aws-samples/multimodal-rag-on-slide-decks

'Talk to your slide deck' (Multimodal RAG) using foundation models (FMs) hosted on Amazon Bedrock and Amazon SageMaker

40
/ 100
Emerging

Implements dual multimodal RAG architectures: one embedding slides directly into Amazon OpenSearch Serverless via Titan embeddings, and another pre-generating LLaVA 1.5 vision model inferences for storage and retrieval. Includes comparative analysis of embedding-first versus inference-first approaches, with complete implementations across all three solution patterns.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

44

Forks

8

Language

HTML

License

MIT-0

Last pushed

Jan 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/aws-samples/multimodal-rag-on-slide-decks"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.