Project repository: https://github.com/lhoestq/duckdb-hf-extension
SET allow_extension_repositories = 'allowed';
CREATE OR REPLACE EXTENSION REPOSITORY hf_repo
WITH PREFIX 'https://hf.co/buckets/duckdb-extensions/builds/resolve';
INSTALL hf FROM hf_repo;
Read/write to Hugging Face buckets, datasets, models and spaces. Optimized with Xet.
LOAD hf FROM hf_repo;
SELECT * FROM 'hf://datasets/fka/prompts.chat/prompts.csv';
SELECT * FROM hf_ls('hf://buckets/commoncrawl/commoncrawl/crawl-data');
COPY (SELECT * FROM range(10) t(i)) TO 'hf://datasets/me/demo/out.parquet';
COPY (SELECT * FROM read_parquet('hf://datasets/me/demo/*.parquet'))
TO 'hf://datasets/me/demo/partitioned' (FORMAT PARQUET, PARTITION_BY (kind));
Login with the hf CLI:
hf auth login
Or pass a token manually:
CREATE SECRET (TYPE HUGGINGFACE, TOKEN 'hf_...');