This repository contains all the recipes that you can use with Chonkie to manage various documents, languages, and more.
Dataset Card
By Feyn, published under apache-2.0, revision bd588a8b1beb.
This repository contains all the recipes that you can use with Chonkie to manage various documents, languages, and more.
Usage
To use the recipes, you need to install chonkie with the hub feature, with the following command:
pip install "chonkie[hub]"
This would enable Hubie which is used internally to get the recipes from this repository. So, you can do things like use the from_recipe method to create a RecursiveChunker from a recipe.
from chonkie import RecursiveChunker
chunker = RecursiveChunker.from_recipe("markdown")
with open("example.md", "r") as f:
text = f.read()
chunks = chunker.chunk(text)
for chunk in chunks:
print(chunk)
The above code would read the example.md file and chunk it into smaller chunks using the markdown recipe.
Recipes
The recipes are stored in the recipes folder. Each recipe is a JSON file that contains the rules for the recipe.
Structure
recipes 56 rows
| Split | Rows | Size |
|---|---|---|
| train | 56 | 13.7 KB |
schemas 1 rows
| Split | Rows | Size |
|---|---|---|
| train | 1 | 693 B |
Details
- Repository
- feyninc/recipes
- Publisher
- Feyn
- Task category
- Not stated by the source
- Tags
- Not stated by the source
- Size category
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- bd588a8b1beb3b387ab999f1f86806e7fcea3dd8
- Last updated
- 2025-10-07
Files
62 files, 264.1 KB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pipelines/markdown.json | Data | 623 B | — |
| recipes/default_af.json | Data | 1.5 KB | — |
| recipes/default_am.json | Data | 1.5 KB | — |
| recipes/default_ar.json | Data | 1.4 KB | — |
| recipes/default_bg.json | Data | 1.5 KB | — |
| recipes/default_bn.json | Data | 1.5 KB | — |
| recipes/default_ca.json | Data | 1.5 KB | — |
| recipes/default_cs.json | Data | 1.5 KB | — |
| recipes/default_cy.json | Data | 1.5 KB | — |
| recipes/default_da.json | Data | 1.5 KB | — |
| recipes/default_de.json | Data | 1.5 KB | — |
| recipes/default_en.json | Data | 1.3 KB | — |
| recipes/default_es.json | Data | 1.6 KB | — |
| recipes/default_et.json | Data | 1.5 KB | — |
| recipes/default_fa.json | Data | 1.5 KB | — |
| recipes/default_fi.json | Data | 1.5 KB | — |
| recipes/default_fr.json | Data | 1.5 KB | — |
| recipes/default_ga.json | Data | 1.5 KB | — |
| recipes/default_gl.json | Data | 1.5 KB | — |
| recipes/default_he.json | Data | 1.5 KB | — |
| recipes/default_hi.json | Data | 1.4 KB | — |
| recipes/default_hr.json | Data | 1.5 KB | — |
| recipes/default_hu.json | Data | 1.5 KB | — |
| recipes/default_id.json | Data | 1.5 KB | — |
| recipes/default_is.json | Data | 1.5 KB | — |
| recipes/default_it.json | Data | 1.5 KB | — |
| recipes/default_jp.json | Data | 1.4 KB | — |
| recipes/default_kr.json | Data | 1.4 KB | — |
| recipes/default_lt.json | Data | 1.5 KB | — |
| recipes/default_lv.json | Data | 1.5 KB | — |
| recipes/default_mk.json | Data | 1.5 KB | — |
| recipes/default_ms.json | Data | 1.5 KB | — |
| recipes/default_mt.json | Data | 1.5 KB | — |
| recipes/default_ne.json | Data | 1.5 KB | — |
| recipes/default_nl.json | Data | 1.5 KB | — |
| recipes/default_no.json | Data | 1.5 KB | — |
| recipes/default_pl.json | Data | 1.5 KB | — |
| recipes/default_pt-BR.json | Data | 1.5 KB | — |
| recipes/default_pt.json | Data | 1.5 KB | — |
| recipes/default_ro.json | Data | 1.5 KB | — |
| recipes/default_ru.json | Data | 1.5 KB | — |
| recipes/default_sk.json | Data | 1.5 KB | — |
| recipes/default_sl.json | Data | 1.5 KB | — |
| recipes/default_sr.json | Data | 1.5 KB | — |
| recipes/default_sv.json | Data | 1.5 KB | — |
| recipes/default_sw.json | Data | 1.5 KB | — |
| recipes/default_ta.json | Data | 1.5 KB | — |
| recipes/default_te.json | Data | 1.5 KB | — |
| recipes/default_th.json | Data | 1.5 KB | — |
| recipes/default_tl.json | Data | 1.5 KB | — |
| recipes/default_tr.json | Data | 1.5 KB | — |
| recipes/default_uk.json | Data | 1.5 KB | — |
| recipes/default_ur.json | Data | 1.5 KB | — |
| recipes/default_vi.json | Data | 1.5 KB | — |
| recipes/default_zh.json | Data | 1.4 KB | — |
| recipes/default_zu.json | Data | 1.5 KB | — |
| recipes/markdown_en.json | Data | 1.5 KB | — |
| v1.schema.json | Data | 2.2 KB | — |
| README.md | Documentation | 7.8 KB | — |
| assets/logo_w_name.png | Other | 168.4 KB | e121c83d0aee |
| .gitattributes | Repository | 2.5 KB | — |
| .gitignore | Repository | 17 B | — |
License and Download
- License
- apache-2.0
- Access
- No access gate
Released by Feyn through its official repository on Hugging Face. Read the license.