AI Terminology Extraction tool
The AI Terminology Extraction tool sends each block's source text to a configured LLM provider and asks it to return notable terms, each with a short definition and domain. The extracted entries are recorded on the block's properties as a terminology list. Blocks whose source is empty are skipped, and blocks with no terms found are left unchanged.
Because the tool calls an external model, it requires provider credentials. An optional subject domain can be supplied to bias extraction toward that field (for example medical, legal, or technology terminology). The results are candidate terms intended for review and curation into a termbase, not an authoritative glossary.
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
apiKey | string | API key for the AI provider | |
domain | string | Subject domain for terminology extraction (e.g. medical legal technology) | |
model | string | AI model name | |
provider | string | anthropic | AI provider |
Configure these parameters interactively and copy the flow-step YAML on the Tool Reference.
Examples
Extract domain-specific terminology
Bias extraction toward a particular subject area.
provider: anthropic domain: medical
Use a local Ollama model
Run extraction against a locally hosted model.
provider: ollama model: llama3
Processing notes
Operates on blocks; blocks with empty source text are skipped.
Blocks are processed in parallel by default for throughput.
Limitations
Requires AI provider credentials and makes an external API call per block.
Extracted terms are model output and should be reviewed before being treated as authoritative.
Operates on source text only.
← Back to the Tool Reference