chore: bump nltk from 3.9.4 to 3.10.0 in /api (#39503 )

Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: yunlu.wen <yunlu.wen@dify.ai>
2026-07-28 02:30:26 -07:00
4 changed files with 10 additions and 9 deletions
@@ -99,9 +99,9 @@ ENV VIRTUAL_ENV=/app/api/.venv
 COPY --from=packages --chown=dify:dify ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"

-# Download nltk data
 RUN mkdir -p /usr/local/share/nltk_data \
-    && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords')" \
+    && NLTK_DATA=/usr/local/share/nltk_data python -m nltk.downloader punkt_tab averaged_perceptron_tagger_eng stopwords \
+    && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; nltk.data.find('tokenizers/punkt_tab'); nltk.data.find('taggers/averaged_perceptron_tagger_eng'); nltk.data.find('corpora/stopwords')" \
    && chmod -R 755 /usr/local/share/nltk_data

 ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache
@@ -316,10 +316,10 @@ class OracleVector(BaseVector):
                    entities.append(current_entity)
            else:
                try:
-                    nltk.data.find("tokenizers/punkt")
+                    nltk.data.find("tokenizers/punkt_tab")
                    nltk.data.find("corpora/stopwords")
                except LookupError:
-                    raise LookupError("Unable to find the required NLTK data package: punkt and stopwords")
+                    raise LookupError("Unable to find the required NLTK data package: punkt_tab and stopwords")
                e_str = re.sub(r"[^\w ]", "", query)
                all_tokens = nltk.word_tokenize(e_str)
                stop_words = stopwords.words("english")
@@ -206,7 +206,7 @@ storage = [
 ############################################################
 # [ Tools ] dependency group
 ############################################################
-tools = ["cloudscraper>=1.2.71,<2.0.0", "nltk>=3.9.1,<4.0.0"]
+tools = ["cloudscraper>=1.2.71,<2.0.0", "nltk>=3.10.0,<4.0.0"]

 ############################################################
 # [ VDB ] workspace plugins — hollow packages under providers/vdb/*
@@ -1738,7 +1738,7 @@ storage = [
 ]
 tools = [
    { name = "cloudscraper", specifier = ">=1.2.71,<2.0.0" },
-    { name = "nltk", specifier = ">=3.9.1,<4.0.0" },
+    { name = "nltk", specifier = ">=3.10.0,<4.0.0" },
 ]
 trace-aliyun = [{ name = "dify-trace-aliyun", editable = "providers/trace/trace-aliyun" }]
 trace-all = [
@@ -4113,17 +4113,18 @@ wheels = [

 [[package]]
 name = "nltk"
-version = "3.9.4"
+version = "3.10.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "click" },
+    { name = "defusedxml" },
    { name = "joblib" },
    { name = "regex" },
    { name = "tqdm" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/74/a1/b3b4adf15585a5bc4c357adde150c01ebeeb642173ded4d871e89468767c/nltk-3.9.4.tar.gz", hash = "sha256:ed03bc098a40481310320808b2db712d95d13ca65b27372f8a403949c8b523d0", size = 2946864, upload-time = "2026-03-24T06:13:40.641Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/96/02/df4f105b28a7c16b0e41423bc09cf0f1b8a305df4ef0b10ca74a2e4c648c/nltk-3.10.0.tar.gz", hash = "sha256:4fbac1d98203cbcd1b5d94a2877fb822300072d80604a5e7fae49d2c5f84e8c1", size = 3089244, upload-time = "2026-07-08T02:39:13.562Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9d/91/04e965f8e717ba0ab4bdca5c112deeab11c9e750d94c4d4602f050295d39/nltk-3.9.4-py3-none-any.whl", hash = "sha256:f2fa301c3a12718ce4a0e9305c5675299da5ad9e26068218b69d692fda84828f", size = 1552087, upload-time = "2026-03-24T06:13:38.47Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/89/a0b0f35e2820d6a99d75ea1c11977ee6d5c9e6658eceb45b0c7620881faa/nltk-3.10.0-py3-none-any.whl", hash = "sha256:54ff84d4916d3ef127e8953bee0023f6a6b320b75d634a19e06ef056d3d244bf", size = 1716144, upload-time = "2026-07-08T02:39:09.753Z" },
 ]

 [[package]]