MeiliSearch/milli/Cargo.toml

147 lines
4.3 KiB
TOML
Raw Normal View History

[package]
name = "milli"
edition = "2021"
publish = false
version.workspace = true
authors.workspace = true
description.workspace = true
homepage.workspace = true
readme.workspace = true
# edition.workspace = true
license.workspace = true
[dependencies]
big_s = "1.0.2"
bimap = { version = "0.6.3", features = ["serde"] }
bincode = "1.3.3"
2024-07-08 18:09:12 +02:00
bstr = "1.9.1"
bytemuck = { version = "1.16.1", features = ["extern_crate_alloc"] }
2024-01-16 15:05:03 +01:00
byteorder = "1.5.0"
2024-07-25 16:02:14 +02:00
charabia = { version = "0.9.0", default-features = false }
concat-arrays = "0.1.2"
2024-07-08 18:09:12 +02:00
crossbeam-channel = "0.5.13"
deserr = "0.6.2"
either = { version = "1.13.0", features = ["serde"] }
2022-06-02 15:46:44 +02:00
flatten-serde-json = { path = "../flatten-serde-json" }
2022-03-14 17:00:53 +01:00
fst = "0.4.7"
fxhash = "0.2.1"
2022-10-04 11:29:39 +02:00
geoutils = "0.5.1"
2024-07-08 18:09:12 +02:00
grenad = { version = "0.4.7", default-features = false, features = [
"rayon", # TODO Should we keep this feature
"tempfile"
], git = "https://github.com/meilisearch/grenad", branch = "various-improvements" }
2024-07-08 18:09:12 +02:00
heed = { version = "0.20.3", default-features = false, features = [
"serde-json",
"serde-bincode",
"read-txn-no-tls",
2023-05-15 11:42:30 +02:00
] }
2024-07-08 18:09:12 +02:00
indexmap = { version = "2.2.6", features = ["serde"] }
2022-04-12 11:22:36 +02:00
json-depth-checker = { path = "../json-depth-checker" }
2022-03-14 17:00:53 +01:00
levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
lru = "0.12.3"
memchr = "2.5.0"
2024-07-08 18:31:15 +02:00
memmap2 = "0.9.4"
obkv = { git = "https://github.com/kerollmops/obkv", branch = "unsized-kvreader" }
2024-01-16 15:05:03 +01:00
once_cell = "1.19.0"
2024-07-08 18:09:12 +02:00
ordered-float = "4.2.1"
rayon = "1.10.0"
roaring = { version = "0.10.6", features = ["serde"] }
2024-07-08 18:31:15 +02:00
rstar = { version = "0.12.0", features = ["serde"] }
2024-07-08 18:09:12 +02:00
serde = { version = "1.0.204", features = ["derive"] }
2024-09-05 18:32:55 +02:00
serde_json = { version = "1.0.120", features = ["preserve_order", "raw_value"] }
2024-01-16 15:05:03 +01:00
slice-group-by = "0.3.1"
2023-05-15 11:42:30 +02:00
smallstr = { version = "0.3.0", features = ["serde"] }
2024-07-08 18:09:12 +02:00
smallvec = "1.13.2"
smartstring = "1.0.1"
2024-07-08 18:09:12 +02:00
tempfile = "3.10.1"
thiserror = "1.0.61"
time = { version = "0.3.36", features = [
2023-05-15 11:42:30 +02:00
"serde-well-known",
"formatting",
"parsing",
"macros",
] }
2024-07-10 13:46:24 +02:00
uuid = { version = "1.10.0", features = ["v4"] }
filter-parser = { path = "../filter-parser" }
# documents words self-join
2024-07-08 18:31:15 +02:00
itertools = "0.13.0"
2024-01-16 15:05:03 +01:00
csv = "1.3.0"
2024-07-08 18:31:15 +02:00
candle-core = { version = "0.6.0" }
candle-transformers = { version = "0.6.0" }
candle-nn = { version = "0.6.0" }
2024-06-13 17:47:44 +02:00
tokenizers = { git = "https://github.com/huggingface/tokenizers.git", tag = "v0.15.2", version = "0.15.2", default-features = false, features = [
2024-03-05 11:05:20 +01:00
"onig",
] }
2024-06-13 17:47:44 +02:00
hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls", default-features = false, features = [
"online",
] }
2024-07-08 18:09:12 +02:00
tiktoken-rs = "0.5.9"
liquid = "0.26.6"
2024-07-04 15:14:50 +02:00
rhai = { version = "1.19.0", features = ["serde", "no_module", "no_custom_syntax", "no_time", "sync"] }
arroy = "0.4.0"
2023-12-07 13:33:15 +01:00
rand = "0.8.5"
2024-01-23 09:42:48 +01:00
tracing = "0.1.40"
2024-07-08 18:09:12 +02:00
ureq = { version = "2.10.0", features = ["json"] }
url = "2.5.2"
2024-05-12 14:45:25 +02:00
rayon-par-bridge = "0.1.0"
[dev-dependencies]
2024-07-08 18:09:12 +02:00
mimalloc = { version = "0.1.43", default-features = false }
insta = "1.39.0"
maplit = "1.0.2"
md5 = "0.7.0"
2023-09-18 09:59:38 +02:00
meili-snap = { path = "../meili-snap" }
2023-05-15 11:42:30 +02:00
rand = { version = "0.8.5", features = ["small_rng"] }
[features]
2024-01-25 18:58:52 +01:00
all-tokenizations = [
"charabia/chinese",
"charabia/hebrew",
"charabia/japanese",
"charabia/thai",
"charabia/korean",
"charabia/greek",
"charabia/khmer",
"charabia/vietnamese",
]
2022-09-08 12:19:44 +02:00
# 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"]
2022-09-08 12:19:44 +02:00
# allow chinese specialized tokenization
chinese = ["charabia/chinese"]
2024-04-18 11:38:26 +02:00
chinese-pinyin = ["chinese", "charabia/chinese-normalization-pinyin"]
2022-09-08 12:19:44 +02:00
# allow hebrew specialized tokenization
hebrew = ["charabia/hebrew"]
# allow japanese specialized tokenization
japanese = ["charabia/japanese"]
2022-12-12 14:53:08 +01:00
japanese-transliteration = ["charabia/japanese-transliteration"]
# allow korean specialized tokenization
korean = ["charabia/korean"]
2022-09-08 12:19:44 +02:00
# allow thai specialized tokenization
thai = ["charabia/thai"]
2023-04-26 14:56:54 +02:00
# allow greek specialized tokenization
2023-04-26 14:58:32 +02:00
greek = ["charabia/greek"]
2023-10-26 17:01:10 +02:00
# allow khmer specialized tokenization
khmer = ["charabia/khmer"]
2024-01-07 21:27:29 +01:00
2024-04-30 14:30:23 +02:00
# allow vietnamese specialized tokenization
2024-01-25 18:58:52 +01:00
vietnamese = ["charabia/vietnamese"]
2024-04-30 14:30:23 +02:00
# force swedish character recomposition
swedish-recomposition = ["charabia/swedish-recomposition"]
2024-01-22 10:13:27 +01:00
# allow CUDA support, see <https://github.com/meilisearch/meilisearch/issues/4306>
2024-01-07 21:27:29 +01:00
cuda = ["candle-core/cuda"]