diff --git a/README.md b/README.md
index 37086d53209b370aa5d6d979668ba978bea8e215..9f66f334db4a2b7a3869031ba3dcfae61e7f7103 100644
--- a/README.md
+++ b/README.md
@@ -142,6 +142,8 @@ Our utterance vector space also integrates with [Pinecone](https://github.com/au
 
 ### Community
 
+Dimitrios Manias, Ali Chouman, Abdallah Shami, [Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration](https://arxiv.org/abs/2404.15869), IEEE GlobeCom 2024
+
 Julian Horsey, [Semantic Router superfast decision layer for LLMs and AI agents](https://www.geeky-gadgets.com/semantic-router-superfast-decision-layer-for-llms-and-ai-agents/), Geeky Gadgets
 
 azhar, [Beyond Basic Chatbots: How Semantic Router is Changing the Game](https://medium.com/ai-insights-cobet/beyond-basic-chatbots-how-semantic-router-is-changing-the-game-783dd959a32d), AI Insights @ Medium
diff --git a/poetry.lock b/poetry.lock
index 9b5761a539e4cc8613d27a609524681a337008ad..1b4125e3829874e2a60595031fadb25dac46b148 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1404,13 +1404,13 @@ files = [
 
 [[package]]
 name = "huggingface-hub"
-version = "0.23.2"
+version = "0.22.2"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "huggingface_hub-0.23.2-py3-none-any.whl", hash = "sha256:48727a16e704d409c4bb5913613308499664f22a99743435dc3a13b23c485827"},
-    {file = "huggingface_hub-0.23.2.tar.gz", hash = "sha256:f6829b62d5fdecb452a76fdbec620cba4c1573655a8d710c1df71735fd9edbd2"},
+    {file = "huggingface_hub-0.22.2-py3-none-any.whl", hash = "sha256:3429e25f38ccb834d310804a3b711e7e4953db5a9e420cc147a5e194ca90fd17"},
+    {file = "huggingface_hub-0.22.2.tar.gz", hash = "sha256:32e9a9a6843c92f253ff9ca16b9985def4d80a93fb357af5353f770ef74a81be"},
 ]
 
 [package.dependencies]
@@ -1423,16 +1423,16 @@ tqdm = ">=4.42.1"
 typing-extensions = ">=3.7.4.3"
 
 [package.extras]
-all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
 cli = ["InquirerPy (==0.3.4)"]
-dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
 fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
 hf-transfer = ["hf-transfer (>=0.1.4)"]
 inference = ["aiohttp", "minijinja (>=1.0)"]
 quality = ["mypy (==1.5.1)", "ruff (>=0.3.0)"]
 tensorflow = ["graphviz", "pydot", "tensorflow"]
 tensorflow-testing = ["keras (<3.0)", "tensorflow"]
-testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
+testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
 torch = ["safetensors", "torch"]
 typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
 
@@ -3997,18 +3997,18 @@ test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,
 
 [[package]]
 name = "transformers"
-version = "4.41.2"
+version = "4.40.2"
 description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
 optional = true
 python-versions = ">=3.8.0"
 files = [
-    {file = "transformers-4.41.2-py3-none-any.whl", hash = "sha256:05555d20e43f808de1ef211ab64803cdb513170cef70d29a888b589caebefc67"},
-    {file = "transformers-4.41.2.tar.gz", hash = "sha256:80a4db216533d573e9cc7388646c31ed9480918feb7c55eb211249cb23567f87"},
+    {file = "transformers-4.40.2-py3-none-any.whl", hash = "sha256:71cb94301ec211a2e1d4b8c8d18dcfaa902dfa00a089dceca167a8aa265d6f2d"},
+    {file = "transformers-4.40.2.tar.gz", hash = "sha256:657b6054a2097671398d976ad46e60836e7e15f9ea9551631a96e33cb9240649"},
 ]
 
 [package.dependencies]
 filelock = "*"
-huggingface-hub = ">=0.23.0,<1.0"
+huggingface-hub = ">=0.19.3,<1.0"
 numpy = ">=1.17"
 packaging = ">=20.0"
 pyyaml = ">=5.1"
@@ -4021,15 +4021,17 @@ tqdm = ">=4.27"
 [package.extras]
 accelerate = ["accelerate (>=0.21.0)"]
 agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"]
-all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"]
+all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"]
 audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
 codecarbon = ["codecarbon (==1.2.0)"]
 deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"]
-deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
-dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
-dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"]
-dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
-flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)"]
+deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
+dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"]
+dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+docs = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"]
+docs-specific = ["hf-doc-builder"]
+flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"]
 flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
 ftfy = ["ftfy"]
 integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"]
@@ -4039,7 +4041,7 @@ natten = ["natten (>=0.14.6,<0.15.0)"]
 onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
 onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
 optuna = ["optuna"]
-quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"]
+quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"]
 ray = ["ray[tune] (>=2.7.0)"]
 retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
 sagemaker = ["sagemaker (>=2.31.0)"]
@@ -4048,16 +4050,16 @@ serving = ["fastapi", "pydantic", "starlette", "uvicorn"]
 sigopt = ["sigopt"]
 sklearn = ["scikit-learn"]
 speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
-testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "parameterized", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
-tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
-tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
+tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
 tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
 timm = ["timm"]
 tokenizers = ["tokenizers (>=0.19,<0.20)"]
 torch = ["accelerate (>=0.21.0)", "torch"]
 torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
 torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"]
-torchhub = ["filelock", "huggingface-hub (>=0.23.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"]
+torchhub = ["filelock", "huggingface-hub (>=0.19.3,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"]
 video = ["av (==9.2.0)", "decord (==0.6.0)"]
 vision = ["Pillow (>=10.0.1,<=15.0)"]
 
@@ -4228,4 +4230,4 @@ vision = ["pillow", "torch", "torchvision", "transformers"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.13"
-content-hash = "ea02ac49c6a0107091cc76153249bece31def22b7d16758c9c024b78d47a9418"
+content-hash = "17f2d76c59c4cb39899f69fe1e2242933a5747cfceb24a77a024d0cae0da1b3f"
diff --git a/pyproject.toml b/pyproject.toml
index dbf4785fc6f87e4760b117252cc8927ffef39bc1..88e515e82f09dc0edc0cc2f99767248c7d43e2b4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -43,7 +43,7 @@ boto3 = { version = "^1.34.98", optional = true }
 
 [tool.poetry.extras]
 hybrid = ["pinecone-text"]
-local = ["torch", "transformers", "tokenizers", "llama-cpp-python"]
+local = ["torch", "transformers", "tokenizers", "huggingface-hub", "llama-cpp-python"]
 pinecone = ["pinecone-client"]
 vision = ["torch", "torchvision", "transformers", "pillow"]
 processing = ["matplotlib"]
diff --git a/semantic_router/encoders/zure.py b/semantic_router/encoders/zure.py
index df2bf858aa32578e4751fac90d698e4db111f84b..55b2a40bc8508b2b7f296598165f59a298619490 100644
--- a/semantic_router/encoders/zure.py
+++ b/semantic_router/encoders/zure.py
@@ -1,8 +1,9 @@
 import os
 from time import sleep
-from typing import List, Optional
+from typing import List, Optional, Union
 
 import openai
+from openai._types import NotGiven
 from openai import OpenAIError
 from openai.types import CreateEmbeddingResponse
 
@@ -13,6 +14,7 @@ from semantic_router.utils.logger import logger
 
 class AzureOpenAIEncoder(BaseEncoder):
     client: Optional[openai.AzureOpenAI] = None
+    dimensions: Union[int, NotGiven] = NotGiven()
     type: str = "azure"
     api_key: Optional[str] = None
     deployment_name: Optional[str] = None
@@ -28,6 +30,7 @@ class AzureOpenAIEncoder(BaseEncoder):
         api_version: Optional[str] = None,
         model: Optional[str] = None,  # TODO we should change to `name` JB
         score_threshold: float = 0.82,
+        dimensions: Union[int, NotGiven] = NotGiven(),
     ):
         name = deployment_name
         if name is None:
@@ -38,6 +41,8 @@ class AzureOpenAIEncoder(BaseEncoder):
         self.azure_endpoint = azure_endpoint
         self.api_version = api_version
         self.model = model
+        # set dimensions to support openai embed 3 dimensions param
+        self.dimensions = dimensions
         if self.api_key is None:
             self.api_key = os.getenv("AZURE_OPENAI_API_KEY")
             if self.api_key is None:
@@ -89,7 +94,9 @@ class AzureOpenAIEncoder(BaseEncoder):
         for j in range(3):
             try:
                 embeds = self.client.embeddings.create(
-                    input=docs, model=str(self.model)
+                    input=docs,
+                    model=str(self.model),
+                    dimensions=self.dimensions,
                 )
                 if embeds.data:
                     break
diff --git a/tests/unit/encoders/test_clip.py b/tests/unit/encoders/test_clip.py
index ebbb80e50c8833fd5923599a2474b9dcc09f13f0..de997e36deb3c22349fb2f8eeba58878b112fe26 100644
--- a/tests/unit/encoders/test_clip.py
+++ b/tests/unit/encoders/test_clip.py
@@ -5,7 +5,7 @@ from PIL import Image
 
 from semantic_router.encoders import CLIPEncoder
 
-test_model_name = "hf-internal-testing/tiny-random-CLIPModel"
+test_model_name = "aurelio-ai/sr-test-clip"
 clip_encoder = CLIPEncoder(name=test_model_name)
 embed_dim = 64
 
diff --git a/tests/unit/encoders/test_huggingface.py b/tests/unit/encoders/test_huggingface.py
index 7c17f98f4e2cea17205a7543e577cb56b763a1af..f14c7a685a497c4fbb7a6afca4c2f8f85c355007 100644
--- a/tests/unit/encoders/test_huggingface.py
+++ b/tests/unit/encoders/test_huggingface.py
@@ -5,7 +5,7 @@ import pytest
 
 from semantic_router.encoders.huggingface import HuggingFaceEncoder
 
-test_model_name = "hf-internal-testing/tiny-bert"
+test_model_name = "aurelio-ai/sr-test-huggingface"
 encoder = HuggingFaceEncoder(name=test_model_name)
 
 
diff --git a/tests/unit/encoders/test_vit.py b/tests/unit/encoders/test_vit.py
index 72d01b349bc83a0b824e2f2f746d29c0553c94ce..64f605e4720df8c3e9942eaec06ae192a4a37ce8 100644
--- a/tests/unit/encoders/test_vit.py
+++ b/tests/unit/encoders/test_vit.py
@@ -5,7 +5,7 @@ from PIL import Image
 
 from semantic_router.encoders import VitEncoder
 
-test_model_name = "hf-internal-testing/tiny-random-vit"
+test_model_name = "aurelio-ai/sr-test-vit"
 vit_encoder = VitEncoder(name=test_model_name)
 embed_dim = 32