shield_lock
金大哥
← 返回 Skill 列表
extension
分类: 数据与分析无需 API Key

LLM流水线的非结构化文档ETL

Unstructured 是一个开源文档处理库，可将 PDF、HTML、Office 文件、电子邮件和其他格式转换为结构化数据，以供下游 AI 工作流使用。它是提取、分块和预处理在嵌入、搜索或代理使用之前的一个实用入口层。

person作者: user_3c6cb52ehubcommunity
download下载资源包

LLM流水线的非结构化文档ETL

Unstructured is an open source document processing library that converts PDFs, HTML, Office files, emails, and other formats into structured data for downstream AI workflows. It is a practical intake layer for extraction, chunking, and preprocessing before embeddings, search, or agent use.

Prerequisites

bun, python, pip, uv, docker, go

Installation

Use the upstream install or setup path that matches your environment:

  • docker pull downloads.unstructured.io/unstructured-io/unstructured:latest
  • docker run -dt --name unstructured downloads.unstructured.io/unstructured-io/unstructured:latest
  • docker exec -it unstructured bash
  • make docker-build

Requirements and caveats from upstream:

  • <a href="https://github.com/1991513ccie-png/skills">https://pypi.python.org/pypi/unstructured/</a>
  • <a href="https://pypi.python.org/pypi/unstructured/">https://pypi.python.org/pypi/unstructured/</a>
  • <a href="https://pypi.python.org/pypi/unstructured/">![https://github.com/1991513ccie-png/skills)</a>

Basic usage or getting-started notes:

  • :eight_pointed_black_star: Quick Start

  • Run the library in a container or

  • Run the library in a container

  • Source: https://github.com/1991513ccie-png/skills

  • Extracted from upstream docs: https://raw.githubusercontent.com/Unstructured-IO/unstructured/HEAD/README.md

Documentation

  • https://unstructured-io.github.io/unstructured/installing.html#installation-with-conda-on-windows