[package]
edition = "2024"
name = "chonkier"
version = "0.0.2"
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "🦛 Chonkie, now in Rust 🦀: No-nonsense, ultra-fast, ultra-light chunking library"
readme = "README.md"
license = "Apache-2.0"
[features]
all = [
"json",
"tokenizers",
"tiktoken",
]
json = ["dep:serde_json"]
tiktoken = ["dep:tiktoken-rs"]
tokenizers = ["dep:tokenizers"]
[lib]
name = "chonkier"
path = "src/lib.rs"
[[example]]
name = "rayon_recursive_bench"
path = "examples/rayon_recursive_bench.rs"
[[example]]
name = "recursive_chunker"
path = "examples/recursive_chunker.rs"
[[example]]
name = "recursive_chunker_json"
path = "examples/recursive_chunker_json.rs"
[[example]]
name = "token_chunker"
path = "examples/token_chunker.rs"
[[bench]]
name = "character_tokenizer"
path = "benches/character_tokenizer.rs"
[[bench]]
name = "hf_tokenizer"
path = "benches/hf_tokenizer.rs"
[[bench]]
name = "main"
path = "benches/main.rs"
harness = false
[[bench]]
name = "recursive_chunker"
path = "benches/recursive_chunker.rs"
[[bench]]
name = "sentence_chunker"
path = "benches/sentence_chunker.rs"
[[bench]]
name = "token_chunker"
path = "benches/token_chunker.rs"
[dependencies.lru]
version = "0.14.0"
[dependencies.rayon]
version = "1.7.0"
[dependencies.serde]
version = "1.0"
features = ["derive"]
[dependencies.serde_json]
version = "1.0.140"
optional = true
[dependencies.tiktoken-rs]
version = "0.6.0"
optional = true
[dependencies.tokenizers]
version = "0.21.1"
features = ["http"]
optional = true
[dev-dependencies.criterion]
version = "0.5"
[dev-dependencies.serde_json]
version = "1.0"
[dev-dependencies.tiktoken-rs]
version = "0.6.0"
[dev-dependencies.tokenizers]
version = "0.21.1"