How to Use Multimodal RAG to Extract Text, Images, & Tables (with Demos)

[@FamilyManMoving]

Brilliant. I was looking for this exact information. Keep up the great work. Thank you.

[@amazonwebservices]

😀 🤝 ☁️

[@basilfateen9247]

Great video Suman!

[@shikharashish7616]

the github link for the code is giving 404 error

[@RedCloudServices]

Suman - thank you. how would this example get the response from reading one of the pdf images?

[@vigneshkaladharan1347]

Will try it

[@awssupport]

Glad to hear! ☁️ ^AD

[@SaiKrishnaReddyMudhiganti]

I have used clip instead of amazon bedrock for embeddings but the problem is I'm not able to see image matches. What could be potential issue, Its same code. Clip is projecting text, images in same dimensional space. Can you help me?

[@SaiKrishnaReddyMudhiganti]

good video

[@awssupport]

Glad to hear you enjoyed it! 😀 ^RS

[@kavinkumar4372]

Retrieval are not up to the expectations. Not worth trying.