Skip to main content

Generate vectorstore for RAG systems using an automated indexing pipeline

Project description

LS ELECTRIC / AX / AX Lab – Indexing Pipeline

이 프로젝트는 RAG(Retrieval-Augmented Generation) 기반 시스템에서 사용할 벡터스토어(Vectorstore)를 생성하는 인덱싱 파이프라인입니다. PDF 문서를 입력으로 받아 이미지 변환, 텍스트 추출, 문서 청킹, 임베딩 처리까지 자동화된 일련의 프로세스를 제공합니다.

주요 기능

  • [PDF -> PNG] PDF 문서의 고해상도 이미지(PNG) 변환
  • OCR 및 Markdown 변환
  • 계층적 문서 청킹 및 메타데이터 태깅
  • 임베딩 및 Vector DB 저장

예시

PDF -> PNG 변환

from lse_indexing_pipeline import convert_pdf_to_png

if __name__ == "__main__":
    convert_pdf_to_png(
        input_file_path="{your_pdf_path}",
        output_folder_dir="{your_output_dir}",
    )

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lse_indexing_pipeline-0.1.2.tar.gz (4.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lse_indexing_pipeline-0.1.2-py3-none-any.whl (5.9 kB view details)

Uploaded Python 3

File details

Details for the file lse_indexing_pipeline-0.1.2.tar.gz.

File metadata

  • Download URL: lse_indexing_pipeline-0.1.2.tar.gz
  • Upload date:
  • Size: 4.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.11

File hashes

Hashes for lse_indexing_pipeline-0.1.2.tar.gz
Algorithm Hash digest
SHA256 22e3cbef29b123207b24554142d18d1e638df586cbaf69e474462208caf8d6b2
MD5 c92b1c3361471aa67a73c808d372658f
BLAKE2b-256 e6297e75c820d7f22074b951546cfd6dd0f540d09283d39902778ae2ce3258f1

See more details on using hashes here.

File details

Details for the file lse_indexing_pipeline-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for lse_indexing_pipeline-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 5d73b1416f7824398caa69cd8208de4d241a0267020cbd407e3aa7a56783dbbb
MD5 2898b4a185db84a1d2c186752d3a4716
BLAKE2b-256 9692123492445bf4628b3dccda25043d47f04172a17c855546f911d1ef4c253e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page