[KDD'2026] "VideoRAG: Chat with Your Videos"
Python large-language-modelsllmslong-video-understandingmulti-modal-llmsragretrieval-augmented-generation
update
Re-binb70bf7f14acc
diff --git a/README.md b/README.mdindex b6abc46..eea7901 100644--- a/README.md+++ b/README.md@@ -272,17 +272,9 @@ ollama_config = LLMConfig(And specify the config when creating your VideoRag instance### Jupyter Notebook-To test the solution on a single video, just load the notebook in the [notebook folder](VideoRAG/nodebooks) andupdate the paramters to fit your situation.-YouTube video for example can be downloaded as follows:--```-yt-dlp -o "%(id)s.%(ext)s" -S "res:720" https://www.youtube.com/live/DPa2iRgzadM?si=8cf8WbYtqiglrwtN -P .-```--## CitationIf you find this work is helpful to your research, please consider citing our paper:```bibtexdiff --git a/notesbooks/videorag.ipynb b/notesbooks/videorag.ipynbindex 4f3ca24..598ae2d 100644--- a/notesbooks/videorag.ipynb+++ b/notesbooks/videorag.ipynb@@ -31,7 +31,7 @@"outputs": [],"source": ["video_paths = [\n",- " '/mnt/data3/AI/software/VideoRAG/Lexington/GMT20241112-164602_Recording_gallery_1280x720.mp4',\n",+ " '/path/to/your/video.mp4',\n","]"]},