PDF.chat API
Upload PDF u chat miegħu mill-app tiegħek stess — jistaqsu mistoqsijiet u jiksbu tweġibiet ikkwotati għall-paġna, f'100 + lingwi.Mkejla għal kull paġna, l-ebda sorpriżi.
Ħarsa ġenerali
Il-PDF.chat API huwa interface REST żgħar. L-ewwel inti POST dokument biex jibilgħu dan u jiksbu lura xogħol mat-test tad-dokument u t-tqassim għal kull paġna (test, kaxxi bounding, kunfidenza). POST Xogħlijiet ta’ 5 paġni jew inqas jiġu rritornati inline; xogħlijiet akbar jiġu rritornati immedjatament b’link għall-paġna ta’ għajnuna, u xogħlijiet ta’ 10 paġni jew inqas jiġu rritornati inline; xogħlijiet akbar jiġu rritornati immedjatament b’link għall-paġna ta’ għajnuna, u pending status li inti poll sakemm done.
- URL bażiku:
https://pdf.chat - Dokumenti f': PDF, kif ukoll Word, PowerPoint, test, u immaġnijiet (PNG, JPG, WEBP, GIF, BMP, TIFF)
- Chat minn: tweġibiet b’ċitazzjonijiet ta’ paġni; tranżazzjonijiet permezz tal-punt aħħari tal-istorja
- Test ipproċessat barra:
txt,md,docx,pdf,csv,json - Magni tal-qari:
cpu(dokumenti stampati malajr) uvlm(premium AI, kitba bl-idejn, tqassim kumpless, matematika)
Awtentikazzjoni
Awtentika bil-password tiegħek Token tal-API (ssibha fuq il- paġna tal-kont) bħala Header tal-Bejjiegħ:
Authorization: Bearer YOUR_API_TOKEN
Tista' wkoll tgħaddi ?api_token=… L-użu jitkejjel kontra l-bilanċ tal-paġna tal-kont tiegħek.
Ippreżenta dokument
POST /api/v1/ocr/, upload tal-formola b’diversi partijiet.
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"
Jirritorna x-xogħol. Għal fajls ≤5-paġna huwa diġà done bit-test; fajls akbar jiġu lura pending/processing, poll l-endpoint status.
{
"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 } ] } ]
}
Ikseb riżultat
GET /api/v1/ocr/<uuid>/, poll sakemm status huwa done jew failed.
curl https://pdf.chat/api/v1/ocr/9f2c1b7e4a.../ \
-H "Authorization: Bearer YOUR_API_TOKEN"
Niżżel format
GET /api/v1/ocr/<uuid>/download/?format=md, jesportaw ir-riżultat. format huwa wieħed minn 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 b’dokument
Staqsi mistoqsijiet dwar xogħol lest. It-tweġibiet huma bbażati biss fit-test estratt u jikkwotaw il-paġna sors. Jeħtieġ token kont, il-karatteristika chat huwa kont-gated.
POST /api/v1/chat/<uuid>/, Korp 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?"}'
Jirritorna l-messaġġ assistent bit-tweġiba tiegħu u lista ta' paġni ċċitati:
{"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 $42…", "document_id": "9f2c1b7e4a…"}]
}}
GET /api/v1/chat/<uuid>/history/, iġib it-tranżmissjoni sħiħa tal-konversazzjoni għal xogħol.
Eżempji ta’ kodiċi
import requests, time
BASE = "https://pdf.chat/api/v1"
H = {"Authorization": "Bearer YOUR_API_TOKEN"}
# 1. Upload a PDF
with open("contract.pdf", "rb") as f:
job = requests.post(BASE + "/ocr/", headers=H, files={"file": f}).json()
# 2. Wait until it's ready to chat
while job["status"] in ("pending", "processing"):
time.sleep(2)
job = requests.get(f"{BASE}/ocr/{job['uuid']}/", headers=H).json()
# 3. Ask questions — every answer is cited to the page
ans = requests.post(f"{BASE}/chat/{job['uuid']}/", headers=H,
json={"message": "What is the termination notice period?"}).json()
print(ans["message"]["content"])
print(ans["message"]["citations"])
import fs from "fs";
const BASE = "https://pdf.chat/api/v1";
const H = { Authorization: "Bearer YOUR_API_TOKEN" };
// 1. Upload a PDF
const form = new FormData();
form.append("file", new Blob([fs.readFileSync("contract.pdf")]), "contract.pdf");
let job = await (await fetch(`${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?"}'
Parametri
| Qasam | Tip | Deskrizzjoni |
|---|---|---|
file | file | Meħtieġ. L-immaġni jew PDF biex tipproċessa. |
tier | string | cpu (default, veloċi/stampat) jew vlm (premium AI: kitba bl-idejn, tqassim, matematika). |
language | string | auto (default) jew kodiċi tal-lingwa (en, ch, ja, ar, …). |
tool | string | Għodda fakultattiva tal-bużżieqa (eż. summarize-pdf, ask-pdf) biex pre-frame l-chat għal dak il-kompitu. |
Żbalji & limiti
| Kodiċi | Tfisser |
|---|---|
400 | Ebda fajl, tip mhux appoġġjati, jew fajl kbir wisq. |
401 | Token tal-API nieqes jew invalidu. |
402 | Mingħajr paġni, il-limitu ta' kuljum/xahar b'xejn laħaq, jew l-ebda krediti. Il-korp jinkludi used/cap. |
404 | Job UUID ma nstabx. |
409 | Download mitlub qabel ix-xogħol lest. |
Kull paġna pproċessati spejjeż krediti (1/paġna fuq il-livell veloċi, aktar fuq premium). pjanijiet imħallsa jgħollu għal kull fajl paġna kapijiet u żid prijorità. prezzijiet.
Mistoqsijiet li jsiru ta' spiss
language=auto biex jiskopru, jew jgħaddu kodiċi speċifiku.