Lewati ke konten

Panduan mulai cepat Python SDK

Instal software development kit (SDK) dari Python Package Index (PyPI):

Terminal window
pip install nextpdf

Buat klien untuk endpoint NextPDF Connect Anda:

from nextpdf import NextPDF
client = NextPDF(base_url="http://localhost:8080", api_key="your-key")
with open("document.pdf", "rb") as file:
blocks = client.ast.extract_cited_text(file.read())
for block in blocks:
page = block.citation.page_index
confidence = block.citation.confidence
print(f"[page {page}, confidence {confidence:.2f}] {block.text[:100]}")

Jika endpoint Anda tidak memerlukan kunci application programming interface (API), jangan sertakan api_key.

Command-line interface (CLI) dan alur kerja agen dapat membaca konfigurasi koneksi dari variabel lingkungan:

Terminal window
export NEXTPDF_BASE_URL=http://localhost:8080
export NEXTPDF_API_KEY=your-key

Di Windows PowerShell:

Terminal window
$env:NEXTPDF_BASE_URL = "http://localhost:8080"
$env:NEXTPDF_API_KEY = "your-key"

Tangani eksepsi dari SDK dan API saat Anda memanggil metode ekstraksi:

from nextpdf import NextPDF
from nextpdf.models.errors import NextPDFAPIError, NextPDFError, QuotaExceededError
client = NextPDF(base_url="http://localhost:8080", api_key="your-key")
try:
with open("document.pdf", "rb") as file:
blocks = client.ast.extract_cited_text(file.read())
except QuotaExceededError as error:
print(f"Rate limit hit: {error}")
except NextPDFAPIError as error:
print(f"API error {error.status_code}: {error}")
except NextPDFError as error:
print(f"SDK error: {error}")

Untuk berkas Portable Document Format (PDF) berukuran lebih dari 100 MB, gunakan CLI. Dengan cara ini, hasil dapat dialirkan tanpa memuat setiap blok hasil ekstraksi ke memori sekaligus.