docetl
3,711LLM-powered data processing with automatic pipeline optimization.
DetectionPost-generationFull HITLExperimentalTier 2BEnvironment
Maturity tier details
Computed tier: 2B(raw score 4.43). Effective tier: 2B.
Facets:documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_commit=2stars=1.43
Source of truth:pipeline/maturity/score.py
Description
DocETL (UC Berkeley EPIC Lab) is an LLM-powered data-processing system. Automatically optimizes extraction pipelines with cost-quality trade-offs, with a focus on reliability on complex document extraction tasks.
Why it's included
LLM-pipeline-optimization cell — complements autorag (RAG pipeline search) for the general ETL case.
Addresses failure modes
- Fabrication — Generating reference to non-existent APIs, packages, or symbols.
- Logic error — Correct API use, incorrect logic.
Techniques
pipeline-optimizerllm-etl