Add turkish normalization

This commit is contained in:
ManyTheFish 2024-09-25 11:03:17 +02:00
parent efdc5739d7
commit e9580fe619
3 changed files with 9 additions and 1 deletions

View File

@ -66,5 +66,8 @@ khmer = ["milli/khmer"]
vietnamese = ["milli/vietnamese"] vietnamese = ["milli/vietnamese"]
# force swedish character recomposition # force swedish character recomposition
swedish-recomposition = ["milli/swedish-recomposition"] swedish-recomposition = ["milli/swedish-recomposition"]
# force german character recomposition # allow german tokenization
german = ["milli/german"] german = ["milli/german"]
# allow turkish normalization
turkish = ["milli/turkish"]

View File

@ -154,6 +154,7 @@ khmer = ["meilisearch-types/khmer"]
vietnamese = ["meilisearch-types/vietnamese"] vietnamese = ["meilisearch-types/vietnamese"]
swedish-recomposition = ["meilisearch-types/swedish-recomposition"] swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
german = ["meilisearch-types/german"] german = ["meilisearch-types/german"]
turkish = ["meilisearch-types/turkish"]
[package.metadata.mini-dashboard] [package.metadata.mini-dashboard]
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip" assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip"

View File

@ -108,6 +108,7 @@ all-tokenizations = [
"charabia/vietnamese", "charabia/vietnamese",
"charabia/swedish-recomposition", "charabia/swedish-recomposition",
"charabia/german-segmentation", "charabia/german-segmentation",
"charabia/turkish",
] ]
# Use POSIX semaphores instead of SysV semaphores in LMDB # Use POSIX semaphores instead of SysV semaphores in LMDB
@ -146,5 +147,8 @@ german = ["charabia/german-segmentation"]
# force swedish character recomposition # force swedish character recomposition
swedish-recomposition = ["charabia/swedish-recomposition"] swedish-recomposition = ["charabia/swedish-recomposition"]
# allow turkish specialized tokenization
turkish = ["charabia/turkish"]
# allow CUDA support, see <https://github.com/meilisearch/meilisearch/issues/4306> # allow CUDA support, see <https://github.com/meilisearch/meilisearch/issues/4306>
cuda = ["candle-core/cuda"] cuda = ["candle-core/cuda"]