meilisearch/milli/Cargo.toml

[package]
name = "milli"
edition = "2018"
publish = false

version.workspace = true
authors.workspace = true
description.workspace = true
homepage.workspace = true
readme.workspace = true
# edition.workspace = true
license.workspace = true

[dependencies]
bimap = { version = "0.6.3", features = ["serde"] }
bincode = "1.3.3"
bstr = "1.4.0"
bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
byteorder = "1.4.3"
charabia = { version = "0.8.5", default-features = false }
concat-arrays = "0.1.2"
crossbeam-channel = "0.5.8"
deserr = "0.6.0"
either = { version = "1.8.1", features = ["serde"] }
flatten-serde-json = { path = "../flatten-serde-json" }
fst = "0.4.7"
fxhash = "0.2.1"
geoutils = "0.5.1"
grenad = { version = "0.4.5", default-features = false, features = [
    "rayon",
    "tempfile",
] }
heed = { version = "0.20.0-alpha.9", default-features = false, features = [
    "serde-json",
    "serde-bincode",
    "read-txn-no-tls",
] }
indexmap = { version = "2.0.0", features = ["serde"] }
json-depth-checker = { path = "../json-depth-checker" }
levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
memmap2 = "0.7.1"
obkv = "0.2.0"
once_cell = "1.17.1"
ordered-float = "3.6.0"
rand_pcg = { version = "0.3.1", features = ["serde1"] }
rayon = "1.7.0"
roaring = "0.10.1"
rstar = { version = "0.11.0", features = ["serde"] }
serde = { version = "1.0.160", features = ["derive"] }
serde_json = { version = "1.0.95", features = ["preserve_order"] }
slice-group-by = "0.3.0"
smallstr = { version = "0.3.0", features = ["serde"] }
smallvec = "1.10.0"
smartstring = "1.0.1"
tempfile = "3.5.0"
thiserror = "1.0.40"
time = { version = "0.3.20", features = [
    "serde-well-known",
    "formatting",
    "parsing",
    "macros",
] }
uuid = { version = "1.3.1", features = ["v4"] }

filter-parser = { path = "../filter-parser" }

# documents words self-join
itertools = "0.11.0"

# profiling
puffin = "0.16.0"

# logging
log = "0.4.17"
logging_timer = "1.1.0"
csv = "1.2.1"
candle-core = { git = "https://github.com/huggingface/candle.git", version = "0.3.1" }
candle-transformers = { git = "https://github.com/huggingface/candle.git", version = "0.3.1" }
candle-nn = { git = "https://github.com/huggingface/candle.git", version = "0.3.1" }
tokenizers = { git = "https://github.com/huggingface/tokenizers.git", tag = "v0.14.1", version = "0.14.1", default_features = false, features = ["onig"] }
hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls", default_features = false, features = [
    "online",
] }
tokio = { version = "1.34.0", features = ["rt"] }
futures = "0.3.29"
reqwest = { version = "0.11.16", features = [
    "rustls-tls",
    "json",
], default-features = false }
tiktoken-rs = "0.5.7"
liquid = "0.26.4"
arroy = { git = "https://github.com/meilisearch/arroy.git", version = "0.1.0" }
rand = "0.8.5"

[dev-dependencies]
mimalloc = { version = "0.1.37", default-features = false }
big_s = "1.0.2"
insta = "1.29.0"
maplit = "1.0.2"
md5 = "0.7.0"
meili-snap = { path = "../meili-snap" }
rand = { version = "0.8.5", features = ["small_rng"] }

[features]
all-tokenizations = [
    "charabia/chinese",
    "charabia/hebrew",
    "charabia/japanese",
    "charabia/thai",
    "charabia/korean",
    "charabia/greek",
    "charabia/khmer",
]

# Use POSIX semaphores instead of SysV semaphores in LMDB
# For more information on this feature, see heed's Cargo.toml
lmdb-posix-sem = ["heed/posix-sem"]

# allow chinese specialized tokenization
chinese = ["charabia/chinese"]

# allow hebrew specialized tokenization
hebrew = ["charabia/hebrew"]

# allow japanese specialized tokenization
japanese = ["charabia/japanese"]
japanese-transliteration = ["charabia/japanese-transliteration"]

# allow korean specialized tokenization
korean = ["charabia/korean"]

# allow thai specialized tokenization
thai = ["charabia/thai"]

# allow greek specialized tokenization
greek = ["charabia/greek"]

# allow khmer specialized tokenization
khmer = ["charabia/khmer"]