pip install -U huggingface_hub

from huggingface_hub import hffs

repo_id = "allenai/c4"
path_in_repo = "en/c4-train.00000-of-01024.json.gz"

# Stream the file
with hffs.open(f"datasets/{repo_id}/{path_in_repo}", "r", compression="gzip") as f:
    print(f.readline())  # read only the first line
    # {"text":"Beginners BBQ Class Taking Place in Missoula!...}

import pandas as pd

repo_id = "YOUR_REPO_ID"
path_in_repo = "data.csv"

batch_size = 5

# Stream the file
with hffs.open(f"datasets/{repo_id}/{path_in_repo}") as f:
    for df in pd.read_csv(f, iterator=True, chunksize=batch_size):  # read 5 lines at a time
        print(len(df))  # 5

>>> curl -L https://huggingface.co/datasets/fka/awesome-chatgpt-prompts/resolve/main/prompts.csv | head -n 5
"act","prompt"
"An Ethereum Developer","Imagine you are an experienced Ethereum developer tasked with creating...
"SEO Prompt","Using WebPilot, create an outline for an article that will be 2,000 words on the ...
"Linux Terminal","I want you to act as a linux terminal. I will type commands and you will repl...
"English Translator and Improver","I want you to act as an English translator, spelling correct...

>>> curl -r 40-88 -L https://huggingface.co/datasets/fka/awesome-chatgpt-prompts/resolve/main/prompts.csv
Imagine you are an experienced Ethereum developer

>>> export HF_TOKEN=hf_xxx
>>> curl -H "Authorization: Bearer $HF_TOKEN" -L https://huggingface.co/...

import pyarrow.parquet as pq

repo_id = "HuggingFaceFW/finewiki"
path_in_repo = "data/enwiki/000_00000.parquet"

# Stream the Parquet file row group per row group
with pq.ParquetFile(f"hf://datasets/{repo_id}/{path_in_repo}") as pf:
    for row_group_idx in range(pf.num_row_groups):
        row_group_table = pf.read_row_group(row_group_idx)
        df = row_group_table.to_pandas()

use std::sync::Arc;
use object_store::path::Path;
use object_store_opendal::OpendalStore;
use opendal::services::Huggingface;
use opendal::Operator;
use parquet::arrow::async_reader::ParquetObjectReader;
use parquet::arrow::ParquetRecordBatchStreamBuilder;
use futures::TryStreamExt;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let repo_id = "HuggingFaceFW/finewiki";
    let path_in_repo = Path::from("data/enwiki/000_00000.parquet");
    let offset = 0;
    let limit = 10;

    let builder = Huggingface::default().repo_type("dataset").repo_id(repo_id);
    let operator = Operator::new(builder)?.finish();
    let store = Arc::new(OpendalStore::new(operator));
    let reader = ParquetObjectReader::new(store, path_in_repo.clone());
    let batch_stream =
        ParquetRecordBatchStreamBuilder::new(reader).await?
            .with_offset(offset as usize)
            .with_limit(limit as usize)
            .build()?;
    let results = batch_stream.try_collect::<Vec<_>>().await?;
    println!("Read {} batches", results.len());
    Ok(())
}