PDF.chat API

Kufotokozera

The PDF.chat API ndi REST m'dera laling'ono. POST alemba pa bokosi la nkhani kuti ayambe kulowa mkati mwake ndipo apeza ntchito yopitanso ndi mawu a nkhaniyo ndi kugawa kwa tsamba (mawu, mabokosi ozungulira, kukhulupilira). POST Mafunso otsutsa ntchitoyo ndi kupeza mayankho ochokera mu ndondomeko, aliyense kutchulidwa tsamba linachokera. Ntchito za 5 masamba kapena ochepa kubwezera inline; zikuluzikulu ntchito kubwezera mofulumira ndi pending khalidwe kuti inu poll mpaka done.

• Base URL: https://pdf.chat
• Mabuku mu: PDF, kuphatikizapo Word, PowerPoint, malemba ndi zithunzi (PNG, JPG, WEBP, GIF, BMP, TIFF)
• Chat kunja: mayankho ndi tsamba zitsanzo; transcripts mwa kutsatira mbiri endpoint
• Kusintha kwa mawu txt, md, docx, pdf, csv, json
• Kuwerenga injini: cpu (mosavuta, zosindikizidwa docs) ndi vlm (premium AI, kulemba, zophweka layout, mathematics)

Kutsimikizira

Kutsimikizira ndi API token (kupeza izo pa tsamba la akaunti) monga Bearer header:

Authorization: Bearer YOUR_API_TOKEN

Mukhozanso kupita ?api_token=… Kugwiritsa ntchito kumawerengedwa motsutsana ndi akaunti yanu ya akaunti ya tsamba.

Kutumiza fayilo

POST /api/v1/ocr/, multipart form upload.

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"

Kubwerera ntchito. Kwa ≤5-tsamba owona izo kale done ndi malemba; zikuluzikulu mafayilo abwerera pending/processing, poll khalidwe endpoint.

{
  "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 } ] } ]
}

Kupeza zotsatira

GET /api/v1/ocr/<uuid>/, poll until status ndi done kapena failed.

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

Kutsitsa mtundu

GET /api/v1/ocr/<uuid>/download/?format=md, kugulitsa zotsatira. format ndi mmodzi wa 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 ndi chidziwitso

Pitani mafunso pa ntchito yomaliza. Mayankho amachokera pa mawu ochokera m'mawu ochokera ndi kulemba tsamba lochokera. Amafuna akaunti yofunikira, chat inali akaunti yofunikira.

POST /api/v1/chat/<uuid>/, Mtundu wa 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?"}'

Kubwerera mnzake uthenga ndi yankho lake ndi mnda wa masamba anatchula:

{"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/, GET: GET kulandira zonse kulankhulana transcript kwa ntchito.

Kodi chitsanzo

• 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?"}'

Ma parameters

Mavuto & mipaka

Patsamba lililonse lomwe limatha kuchitidwa, ndalama zolipira zimagulitsidwa (1 / tsamba panthawi yothamanga, zambiri pa premium). Malamulo olipira amawonjezera masamba a tsamba la fayilo ndi kuwonjezera kufunika. Kugulitsa.

Mafunso ofunsidwa nthawi zambiri