Spaces:

88hours
/

multimodel-rag-chat-with-videos

Sleeping

App Files Files Community

multimodel-rag-chat-with-videos

1.75 MB

Ctrl+K

Ctrl+K

3 contributors

History: 98 commits

88hours's picture

improved limited UI

913d475 over 1 year ago

mm_rag
Add more path in ignore over 1 year ago
shared_data
Upload folder using huggingface_hub over 1 year ago
.gitattributes

1.6 kB
Upload folder using huggingface_hub over 1 year ago
.gitignore

289 Bytes
Update gitignore and use dockerfile for dev container over 1 year ago
Dockerfile

497 Bytes
Upload folder using huggingface_hub over 1 year ago
README.md

6.43 kB
Upload folder using huggingface_hub over 1 year ago
app.py

13.9 kB
improved limited UI over 1 year ago
gradio_utils.py

19 kB
Upload folder using huggingface_hub over 1 year ago
lrn_vector_embeddings.py

3.76 kB
Changing embedding from PredictionGuard to Local over 1 year ago
requirements.txt

330 Bytes
Upload folder using huggingface_hub over 1 year ago
s2_download_data.py

1.34 kB
Remove Hugging Face download over 1 year ago
s3_data_to_vector_embedding.py

2.03 kB
Remove Hugging Face download over 1 year ago
s4_calculate_distance.py

2.85 kB
File Rename over 1 year ago
s5-how-to-umap.py

5.3 kB
Plot shows, however, I am not certain if it is showing the right data. The main confusion is that to see vector data of 512 dimenstion, you need to reduce it to 2 dimension on a scaler plot. The function given here does not work. First np.concatenate does not like lists that has embeddings and has grad init. It want me to detach numpy. The second problem is with MinMaxScaler method that has issue with dimention, it expects 2, but one is given. Not very clear on this over 1 year ago
s6_prepare_video_input.py

3.17 kB
Upload folder using huggingface_hub over 1 year ago
s7_store_in_rag.py

3.6 kB
Upload folder using huggingface_hub over 1 year ago
utility.py

29.4 kB
Upload folder using huggingface_hub over 1 year ago