Skip to content
PlaidCloud

Text NLP AI

Description

Section titled “Description”

The Text NLP AI step runs one of five per-row NLP tasks over a text column, each as a batch of structured (forced tool-use) LLM calls: Named Entity Recognition, POS Tagging, Summary, Zero-shot Classification, and Key/Value Extraction. It runs as a managed PlaidCloud job (like ML: Train Model and the LLM Step), so it does not compete with the rest of the workflow for resources.

Because every task is a real LLM call, results are not bit-for-bit reproducible between runs — see Non-Determinism.

Configuration

Section titled “Configuration”
  • Source / Output tables — the input table and the table the results are written to.
  • Text Column (field) — the column each task reads.
  • Task (task) — one of ner, pos, summary, zeroshot, keyvalue.
  • Language (language) — the text’s language, passed to the model. Defaults to en.
  • LLM Connection (llm_connection_id) — an Anthropic LLM connection. Leave blank to use the workspace default.
  • Model (llm_model) — leave blank to use the connection’s default model.
  • Temperature (temperature) — optional sampling temperature. See Non-Determinism: current-generation models ignore it.
  • Batch Size (batch_size) — rows sent per LLM call, 1 to 500. Defaults to 25. A batch whose response is truncated is split in half and retried rather than losing rows.

Tasks

Section titled “Tasks”

Two tasks return one output row per input row (row-preserving); three return zero or more rows per input row and carry the source’s identifier columns (id_columns) onto each one (row-exploding).

Task Fan-out Output columns Task-specific fields
Named Entity Recognition (ner) Row-exploding entity_text, entity_type Entity Types (entity_types) — the allowed type list. Defaults to people, organizations, locations, dates, quantities if left blank.
POS Tagger (pos) Row-exploding token, pos (universal POS tag, for example NOUN, VERB, ADJ) None.
Summary (summary) Row-preserving summary Summary Length (summary_length) — maximum sentences, 1 to 20. Defaults to 3.
Zero-shot Classification (zeroshot) Row-preserving label, score (0 to 1) Label Field (label_field) — the source column holding each row’s candidate labels; without it the model has nothing to choose from. Multi-Label (multi) — allow more than one label per row (joined with , ) instead of picking the single best.
Key/Value Pairs (keyvalue) Row-exploding key, value Key Field (key_field) — the source column holding each row’s candidate keys to extract; leave blank to let the model find keys freely. Fuzzy (fuzzy) — match candidate keys loosely instead of exactly.

ID Columns (id_columns) carry identifying columns from the source table onto every output row of a row-exploding task, so you can trace an extracted entity or pair back to its source record. A configured ID column that collides with a task’s own output column name (for example naming an ID column entity_type on an ner task) is rejected when the step runs, not when it’s saved.

Non-Determinism (LLM-Backed Results)

Section titled “Non-Determinism (LLM-Backed Results)”

Every task is a real call to an LLM, so results can vary between runs even with identical input — there is no bit-for-bit guarantee, and this is expected, not a bug.

Temperature exposes a further wrinkle: current-generation models (Opus 4.7+, Sonnet 5+, Fable) reject an explicit sampling temperature outright. If you set one, the step tries it once; the first rejection is detected, the run falls back to the model’s own server default for the rest of the batches, and the step’s result carries a one-time informational note rather than failing. Leaving Temperature blank (the default) skips this round-trip entirely and is the recommended setting on current models.

Section titled “Related”
  • ML: Train Model — fit a model rather than call an LLM per row.
  • LLM Step — a free-form agentic LLM call with scoped read/write project access, rather than one of these five fixed per-row tasks.
  • Alteryx Conversion Matrix — Named Entity Recognition, POS Tagger, Text Summary, Zero-shot Text Classification, and Key/Value Pairs all convert to this step.