Bump nltk from 3.8.1 to 3.9.1 (#966)

* Bump nltk from 3.8.1 to 3.9.1

Bumps [nltk](https://github.com/nltk/nltk) from 3.8.1 to 3.9.1.
- [Changelog](https://github.com/nltk/nltk/blob/develop/ChangeLog)
- [Commits](https://github.com/nltk/nltk/compare/3.8.1...3.9.1)

---
updated-dependencies:
- dependency-name: nltk
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* Download punk_tab

* Semver

* Add missing installs

* Add missing installs

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>

.semversioner/next-release/patch-20240820202507768622.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Update to nltk 3.9.1"
+}

graphrag/index/bootstrap.py

@@ -20,8 +20,11 @@ def bootstrap():
         from nltk.corpus import wordnet as wn
 
         nltk.download("punkt")
+        nltk.download("punkt_tab")
         nltk.download("averaged_perceptron_tagger")
+        nltk.download("averaged_perceptron_tagger_eng")
         nltk.download("maxent_ne_chunker")
+        nltk.download("maxent_ne_chunker_tab")
         nltk.download("words")
         nltk.download("wordnet")
         wn.ensure_loaded()

poetry.lock

@@ -1204,6 +1204,7 @@ files = [
     {file = "fastparquet-2024.5.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5626fc72204001b7e82fedb4b02174ecb4e2d4143b38b4ea8d2f9eb65f6b000e"},
     {file = "fastparquet-2024.5.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:c8b2e86fe6488cce0e3d41263bb0296ef9bbb875a2fca09d67d7685640017a66"},
     {file = "fastparquet-2024.5.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:2a951106782d51e5ab110beaad29c4aa0537f045711bb0bf146f65aeaed14174"},
+    {file = "fastparquet-2024.5.0-cp312-cp312-win_amd64.whl", hash = "sha256:cd3473d3e299bfb04c0ac7726cca5d13ee450cc2387ee7fd70587ca150647315"},
     {file = "fastparquet-2024.5.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:47695037fdc534ef4247f25ccf17dcbd8825be6ecb70c54ca54d588a794f4a6d"},
     {file = "fastparquet-2024.5.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fc3d35ff8341cd65baecac71062e9d73393d7afda207b3421709c1d3f4baa194"},
     {file = "fastparquet-2024.5.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:691348cc85890663dd3c0bb02544d38d4c07a0c3d68837324dc01007301150b5"},
@@ -2633,13 +2634,13 @@ test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
 
 [[package]]
 name = "nltk"
-version = "3.8.1"
+version = "3.9.1"
 description = "Natural Language Toolkit"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "nltk-3.8.1-py3-none-any.whl", hash = "sha256:fd5c9109f976fa86bcadba8f91e47f5e9293bd034474752e92a520f81c93dda5"},
-    {file = "nltk-3.8.1.zip", hash = "sha256:1834da3d0682cba4f2cede2f9aad6b0fafb6461ba451db0efb6f9c39798d64d3"},
+    {file = "nltk-3.9.1-py3-none-any.whl", hash = "sha256:4fa26829c5b00715afe3061398a8989dc643b92ce7dd93fb4585a70930d168a1"},
+    {file = "nltk-3.9.1.tar.gz", hash = "sha256:87d127bd3de4bd89a4f81265e5fa59cb1b199b27440175370f7417d2bc7ae868"},
 ]
 
 [package.dependencies]
@@ -5164,4 +5165,4 @@ test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools",
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "9e60203deeb424d3269364106be5286b3b8cec2d4d8729e21a5eed41c6761bbc"
+content-hash = "657679cf3810b8c6d6b06be70113a9557193d131b8e8f903ce7672a0db09af57"

pyproject.toml

@@ -54,7 +54,7 @@ aiofiles = "^24.1.0"
 
 # LLM
 openai = "^1.37.1"
-nltk = "3.8.1"
+nltk = "3.9.1"
 tiktoken = "^0.7.0"
 
 # Data-Sci