ci: Remove submodule and clone internvideo (#1070)

* Remove submodule

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Update dockerfile to clone internvideo and apply patch

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Update internvideo import

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Uv add internvideo for cpu tests

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Update uv lock file

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Update external path

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* cd into repo

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Checkout and patch for cpu test

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Correct typo

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Use full commit sha

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Update internvideo package data config json

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

* Add copyright header for patch file

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

---------

Signed-off-by: Dong Hyuk Chang <donghyukc@nvidia.com>

Author: thomasdhc

.github/workflows/cicd-main.yml

@@ -140,6 +140,11 @@ jobs:
       - uses: actions/checkout@v4
         with:
           submodules: recursive
+      - uses: actions/checkout@v4
+        with:
+          repository: OpenGVLab/InternVideo
+          path: InternVideo
+          ref: 09d872e5093296c6f36b8b3a91fc511b76433bf7
       - name: Optionally free up space on Ubuntu
         run: |
           sudo rm -rf /usr/share/dotnet
@@ -152,7 +157,9 @@ jobs:
           python-version: ${{ matrix.python-version }}
       - name: Run tests ${{ matrix.folder }} (CPU)
         run: |
+          cd InternVideo && patch -p1 < ../external/intern_video2_multimodal.patch && cd ..
           uv sync --link-mode copy --locked --extra audio_cpu --extra text_cpu --extra video_cpu --group test
+          uv add InternVideo/InternVideo2/multi_modality
           uv run coverage run --branch --source=nemo_curator -m pytest -v tests/${{ matrix.folder }} -m "not gpu"
 
       - name: Generate report

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "nemo_curator/internvideo2_multi_modality"]
-	path = nemo_curator/internvideo2_multi_modality
-	url = https://github.com/thomasdhc/InternVideo2MultiModality.git

docker/Dockerfile

@@ -64,10 +64,21 @@ RUN bash install_ffmpeg.sh && \
 
 FROM nemo_curator_dep AS nemo_curator
 
+ARG INTERN_VIDEO_COMMIT=09d872e5093296c6f36b8b3a91fc511b76433bf7
+COPY external/intern_video2_multimodal.patch .
+# Clone InternVideo (Video curation dependency)
+RUN git clone https://github.com/OpenGVLab/InternVideo.git && \
+    cd InternVideo && \
+    git checkout ${INTERN_VIDEO_COMMIT} && \
+    patch -p1 < /opt/intern_video2_multimodal.patch && \
+    rm /opt/intern_video2_multimodal.patch
+
+# Install Curator
 COPY . /opt/Curator
 RUN cd /opt/Curator && \
   uv sync --locked --only-group build && \
-  uv sync --link-mode copy --locked --extra all --all-groups
+  uv sync --link-mode copy --locked --extra all --all-groups && \
+  uv add /opt/InternVideo/InternVideo2/multi_modality
 
 COPY <<EOF /opt/venv/env.sh
 export UV_PROJECT_ENVIRONMENT=/opt/venv