github/CodeSearchNet

Datasets, tools, and benchmarks for representation learning of code.

Archived
49
/ 100
Emerging

Provides 2 million (comment, code) function pairs across six languages with repository-level train/test splits to prevent data leakage, paired with a dual-encoder baseline model and NDCG evaluation metrics for semantic code search. Includes manually annotated relevance judgments for 99 queries across languages, enabling rigorous benchmarking of retrieval-based approaches. Integrates with Weights & Biases for experiment tracking and community leaderboard submission via containerized training pipelines.

2,417 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

2,417

Forks

408

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 31, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/github/CodeSearchNet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.