Multimodal-VideoRAG: Using BridgeTower Embeddings and Large Vision Language Models
-
Updated
Sep 26, 2024 - Jupyter Notebook
#
bridgetower
Here are 2 public repositories matching this topic...
Multimodal RAG over video: fine-tuned BridgeTower embeddings + LanceDB retrieval + LLaVA-1.5 grounded answers, with a Gradio UI that returns the matching video clip
computer-visionpytorchgradiovideo-question-answeringcontrastive-learninglangchainllavalancedbmultimodal-ragbridgetower
-
Updated
Aug 19, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the bridgetower topic, visit your repo's landing page and select "manage topics."