API PDF.chat

Whakamāramatanga

Ko te API PDF.chat he whakawhitinga iti o te REST. Tuatahi koe POST He tuhinga tētahi tuhinga kia whakawātea ai, kia hoki mai ai te mahi me te kupu o te tuhinga me te whakawāteatanga i ia pātaka (tuhi, kāwai whakawhāiti, whakawhirinaki). POST Ka whakamātau te kaituhi ki ngā pātai ki taua mahi, ā, ka whiwhi whakautu i te take i roto i te tuhinga, ko ia e whakahua ana i te pātaka i puta mai ai. pending te tūnga e pā ana ki te pāpāho tae noa ki te done.

• URL taketake: https://pdf.chat
• Ko ngā tuhinga i roto: PDF, tae atu ki te Wā, PowerPoint, kupu, me ngā whakaahua (PNG, JPG, WEBP, GIF, BMP, TIFF)
• Chat o waho: Ka whakautua ki ngā whakahuapānga me ngā whakahuapātanga o te pātaka; ngā tāruatanga mā te wāhi mutunga o te hītori
• Ka whakamātautia te kupu i waho: txt, md, docx, pdf, csv, json
• Ka pānui te pūkaha: cpu (tere, ngā tuhinga tātai) me vlm (AI utu, tuhituhi, whakaritenga matatini, pāngarau)

Whakatuhi

Whakamau me tōna Ko te tohu API (Ki te kimia i runga i tōna Te pou ā-kōrero) hei pūmatua Taketake:

Authorization: Bearer YOUR_API_TOKEN

Ka taea hoki e koe te whakawhiti ?api_token=… Hei tohutoro uiui. Ka inetia te whakamahinga ki te taurite i te taumahatanga o te pātaka o tōna pūkete.

Whakahauhau i tētahi tuhinga

POST /api/v1/ocr/, Ka whakarewa te tātai maha.

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"

Ka hoki te mahi. Mō ngā pūranga ≤5-pātaka kua oti te mahi done me te kuputuhi; ka hoki mai ngā faila nui ake pending/processing, te pātai ki te wāhi mutunga o te tūnga.

{
  "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 } ] } ]
}

Ka whiwhi hua

GET /api/v1/ocr/<uuid>/, Ka pātata ki te pātai status He done rānei failed.

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

Whakahua i tētahi hanga

GET /api/v1/ocr/<uuid>/download/?format=md, Ka whakawātea te hua. format Ko tētahi o 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 me tētahi tuhinga

E pātai ana ki ngā pātai mo tētahi mahi oti. Ko ngā whakautu e whakatū ana anake i roto i te kupu whakawātea, ā, ka whakahuatia te pātaka pūtake. E hiahiatia ana he tohu kāwanatanga, he āhuahira chat te āhuahira kāwanatanga.

POST /api/v1/chat/<uuid>/, Te tinana 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?"}'

Ka hoki te karere āwhina ki tōna urupare me tētahi rārangi o ngā pātaka i whakahuatia:

{"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/, ki te whiwhi i te whakahua kōrero katoa mō tētahi mahi.

Ko ngā tauira waehere

• 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?"}'

Parameter

Whakarewa

Ko ia pātaka i whakamātauria he utu ā-pūtea (1/pātaka i runga i te taumata tere, nui ake i te utu). Ko ngā mahere utu e whakanui ana i ngā kōpaka pātaka-whakahaere me te tāpiri i te arotahi. Tirohia. Whakataurite.

Ko nga pātai e pā ana