DocETL
Open-source toolkit, built by the EPIC Data Lab at UC Berkeley, for creating LLM-powered pipelines that extract, transform, and link knowledge from unstructured documents.
spaCy
Industrial-strength Natural Language Processing (NLP) in Python
Categories
More in Extraction
View all tools
ExtractBench
A benchmark for schema-guided extraction from real enterprise documents. 370 documents, 4,869 pages, 67 document types, each with its own JSON Schema. Scored on value accuracy, completeness, and evidence.
K
Knowledge Graph Builder
Repository for building knowledge graphs from specific datasets using generative language model through ollama