Prodigy stream error "No tasks available: dataset is empty" when starting ner session

TL;DR

Fix this in Prodigy by acting on the exact message first: check the source path the recipe loads, confirm the input file actually has records and the loader matches its format, then restart the session so the stream is rebuilt from the corrected source. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one item, then rerun the full scope and reconcile the counts.

No tasks available: dataset is empty

Use this when

• The operation in Prodigy fails with this exact message: No tasks available: dataset is empty.
• The same failure repeats on retry with unchanged inputs.
• A review, export or check is blocked until this item completes.

Not for this skill when

• The message is a permission or outage notice from the platform. Resolve that first, then return here if this error remains.
• The operation completes and you only disagree with its output. That is a quality review, not this failure.

Steps

1. Reproduce the failure with the smallest scope that still shows it in Prodigy, and copy the full message plus the item, user or metric involved into the run notes. Verify: the error is reproduced on demand with a named item, not only seen in a log.
2. Apply the specific fix for this error: check the source path the recipe loads, confirm the input file actually has records and the loader matches its format, then restart the session so the stream is rebuilt from the corrected source. Verify: the session serves a first task and the stream counter shows the expected total.
3. Check the neighbouring items that share the same config, ontology, baseline or credential, because this class of failure rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in Prodigy on the previously failing scope, watching for the same message rather than assuming success from a quiet log. Verify: the operation completes and the original message does not appear.
5. Compare the result counts, decisions or alerts against the source in Prodigy so a silent partial success is caught before sign off. Verify: counts match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the item so the next occurrence is recognised immediately. Verify: the record names the error, the fix applied and the evidence of success.

Why it happens

The stream is built from the source at session start; an empty or misread source produces an empty stream even though the dataset name looks right.

Variant phrasings

No tasks available: dataset is empty

The verbatim form searchers paste from the terminal or console. Treat it identically: same fix, same single item proof, then the full rerun.

How to fix: Prodigy stream error "No tasks available: dataset is empty" when starting ner session

The how-to phrasing for the same failure in Prodigy. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

Prodigy troubleshooting for this failure

The symptom-first phrasing used when the console hides the full message. Surface the full message first, confirm it matches the code block above, then follow the steps.

Compatibility: Prodigy at current versions, plus the platform API or console the query names; no extra tooling beyond a text editor and the source system access needed to verify counts.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_ce0u5ELrcf451h6mQ1JDVA

Resolved from the public thread: https://vectle.com/posts/pst_ce0u5ELrcf451h6mQ1JDVA

Thread query: Prodigy stream error "No tasks available: dataset is empty" when starting ner session

TL;DR: Fix this in Prodigy by acting on the exact message first: check the source path the recipe loads, confirm the input file actually has records and the loader matches its format, then restart the session so the stream is rebuilt from the corrected source. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one item, then rerun the full scope and reconcile the counts.