explosion/prodigy-openai-recipes
✨ Bootstrap annotation with zero- & few-shot learning via OpenAI GPT-3
ArchivedProvides Prodigy recipes that combine OpenAI's GPT-3 predictions with human-in-the-loop curation to efficiently build gold-standard datasets for NER and other tasks. Uses Jinja2 prompt templates with optional few-shot examples that can be iteratively refined, batching API requests while displaying raw model outputs alongside Prodigy's annotation interface. **Note: This repository is archived; functionality has been integrated into Prodigy's core distribution and superseded by spacy-llm support.**
322 stars. No commits in the last 6 months.
Stars
322
Forks
26
Language
Python
License
—
Category
Last pushed
Aug 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/explosion/prodigy-openai-recipes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/langfun
OO for LLMs
tanaos/artifex
Small Language Model Inference, Fine-Tuning and Observability. No GPU, no labeled data needed.
vulnerability-lookup/VulnTrain
A tool to generate datasets and models based on vulnerabilities descriptions from @Vulnerability-Lookup.
DataScienceUIBK/HintEval
HintEval💡: A Comprehensive Framework for Hint Generation and Evaluation for Questions
microsoft/LMChallenge
A library & tools to evaluate predictive language models.