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.

get_text_formats() shows every text encoding format registered in a corpus and renders a short preview of each using the corpus’s first three words. Use it to discover which format names you can pass as the fmt argument to search() and get_passages(). Different formats may offer original-script text, transliterations, plain transcriptions, or morphological representations depending on the corpus.

​
Parameters

​
corpus
string
Corpus name. When omitted, the currently active corpus is used. Use list_corpora() to see available names.

​
Returns

A formatted string that begins with "Available text formats:" followed by one entry per format. Each entry shows the format name on one line and a sample: preview indented below it. The preview is the rendered text of the first three words in the corpus for that format, shown as a Python-style quoted string. Returns "Text formats unavailable for this corpus." if the corpus does not expose format information, or "No text formats defined." if the format dictionary is empty.

​
Example

result = get_text_formats(corpus="BHSA")
print(result)
Expected output: 
Available text formats:
  text-orig-full
    sample: 'בְּרֵאשִׁ֖ית בָּרָ֣א אֱלֹהִ֑ים'
  text-trans-plain
    sample: 'In beginning created God'
  text-phono-full
    sample: 'bərēšîṯ bārāʾ ʾĕlōhîm'

Build docs developers (and LLMs) love

Get started for freeTalk to us