diff --git a/front/admin_ui/poetry.lock b/front/admin_ui/poetry.lock
index 1c7ac0f03..6bb5feb89 100644
--- a/front/admin_ui/poetry.lock
+++ b/front/admin_ui/poetry.lock
@@ -624,13 +624,13 @@ files = [
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -638,7 +638,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -654,19 +654,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1451,7 +1449,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/jobs/cache_maintenance/poetry.lock b/jobs/cache_maintenance/poetry.lock
index 0643c1c7f..7b24688d1 100644
--- a/jobs/cache_maintenance/poetry.lock
+++ b/jobs/cache_maintenance/poetry.lock
@@ -557,13 +557,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -571,7 +571,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -587,19 +587,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1078,7 +1076,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/jobs/mongodb_migration/poetry.lock b/jobs/mongodb_migration/poetry.lock
index d22b367dd..736f75289 100644
--- a/jobs/mongodb_migration/poetry.lock
+++ b/jobs/mongodb_migration/poetry.lock
@@ -557,13 +557,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -571,7 +571,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -587,19 +587,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1078,7 +1076,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/libs/libapi/poetry.lock b/libs/libapi/poetry.lock
index 358e6bd0a..1fd970014 100644
--- a/libs/libapi/poetry.lock
+++ b/libs/libapi/poetry.lock
@@ -564,13 +564,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -578,7 +578,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -594,19 +594,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1146,7 +1144,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/libs/libcommon/poetry.lock b/libs/libcommon/poetry.lock
index b68e9bed0..a27e354d2 100644
--- a/libs/libcommon/poetry.lock
+++ b/libs/libcommon/poetry.lock
@@ -593,13 +593,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -607,7 +607,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -623,19 +623,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -3938,4 +3936,4 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "3.9.18"
-content-hash = "473869a173375a14c8ea239be01e67bed43e038a92fba945e21bd52427e366dd"
+content-hash = "419bf28e25db5cb8f11b75b38723520b7cad3187fe6800cf690fb45610b62c4b"
diff --git a/services/admin/poetry.lock b/services/admin/poetry.lock
index 8f5615dfe..f0377ef69 100644
--- a/services/admin/poetry.lock
+++ b/services/admin/poetry.lock
@@ -571,13 +571,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -585,7 +585,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -601,19 +601,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1169,7 +1167,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/services/api/poetry.lock b/services/api/poetry.lock
index a8ec4a781..5f744de50 100644
--- a/services/api/poetry.lock
+++ b/services/api/poetry.lock
@@ -571,13 +571,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -585,7 +585,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -601,19 +601,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1188,7 +1186,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/services/rows/poetry.lock b/services/rows/poetry.lock
index a9dd66577..6dd726917 100644
--- a/services/rows/poetry.lock
+++ b/services/rows/poetry.lock
@@ -590,13 +590,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -604,7 +604,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -620,19 +620,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1207,7 +1205,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/services/search/poetry.lock b/services/search/poetry.lock
index a7e910719..ec0f59043 100644
--- a/services/search/poetry.lock
+++ b/services/search/poetry.lock
@@ -571,13 +571,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -585,7 +585,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -601,19 +601,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1247,7 +1245,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/services/sse-api/poetry.lock b/services/sse-api/poetry.lock
index 971201c6f..7ddf29534 100644
--- a/services/sse-api/poetry.lock
+++ b/services/sse-api/poetry.lock
@@ -571,13 +571,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -585,7 +585,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -601,19 +601,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1217,7 +1215,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/services/webhook/poetry.lock b/services/webhook/poetry.lock
index f50001efc..7e333924b 100644
--- a/services/webhook/poetry.lock
+++ b/services/webhook/poetry.lock
@@ -571,13 +571,13 @@ xml-validation = ["lxml (>=4,<6)"]
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -585,7 +585,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -601,19 +601,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1188,7 +1186,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}
diff --git a/services/worker/poetry.lock b/services/worker/poetry.lock
index 09052af4f..c7940b374 100644
--- a/services/worker/poetry.lock
+++ b/services/worker/poetry.lock
@@ -879,13 +879,13 @@ files = [
 
 [[package]]
 name = "datasets"
-version = "2.21.0"
+version = "3.0.1"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
-    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
+    {file = "datasets-3.0.1-py3-none-any.whl", hash = "sha256:db080aab41c8cc68645117a0f172e5c6789cbc672f066de0aa5a08fc3eebc686"},
+    {file = "datasets-3.0.1.tar.gz", hash = "sha256:40d63b09e76a3066c32e746d6fdc36fd3f29ed2acd49bf5b1a2100da32936511"},
 ]
 
 [package.dependencies]
@@ -893,7 +893,7 @@ aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
 fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
-huggingface-hub = ">=0.21.2"
+huggingface-hub = ">=0.22.0"
 librosa = {version = "*", optional = true, markers = "extra == \"audio\""}
 multiprocess = "*"
 numpy = ">=1.17"
@@ -909,19 +909,17 @@ tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "transformers", "transformers (>=4.42.0)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
-tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1648,7 +1646,7 @@ develop = true
 [package.dependencies]
 appdirs = "^1.4.4"
 cryptography = "^43.0.1"
-datasets = {version = "^2.21.0", extras = ["audio", "vision"]}
+datasets = {version = "3.0.1", extras = ["audio", "vision"]}
 environs = "^9.5.0"
 fsspec = {version = "2024.3.1", extras = ["s3"]}
 huggingface-hub = {version = "^0.24.6", extras = ["hf-transfer"]}