{"repo":"Center-for-Applied-AI/delm","free":true,"listed":false,"github":"https://github.com/Center-for-Applied-AI/delm","clone":"git clone https://github.com/Center-for-Applied-AI/delm.git","description":"Data Extraction with Language Models","language":"Python","stars":12,"topics":["ai","data-extraction","data-science","information-extraction","llm"],"license":"MIT","category":"ai-agents","readme_excerpt":"Data Extraction with Language Models DELM is a Python toolkit for extracting structured data from unstructured text using language models. 📖 Full Documentation Features - Multiple input formats : TXT, HTML, MD, DOCX, PDF, CSV, Excel, Parquet, Feather - Flexible schemas : Simple key-value → nested objects → multiple schemas - Multiple LLM providers : OpenAI, Anthropic, Google, Groq, Together AI, Fireworks AI - Cost management : Automatic cost tracking, caching, and budget limits - Built for scale : Batch processing with parallel execution and checkpointing Installation Quick Start Define your extraction schema and extract structured data in just a few lines: Schema Types DELM supports three schema types for different extraction needs: Simple Schema Extract key-value pairs from text: Nested Schema Extract lists of structured objects: Multiple Schemas Extract multiple different schemas simultaneously: Supported Data Types Type Description Example ------ ------------- --------- string Text values \"Apple Inc.\" number Floating-point 150.5 integer Whole numbers 2024 boolean True/False true date Date strings \"2025-09-15\" [string] List of strings [\"oil\", \"gas\"] [number] List of numbers [100, 200] Advanced Features Custom Prompts Process CSV/Structured Data Cost Tracking & Limits Batch Processing Configuration Options For a complete list of configuration options, see the documentation. Common parameters: - provider : LLM provider ( \"openai\" , \"anthropic\" , \"google\" , etc.) - model : M","default_branch":null,"files":null,"tree":[],"storefront":"/r/Center-for-Applied-AI","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Center-for-Applied-AI/delm/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}