fix: Pin nltk version for sentence tokenizer (#8786)

* Pin nltk version for sentence tokenizer * Update pyproject.toml * Update haystack/components/preprocessors/sentence_tokenizer.py --------- Co-authored-by: David S. Batista <[email protected]>
deepset-ai · Jan 31, 2025 · 379711f · 379711f
1 parent 80575a7
commit 379711f
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/haystack/components/preprocessors/sentence_tokenizer.py b/haystack/components/preprocessors/sentence_tokenizer.py
@@ -9,7 +9,7 @@
 from haystack import logging
 from haystack.lazy_imports import LazyImport
 
-with LazyImport("Run 'pip install nltk'") as nltk_imports:
+with LazyImport("Run 'pip install nltk>=3.9.1'") as nltk_imports:
     import nltk
 
 logger = logging.getLogger(__name__)

diff --git a/pyproject.toml b/pyproject.toml
@@ -112,7 +112,7 @@ extra-dependencies = [
   "openpyxl",                         # XLSXToDocument
   "tabulate",                         # XLSXToDocument
 
-  "nltk", # NLTKDocumentSplitter
+  "nltk>=3.9.1", # NLTKDocumentSplitter
 
   # OpenAPI
   "jsonref",  # OpenAPIServiceConnector, OpenAPIServiceToFunctions