Spaces:

88hours
/

multimodel-rag-chat-with-videos

Sleeping

App Files Files Community

multimodel-rag-chat-with-videos

Ctrl+K

Ctrl+K

3 contributors

History: 83 commits

Nauman J Qazi

Add Chat in Demo

4609d8b over 1 year ago

mm_rag
Fix embed_query to check dict and convert tensor to list over 1 year ago
shared_data
Remove lanceDB table if exists over 1 year ago
.gitattributes

1.56 kB
Track large files with Git LFS over 1 year ago
.gitignore

136 Bytes
Add Chat in Demo over 1 year ago
README.md

6.13 kB
fix app.py path for HF over 1 year ago
app.py

9.69 kB
Add Chat in Demo over 1 year ago
gradio_utils.py

18.6 kB
add llava and whisper support over 1 year ago
lrn_vector_embeddings.py

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

263 Bytes
Rename app.py to hugging face requirement 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

3.08 kB
Wip=> Fix code erros regarding filepath, metadatas over 1 year ago
s7_store_in_rag.py

3.49 kB
Confirm DataStorage in LancdDB over 1 year ago
utility.py

27.6 kB
Add Chat in Demo over 1 year ago