From 9567f55e47168c82a4528adf07b7e6465eaac030 Mon Sep 17 00:00:00 2001
From: Bereket Terefe <bereket.terefe@tabiya.org>
Date: Thu, 11 Jun 2026 19:56:36 +0300
Subject: [PATCH] fix: update CI for tests to exclude torch as it isnt used and
 is breaking CI (ENOSPACE) [deploy dev]

---
 .github/workflows/backend-ci.yml |   9 +-
 .github/workflows/main.yml       |   8 +-
 backend/nel/poetry.lock          | 148 +++++++++++++++----------------
 backend/nel/pyproject.toml       |   6 +-
 4 files changed, 91 insertions(+), 80 deletions(-)

diff --git a/.github/workflows/backend-ci.yml b/.github/workflows/backend-ci.yml
index 2de96b7..4e568cf 100644
--- a/.github/workflows/backend-ci.yml
+++ b/.github/workflows/backend-ci.yml
@@ -47,7 +47,14 @@ jobs:
         run: poetry install --no-root
 
       - name: Install dependencies
-        run: poetry install --no-interaction ${{ matrix.service == 'nel_v2' && '--extras inference' || '' }}
+        run: |
+          if [ "${{ matrix.service }}" = "nel" ]; then
+            poetry install --no-interaction --without inference
+          elif [ "${{ matrix.service }}" = "nel_v2" ]; then
+            poetry install --no-interaction --extras inference
+          else
+            poetry install --no-interaction
+          fi
         working-directory: backend/${{ matrix.service }}
 
       - name: Run tests
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 52d379c..bebe237 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -2,13 +2,15 @@ name: CI
 
 on:
   push:
-    branches: ["**"]
+    branches:
+      - main
+  pull_request:
 
 # Only one deploy at a time; cancel in-progress CI runs on the same branch
 # but never cancel a deploy that is already running.
 concurrency:
-  group: ${{ github.workflow }}-${{ contains(github.event.head_commit.message, '[deploy dev]') && 'deploying' || github.ref_name }}
-  cancel-in-progress: false
+  group: ${{ github.workflow }}-${{ contains(github.event.head_commit.message, '[deploy dev]') && 'deploying' || github.ref }}-${{ github.event_name }}
+  cancel-in-progress: true
 
 jobs:
   backend-ci:
diff --git a/backend/nel/poetry.lock b/backend/nel/poetry.lock
index ffacecb..18028e7 100644
--- a/backend/nel/poetry.lock
+++ b/backend/nel/poetry.lock
@@ -50,7 +50,7 @@ version = "2026.2.25"
 description = "Python package for providing Mozilla's CA Bundle."
 optional = false
 python-versions = ">=3.7"
-groups = ["main", "dev"]
+groups = ["main", "dev", "inference"]
 files = [
     {file = "certifi-2026.2.25-py3-none-any.whl", hash = "sha256:027692e4402ad994f1c42e52a4997a9763c646b73e4096e4d5d6db8af1d6f0fa"},
     {file = "certifi-2026.2.25.tar.gz", hash = "sha256:e887ab5cee78ea814d3472169153c2d12cd43b14bd03329a39a9c6e2e80bfba7"},
@@ -62,7 +62,7 @@ version = "3.4.7"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 optional = false
 python-versions = ">=3.7"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "charset_normalizer-3.4.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cdd68a1fb318e290a2077696b7eb7a21a49163c455979c639bf5a5dcdc46617d"},
     {file = "charset_normalizer-3.4.7-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e17b8d5d6a8c47c85e68ca8379def1303fd360c3e22093a807cd34a71cd082b8"},
@@ -216,12 +216,12 @@ version = "0.4.6"
 description = "Cross-platform colored terminal text."
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
-groups = ["main", "dev"]
+groups = ["main", "dev", "inference"]
 files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
-markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\"", dev = "sys_platform == \"win32\""}
+markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\"", dev = "sys_platform == \"win32\"", inference = "platform_system == \"Windows\""}
 
 [[package]]
 name = "cuda-bindings"
@@ -229,7 +229,7 @@ version = "13.2.0"
 description = "Python bindings for CUDA"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "cuda_bindings-13.2.0-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:08b395f79cb89ce0cd8effff07c4a1e20101b873c256a1aeb286e8fd7bd0f556"},
@@ -264,7 +264,7 @@ version = "1.5.2"
 description = "Pathfinder for CUDA components"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "cuda_pathfinder-1.5.2-py3-none-any.whl", hash = "sha256:0c5f160a7756c5b072723cbbd6d861e38917ef956c68150b02f0b6e9271c71fa"},
@@ -276,7 +276,7 @@ version = "13.0.2"
 description = "CUDA Toolkit meta-package"
 optional = false
 python-versions = "*"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "cuda_toolkit-13.0.2-py2.py3-none-any.whl", hash = "sha256:b198824cf2f54003f50d64ada3a0f184b42ca0846c1c94192fa269ecd97a66eb"},
@@ -434,7 +434,7 @@ version = "3.25.2"
 description = "A platform independent file lock."
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "filelock-3.25.2-py3-none-any.whl", hash = "sha256:ca8afb0da15f229774c9ad1b455ed96e85a81373065fb10446672f64444ddf70"},
     {file = "filelock-3.25.2.tar.gz", hash = "sha256:b64ece2b38f4ca29dd3e810287aa8c48182bbecd1ae6e9ae126c9b35f1382694"},
@@ -446,7 +446,7 @@ version = "2026.3.0"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "fsspec-2026.3.0-py3-none-any.whl", hash = "sha256:d2ceafaad1b3457968ed14efa28798162f1638dbb5d2a6868a2db002a5ee39a4"},
     {file = "fsspec-2026.3.0.tar.gz", hash = "sha256:1ee6a0e28677557f8c2f994e3eea77db6392b4de9cd1f5d7a9e87a0ae9d01b41"},
@@ -498,7 +498,7 @@ version = "1.4.3"
 description = "Fast transfer of large files with the Hugging Face Hub."
 optional = false
 python-versions = ">=3.8"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\""
 files = [
     {file = "hf_xet-1.4.3-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:7551659ba4f1e1074e9623996f28c3873682530aee0a846b7f2f066239228144"},
@@ -638,7 +638,7 @@ version = "0.36.2"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "huggingface_hub-0.36.2-py3-none-any.whl", hash = "sha256:48f0c8eac16145dfce371e9d2d7772854a4f591bcb56c9cf548accf531d54270"},
     {file = "huggingface_hub-0.36.2.tar.gz", hash = "sha256:1934304d2fb224f8afa3b87007d58501acfda9215b334eed53072dd5e815ff7a"},
@@ -677,7 +677,7 @@ version = "3.11"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.8"
-groups = ["main", "dev"]
+groups = ["main", "dev", "inference"]
 files = [
     {file = "idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea"},
     {file = "idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902"},
@@ -704,7 +704,7 @@ version = "3.1.6"
 description = "A very fast and expressive template engine."
 optional = false
 python-versions = ">=3.7"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67"},
     {file = "jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d"},
@@ -722,7 +722,7 @@ version = "1.5.3"
 description = "Lightweight pipelining with Python functions"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["inference"]
 files = [
     {file = "joblib-1.5.3-py3-none-any.whl", hash = "sha256:5fc3c5039fc5ca8c0276333a188bbd59d6b7ab37fe6632daa76bc7f9ec18e713"},
     {file = "joblib-1.5.3.tar.gz", hash = "sha256:8561a3269e6801106863fd0d6d84bb737be9e7631e33aaed3fb9ce5953688da3"},
@@ -758,7 +758,7 @@ version = "3.0.3"
 description = "Safely add untrusted strings to HTML/XML markup."
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "markupsafe-3.0.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2f981d352f04553a7171b8e44369f2af4055f888dfb147d55e42d29e29e74559"},
     {file = "markupsafe-3.0.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e1c1493fb6e50ab01d20a22826e57520f1284df32f2d8601fdd90b6304601419"},
@@ -869,7 +869,7 @@ version = "1.3.0"
 description = "Python library for arbitrary-precision floating-point arithmetic"
 optional = false
 python-versions = "*"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
     {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
@@ -887,7 +887,7 @@ version = "3.4.2"
 description = "Python package for creating and manipulating graphs and networks"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version == \"3.10\""
 files = [
     {file = "networkx-3.4.2-py3-none-any.whl", hash = "sha256:df5d4365b724cf81b8c6a7312509d0c22386097011ad1abe274afd5e9d3bbc5f"},
@@ -908,7 +908,7 @@ version = "3.6"
 description = "Python package for creating and manipulating graphs and networks"
 optional = false
 python-versions = ">=3.11"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version >= \"3.12\""
 files = [
     {file = "networkx-3.6-py3-none-any.whl", hash = "sha256:cdb395b105806062473d3be36458d8f1459a4e4b98e236a66c3a48996e07684f"},
@@ -932,7 +932,7 @@ version = "3.6.1"
 description = "Python package for creating and manipulating graphs and networks"
 optional = false
 python-versions = "!=3.14.1,>=3.11"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version == \"3.11\""
 files = [
     {file = "networkx-3.6.1-py3-none-any.whl", hash = "sha256:d47fbf302e7d9cbbb9e2555a0d267983d2aa476bac30e90dfbe5669bd57f3762"},
@@ -956,7 +956,7 @@ version = "1.26.4"
 description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
     {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
@@ -1002,7 +1002,7 @@ version = "13.1.0.3"
 description = "CUBLAS native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cublas-13.1.0.3-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:c86fc7f7ae36d7528288c5d88098edcb7b02c633d262e7ddbb86b0ad91be5df2"},
@@ -1016,7 +1016,7 @@ version = "12.6.4.1"
 description = "CUBLAS native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cublas_cu12-12.6.4.1-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:08ed2686e9875d01b58e3cb379c6896df8e76c75e0d4a7f7dace3d7b6d9ef8eb"},
@@ -1030,7 +1030,7 @@ version = "13.0.85"
 description = "CUDA profiling tools runtime libs."
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_cuda_cupti-13.0.85-py3-none-manylinux_2_25_aarch64.whl", hash = "sha256:796bd679890ee55fb14a94629b698b6db54bcfd833d391d5e94017dd9d7d3151"},
@@ -1044,7 +1044,7 @@ version = "12.6.80"
 description = "CUDA profiling tools runtime libs."
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:166ee35a3ff1587f2490364f90eeeb8da06cd867bd5b701bf7f9a02b78bc63fc"},
@@ -1060,7 +1060,7 @@ version = "13.0.88"
 description = "NVRTC native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_cuda_nvrtc-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:ad9b6d2ead2435f11cbb6868809d2adeeee302e9bb94bcf0539c7a40d80e8575"},
@@ -1074,7 +1074,7 @@ version = "12.6.77"
 description = "NVRTC native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cuda_nvrtc_cu12-12.6.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5847f1d6e5b757f1d2b3991a01082a44aad6f10ab3c5c0213fa3e25bddc25a13"},
@@ -1088,7 +1088,7 @@ version = "13.0.96"
 description = "CUDA Runtime native Libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_cuda_runtime-13.0.96-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ef9bcbe90493a2b9d810e43d249adb3d02e98dd30200d86607d8d02687c43f55"},
@@ -1102,7 +1102,7 @@ version = "12.6.77"
 description = "CUDA Runtime native Libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6116fad3e049e04791c0256a9778c16237837c08b27ed8c8401e2e45de8d60cd"},
@@ -1118,7 +1118,7 @@ version = "9.5.1.17"
 description = "cuDNN runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cudnn_cu12-9.5.1.17-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:9fd4584468533c61873e5fda8ca41bac3a38bcb2d12350830c69b0a96a7e4def"},
@@ -1135,7 +1135,7 @@ version = "9.19.0.56"
 description = "cuDNN runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cudnn_cu13-9.19.0.56-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:6ed29ffaee1176c612daf442e4dd6cfeb6a0caa43ddcbeb59da94953030b1be4"},
@@ -1152,7 +1152,7 @@ version = "12.0.0.61"
 description = "CUFFT native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5"},
@@ -1169,7 +1169,7 @@ version = "11.3.0.4"
 description = "CUFFT native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d16079550df460376455cba121db6564089176d9bac9e4f360493ca4741b22a6"},
@@ -1188,7 +1188,7 @@ version = "1.15.1.6"
 description = "cuFile GPUDirect libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and sys_platform == \"linux\""
 files = [
     {file = "nvidia_cufile-1.15.1.6-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:08a3ecefae5a01c7f5117351c64f17c7c62efa5fffdbe24fc7d298da19cd0b44"},
@@ -1201,7 +1201,7 @@ version = "1.11.1.6"
 description = "cuFile GPUDirect libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cufile_cu12-1.11.1.6-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:cc23469d1c7e52ce6c1d55253273d32c565dd22068647f3aa59b3c6b005bf159"},
@@ -1214,7 +1214,7 @@ version = "10.4.0.35"
 description = "CURAND native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_curand-10.4.0.35-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:133df5a7509c3e292aaa2b477afd0194f06ce4ea24d714d616ff36439cee349a"},
@@ -1228,7 +1228,7 @@ version = "10.3.7.77"
 description = "CURAND native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:6e82df077060ea28e37f48a3ec442a8f47690c7499bff392a5938614b56c98d8"},
@@ -1244,7 +1244,7 @@ version = "12.0.4.66"
 description = "CUDA solver native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2"},
@@ -1263,7 +1263,7 @@ version = "11.7.1.2"
 description = "CUDA solver native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0ce237ef60acde1efc457335a2ddadfd7610b892d94efee7b776c64bb1cac9e0"},
@@ -1284,7 +1284,7 @@ version = "12.6.3.3"
 description = "CUSPARSE native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c"},
@@ -1301,7 +1301,7 @@ version = "12.5.4.2"
 description = "CUSPARSE native runtime libraries"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d25b62fb18751758fe3c93a4a08eff08effedfe4edf1c6bb5afd0890fe88f887"},
@@ -1320,7 +1320,7 @@ version = "0.6.3"
 description = "NVIDIA cuSPARSELt"
 optional = false
 python-versions = "*"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:8371549623ba601a06322af2133c4a44350575f5a3108fb75f3ef20b822ad5f1"},
@@ -1334,7 +1334,7 @@ version = "0.8.0"
 description = "NVIDIA cuSPARSELt"
 optional = false
 python-versions = "*"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cusparselt_cu13-0.8.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:400c6ed1cf6780fc6efedd64ec9f1345871767e6a1a0a552a1ea0578117ea77c"},
@@ -1348,7 +1348,7 @@ version = "2.26.2"
 description = "NVIDIA Collective Communication Library (NCCL) Runtime"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_nccl_cu12-2.26.2-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5c196e95e832ad30fbbb50381eb3cbd1fadd5675e587a548563993609af19522"},
@@ -1361,7 +1361,7 @@ version = "2.28.9"
 description = "NVIDIA Collective Communication Library (NCCL) Runtime"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_nccl_cu13-2.28.9-py3-none-manylinux_2_18_aarch64.whl", hash = "sha256:01c873ba1626b54caa12272ed228dc5b2781545e0ae8ba3f432a8ef1c6d78643"},
@@ -1374,7 +1374,7 @@ version = "13.0.88"
 description = "Nvidia JIT LTO Library"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_nvjitlink-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:13a74f429e23b921c1109976abefacc69835f2f433ebd323d3946e11d804e47b"},
@@ -1388,7 +1388,7 @@ version = "12.6.85"
 description = "Nvidia JIT LTO Library"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a"},
@@ -1402,7 +1402,7 @@ version = "3.4.5"
 description = "NVSHMEM creates a global address space that provides efficient and scalable communication for NVIDIA GPU clusters."
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_nvshmem_cu13-3.4.5-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6dc2a197f38e5d0376ad52cd1a2a3617d3cdc150fd5966f4aee9bcebb1d68fe9"},
@@ -1415,7 +1415,7 @@ version = "13.0.85"
 description = "NVIDIA Tools Extension"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\" and (sys_platform == \"linux\" or sys_platform == \"win32\")"
 files = [
     {file = "nvidia_nvtx-13.0.85-py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:4936d1d6780fbe68db454f5e72a42ff64d1fd6397df9f363ae786930fd5c1cd4"},
@@ -1429,7 +1429,7 @@ version = "12.6.77"
 description = "NVIDIA Tools Extension"
 optional = false
 python-versions = ">=3"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f44f8d86bb7d5629988d61c8d3ae61dddb2015dee142740536bc7481b022fe4b"},
@@ -1445,7 +1445,7 @@ version = "26.0"
 description = "Core utilities for Python packages"
 optional = false
 python-versions = ">=3.8"
-groups = ["main", "dev"]
+groups = ["main", "dev", "inference"]
 files = [
     {file = "packaging-26.0-py3-none-any.whl", hash = "sha256:b36f1fef9334a5588b4166f8bcd26a14e521f2b55e6b9de3aaa80d3ff7a37529"},
     {file = "packaging-26.0.tar.gz", hash = "sha256:00243ae351a257117b6a241061796684b084ed1c516a08c48a3f7e147a9d80b4"},
@@ -1557,7 +1557,7 @@ version = "12.2.0"
 description = "Python Imaging Library (fork)"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["inference"]
 files = [
     {file = "pillow-12.2.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:a4e8f36e677d3336f35089648c8955c51c6d386a13cf6ee9c189c5f5bd713a9f"},
     {file = "pillow-12.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e589959f10d9824d39b350472b92f0ce3b443c0a3442ebf41c40cb8361c5b97"},
@@ -1950,7 +1950,7 @@ version = "6.0.3"
 description = "YAML parser and emitter for Python"
 optional = false
 python-versions = ">=3.8"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "PyYAML-6.0.3-cp38-cp38-macosx_10_13_x86_64.whl", hash = "sha256:c2514fceb77bc5e7a2f7adfaa1feb2fb311607c9cb518dbc378688ec73d8292f"},
     {file = "PyYAML-6.0.3-cp38-cp38-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c57bb8c96f6d1808c030b1687b9b5fb476abaa47f0db9c0101f5e9f394e97f4"},
@@ -2033,7 +2033,7 @@ version = "2026.4.4"
 description = "Alternative regular expression module, to replace re."
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "regex-2026.4.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:74fa82dcc8143386c7c0392e18032009d1db715c25f4ba22d23dc2e04d02a20f"},
     {file = "regex-2026.4.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a85b620a388d6c9caa12189233109e236b3da3deffe4ff11b84ae84e218a274f"},
@@ -2157,7 +2157,7 @@ version = "2.33.1"
 description = "Python HTTP for Humans."
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "requests-2.33.1-py3-none-any.whl", hash = "sha256:4e6d1ef462f3626a1f0a0a9c42dd93c63bad33f9f1c1937509b8c5c8718ab56a"},
     {file = "requests-2.33.1.tar.gz", hash = "sha256:18817f8c57c6263968bc123d237e3b8b08ac046f5456bd1e307ee8f4250d3517"},
@@ -2215,7 +2215,7 @@ version = "0.7.0"
 description = ""
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "safetensors-0.7.0-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:c82f4d474cf725255d9e6acf17252991c3c8aac038d6ef363a4bf8be2f6db517"},
     {file = "safetensors-0.7.0-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:94fd4858284736bb67a897a41608b5b0c2496c9bdb3bf2af1fa3409127f20d57"},
@@ -2262,7 +2262,7 @@ version = "1.7.2"
 description = "A set of python modules for machine learning and data mining"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["inference"]
 markers = "python_version == \"3.10\""
 files = [
     {file = "scikit_learn-1.7.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6b33579c10a3081d076ab403df4a4190da4f4432d443521674637677dc91e61f"},
@@ -2319,7 +2319,7 @@ version = "1.8.0"
 description = "A set of python modules for machine learning and data mining"
 optional = false
 python-versions = ">=3.11"
-groups = ["main"]
+groups = ["inference"]
 markers = "python_version >= \"3.11\""
 files = [
     {file = "scikit_learn-1.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:146b4d36f800c013d267b29168813f7a03a43ecd2895d04861f1240b564421da"},
@@ -2382,7 +2382,7 @@ version = "1.15.3"
 description = "Fundamental algorithms for scientific computing in Python"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["inference"]
 markers = "python_version == \"3.10\""
 files = [
     {file = "scipy-1.15.3-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:a345928c86d535060c9c2b25e71e87c39ab2f22fc96e9636bd74d1dbf9de448c"},
@@ -2447,7 +2447,7 @@ version = "1.17.1"
 description = "Fundamental algorithms for scientific computing in Python"
 optional = false
 python-versions = ">=3.11"
-groups = ["main"]
+groups = ["inference"]
 markers = "python_version >= \"3.11\""
 files = [
     {file = "scipy-1.17.1-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:1f95b894f13729334fb990162e911c9e5dc1ab390c58aa6cbecb389c5b5e28ec"},
@@ -2527,7 +2527,7 @@ version = "2.7.0"
 description = "Multilingual text embeddings"
 optional = false
 python-versions = ">=3.8.0"
-groups = ["main"]
+groups = ["inference"]
 files = [
     {file = "sentence_transformers-2.7.0-py3-none-any.whl", hash = "sha256:6a7276b05a95931581bbfa4ba49d780b2cf6904fa4a171ec7fd66c343f761c98"},
     {file = "sentence_transformers-2.7.0.tar.gz", hash = "sha256:2f7df99d1c021dded471ed2d079e9d1e4fc8e30ecb06f957be060511b36f24ea"},
@@ -2552,7 +2552,7 @@ version = "81.0.0"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\""
 files = [
     {file = "setuptools-81.0.0-py3-none-any.whl", hash = "sha256:fdd925d5c5d9f62e4b74b30d6dd7828ce236fd6ed998a08d81de62ce5a6310d6"},
@@ -2574,7 +2574,7 @@ version = "82.0.1"
 description = "Most extensible Python build backend with support for C/C++ extension modules"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version >= \"3.12\""
 files = [
     {file = "setuptools-82.0.1-py3-none-any.whl", hash = "sha256:a59e362652f08dcd477c78bb6e7bd9d80a7995bc73ce773050228a348ce2e5bb"},
@@ -2650,7 +2650,7 @@ version = "1.14.0"
 description = "Computer algebra system (CAS) in Python"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "sympy-1.14.0-py3-none-any.whl", hash = "sha256:e091cc3e99d2141a0ba2847328f5479b05d94a6635cb96148ccb3f34671bd8f5"},
     {file = "sympy-1.14.0.tar.gz", hash = "sha256:d3d3fe8df1e5a0b42f0e7bdf50541697dbe7d23746e894990c030e2b05e72517"},
@@ -2687,7 +2687,7 @@ version = "3.6.0"
 description = "threadpoolctl"
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["inference"]
 files = [
     {file = "threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb"},
     {file = "threadpoolctl-3.6.0.tar.gz", hash = "sha256:8ab8b4aa3491d812b623328249fab5302a68d2d71745c8a4c719a2fcaba9f44e"},
@@ -2699,7 +2699,7 @@ version = "0.22.2"
 description = ""
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "tokenizers-0.22.2-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:544dd704ae7238755d790de45ba8da072e9af3eea688f698b137915ae959281c"},
     {file = "tokenizers-0.22.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:1e418a55456beedca4621dbab65a318981467a2b188e982a23e117f115ce5001"},
@@ -2799,7 +2799,7 @@ version = "2.7.1"
 description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
 optional = false
 python-versions = ">=3.9.0"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version >= \"3.12\""
 files = [
     {file = "torch-2.7.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:a103b5d782af5bd119b81dbcc7ffc6fa09904c423ff8db397a1e6ea8fd71508f"},
@@ -2862,7 +2862,7 @@ version = "2.11.0"
 description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
 optional = false
 python-versions = ">=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\""
 files = [
     {file = "torch-2.11.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2c0d7fcfbc0c4e8bb5ebc3907cbc0c6a0da1b8f82b1fc6e14e914fa0b9baf74e"},
@@ -2922,7 +2922,7 @@ version = "4.67.3"
 description = "Fast, Extensible Progress Meter"
 optional = false
 python-versions = ">=3.7"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "tqdm-4.67.3-py3-none-any.whl", hash = "sha256:ee1e4c0e59148062281c49d80b25b67771a127c85fc9676d3be5f243206826bf"},
     {file = "tqdm-4.67.3.tar.gz", hash = "sha256:7d825f03f89244ef73f1d4ce193cb1774a8179fd96f31d7e1dcde62092b960bb"},
@@ -2944,7 +2944,7 @@ version = "4.57.6"
 description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
 optional = false
 python-versions = ">=3.9.0"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "transformers-4.57.6-py3-none-any.whl", hash = "sha256:4c9e9de11333ddfe5114bc872c9f370509198acf0b87a832a0ab9458e2bd0550"},
     {file = "transformers-4.57.6.tar.gz", hash = "sha256:55e44126ece9dc0a291521b7e5492b572e6ef2766338a610b9ab5afbb70689d3"},
@@ -3019,7 +3019,7 @@ version = "3.3.1"
 description = "A language and compiler for custom Deep Learning operations"
 optional = false
 python-versions = "*"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version >= \"3.12\""
 files = [
     {file = "triton-3.3.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b74db445b1c562844d3cfad6e9679c72e93fdfb1a90a24052b03bb5c49d1242e"},
@@ -3044,7 +3044,7 @@ version = "3.6.0"
 description = "A language and compiler for custom Deep Learning operations"
 optional = false
 python-versions = "<3.15,>=3.10"
-groups = ["main"]
+groups = ["main", "inference"]
 markers = "python_version < \"3.12\" and platform_system == \"Linux\""
 files = [
     {file = "triton-3.6.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6c723cfb12f6842a0ae94ac307dba7e7a44741d720a40cf0e270ed4a4e3be781"},
@@ -3092,7 +3092,7 @@ version = "4.15.0"
 description = "Backported and Experimental Type Hints for Python 3.9+"
 optional = false
 python-versions = ">=3.9"
-groups = ["main", "dev"]
+groups = ["main", "dev", "inference"]
 files = [
     {file = "typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548"},
     {file = "typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466"},
@@ -3132,7 +3132,7 @@ version = "2.6.3"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 optional = false
 python-versions = ">=3.9"
-groups = ["main"]
+groups = ["main", "inference"]
 files = [
     {file = "urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4"},
     {file = "urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed"},
@@ -3432,4 +3432,4 @@ files = [
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.10"
-content-hash = "6e290bb13a3eb09c4b77f45b9058379b106f1ab410380d7e35e5d1b93fe9f5cd"
+content-hash = "ae4a3ed53dd7a4a3593849b8942b9244c0194e47fbe6811c229d938a2ffc7b43"
diff --git a/backend/nel/pyproject.toml b/backend/nel/pyproject.toml
index 2d60186..c310c2d 100644
--- a/backend/nel/pyproject.toml
+++ b/backend/nel/pyproject.toml
@@ -9,13 +9,15 @@ packages = [{ include = "nel" }]
 python = "^3.10"
 fastapi = "^0.111.0"
 uvicorn = { version = "^0.30.0", extras = ["standard"] }
-torch = "^2.1.2"
-sentence-transformers = "^2.2.2"
 pandas = "^2.0.3"
 numpy = "^1.24.3"
 python-dotenv = "^1.0.1"
 tabiya-shared = { path = "../shared", develop = true }
 
+[tool.poetry.group.inference.dependencies]
+torch = "^2.1.2"
+sentence-transformers = "^2.2.2"
+
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"
 pytest-asyncio = "^0.23.0"