PDF.chat API

Forbhreathnú

Is é an API PDF.chat comhéadan REST beag. An chéad tú POST doiciméad a ionghabháil é agus a fháil ar ais post le téacs an doiciméid agus miondealú in aghaidh an leathanaigh (téacs, boscaí teorann, muinín). POST ceisteanna i gcoinne an phost agus freagraí bunaithe sa doiciméad a fháil, gach ceann acu ag lua an leathanach a tháinig sé as.Poist de 5 leathanach nó níos lú ar ais inlíne; poist níos mó ar ais láithreach le pending stádas go bhfuil tú poll go dtí done.

• URL bunaidh: https://pdf.chat
• Cáipéisí i: PDF, chomh maith le Word, PowerPoint, téacs, agus íomhánna (PNG, JPG, WEBP, GIF, BMP, TIFF)
• Chat amach: freagraí le lua leathanaigh; tras-scríbhinní tríd an gcríochphointe stair
• Téacs próiseáilte amach: txt, md, docx, pdf, csv, json
• Inneall léitheoireachta: cpu (doiciméid tapa, clóite) agus vlm (AI préimhe, lámhscríbhinn, leagan amach casta, matamaitic)

Fíordheimhniú

Fíordheimhnigh le do phasfhocal Comhartha API (aimsigh é ar do leathanach cuntais) mar cheanntásc Sealbhóra:

Authorization: Bearer YOUR_API_TOKEN

Is féidir leat pas a fháil freisin ?api_token=… mar pharaiméadar iarratais. Déantar úsáid a thomhas i gcoinne iarmhéid leathanach do chuntais.

Cuir cáipéis isteach

POST /api/v1/ocr/, uaslódáil foirm ilpháirtí.

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"

Fill an jab. I gcás comhaid ≤5 leathanach tá sé ann cheana done leis an téacs; comhaid níos mó teacht ar ais pending/processing, poll an stádas pointe deiridh.

{
  "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 } ] } ]
}

Faigh toradh

GET /api/v1/ocr/<uuid>/, poll go dtí status is done nó failed.

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

Íosluchtaigh formáid

GET /api/v1/ocr/<uuid>/download/?format=md, onnmhairiú an toradh. format Is é ceann de 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 le doiciméad

Cuir ceisteanna faoi jab críochnaithe. Ní bhíonn freagraí bunaithe ach ar an téacs asbhainte agus luaitear an leathanach foinseach. Tá comhartha cuntais de dhíth, tá an ghné chat teoranta do chuntais.

POST /api/v1/chat/<uuid>/, Corp JSON {"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?"}'

Fillfidh sé seo an teachtaireacht chúntair lena freagra agus liosta de leathanaigh luaite:

{"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/, tras-scríbhinn iomlán an chomhrá a fháil le haghaidh poist.

Samplaí de chód

• Python
• Node.js
• cURL

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?"}'

Paraiméadair

Earráidí agus teorainneacha

Cosnaíonn gach leathanach a phróiseáiltear creidmheasanna (1/leathanach ar an leibhéal tapa, níos mó ar phréimh). Ardaíonn pleananna íoctha uasteorainneacha leathanaigh in aghaidh an chomhaid agus cuireann siad tosaíocht leis. praghsáil.

Ceisteanna Coitianta