Import and Export Datasets

Move datasets in and out of Staso as CSVs, or synthesize new entries from existing ones.

import staso as st

st.init(api_key="...", workspace_slug="...")

count = st.dataset.upload_csv(ds.id, "./entries.csv", split="train")
path  = st.dataset.download_csv(ds.id, "./out.csv")

new_entries = st.dataset.generate(
    ds.id,
    count=50,
    prompt="Generate refund scenarios with amount > $500",
)

Upload CSV

count = st.dataset.upload_csv(
    dataset_id,
    "./entries.csv",
    split="train",
)

Column names in the CSV header must match existing dataset columns (create them first with st.dataset.create(..., columns=[...]) — see /docs/datasets/manage). Returns the number of entries inserted.

Download CSV

path = st.dataset.download_csv(
    dataset_id,
    "./out.csv",
    split=None,
)

Writes every entry to file_path and returns the resolved Path. Pass split="test" to export only one split.

Synthetic generation

generate asks Staso to synthesize new entries that match the dataset's schema and style.

entries = st.dataset.generate(
    dataset_id,
    count=50,
    prompt="Generate refund scenarios where the customer is upset and the amount is over $500",
    seed_entry_ids=["ent_abc", "ent_def"],
)

• count — how many new entries to generate. Default 10.
• prompt — natural-language instructions to steer the generator.
• seed_entry_ids — optional list of existing entries to ground the generator on. Use this to keep the synthetic batch on-distribution with your real data.

Generated rows are appended to the dataset and returned as a list of DatasetEntry.

Next

• Create and manage datasets
• Evaluate a dataset