǹṣé ìṣàfarawé iṣẹ́ nlà?

Ńlá nínú àwọn SDK̀ àìdálẹ̀?