Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/exegia/corpora-py/llms.txt

Use this file to discover all available pages before exploring further.

list_features() returns an alphabetically sorted list of feature names available in a corpus. You can narrow the results by node type (to see only features that appear on, say, word nodes) or by feature kind ("node" or "edge"). Use this tool after describe_corpus() to discover which feature names you can use in search templates or pass to describe_feature() and get_node_features().

Parameters

node_type
string
Filter the list to features that have at least one value on this node type (e.g. "word", "verse"). When omitted, features for all node types are included.
kind
string
Filter by feature kind. Accepted values are "node" (features stored on individual nodes) and "edge" (features stored on directed edges between nodes). When omitted, both kinds are returned.
limit
integer
Maximum number of feature names to return. Defaults to 50. Increase this if you need to see more names in one call.
corpus
string
Corpus name. When omitted, the currently active corpus is used.

Returns

A formatted string beginning with "Features:" followed by the matching feature names, one per line, indented by two spaces. When the total number of matching features exceeds limit, a (showing N of M) suffix is appended so you know more exist. Returns "Could not retrieve feature list from this corpus." if the corpus does not expose feature data.
Features:
  book
  chapter
  freq
  gloss
  lex
  pos
  verse
(showing 7 of 80)

Example

# List word-level features only, up to 10
result = list_features(node_type="word", limit=10)
print(result)
Expected output:
Features:
  freq
  gloss
  lex
  nu
  pdp
  pos
  sp
  st
  typ
  vbe
(showing 10 of 34)

Build docs developers (and LLMs) love