[KDD'2026] "VideoRAG: Chat with Your Videos"
Python large-language-modelsllmslong-video-understandingmulti-modal-llmsragretrieval-augmented-generation
update README.md
Re-bin697129440221
diff --git a/README.md b/README.mdindex 91822c9..dcf8b64 100644--- a/README.md+++ b/README.md@@ -162,7 +162,7 @@ if __name__ == '__main__':print(response)```-## Evaluation+## Experiments### LongerVideosWe constructed the LongerVideos benchmark to evaluate the model's performance in comprehending multiple long-context videos and answering open-ended queries. All the videos are open-access videos on YouTube, and we record the URLs of the collections of videos as well as the corresponding queries in the [JSON](longervideos/dataset.json) file.@@ -244,7 +244,7 @@ python batch_winrate_quant_download.pypython batch_winrate_quant_calculate.py```-### Ollama Support+## Ollama SupportThis project also supports ollama. To use, edit the ollama_config in [_llm.py](VideoRAG/videorag/_llm.py).Adjust the paramters of the models being used