Structured Data Extraction Python Packages

llm-data-converter

Best open-source document to markdown converter for LLM training data. Convert PDF, Word, PowerPoint, Excel, images, URLs to clean markdown, JSON, HTML locally. Alternative to Unstructured, Docling, Marker, MarkItDown, MinerU, PaddleOCR, Tesseract

document-data-extractor

Best open-source document to markdown extractor for LLM training data. Convert PDF, Word, PowerPoint, Excel, images, URLs to clean markdown, JSON, HTML locally. Alternative to Unstructured, Docling, Marker, MarkItDown, MinerU, PaddleOCR, Tesseract

axetract

Low-Cost Cross-Domain Web Structured Information Extraction using specialized LoRA adapters.

financial-parser

A new package is designed to analyze financial news headlines and extract key structured information such as company names, financial targets, timeframes, and goal updates from text inputs. It simplif

text-snippet-summarizer

A new package facilitates extracting a concise, structured summary from user-provided news headlines or brief texts by utilizing pattern matching and LLM interactions. This tool aims to help researche

textract-io

A new package designed to facilitate structured extraction of key information from scientific or factual text inputs, enabling precise summaries, data extraction, or categorization based on user promp

dns-insight-extractor

This new package facilitates extracting structured insights from text-based content related to domain-specific issues, such as analyzing DNS blocking reports. Given unstructured text describing networ

iac-summarizer

A new package that analyzes technical arguments and extracts structured summaries from text discussions about infrastructure-as-code practices. It takes user-provided text (such as forum posts, articl

resume-yaml-builder

A new package that leverages language models to transform structured YAML data into well-formatted resume PDFs. Users provide their resume details in YAML format, and the package extracts key informat

validex

Simplifies the retrieval, extraction, and training of structured data from various unstructured sources.