Cianplan

Level 5: AI / LLM systems · L5.8 Generative AI on AWS: Bedrock in practice (AIP-C01)

Multimodal inputs: documents, images, audio and video for foundation models

Turn documents, images, audio and video into model-ready input with Bedrock Data Automation, Amazon Transcribe, Amazon Textract or a multimodal embedding model, and choose how a knowledge base parses them.

13 min · Pro

What you take away

  • Each modality is either converted to text (transcripts, OCR, scene summaries) or embedded as it is with a multimodal embedding model; converting keeps full RAG, embedding keeps what text loses.

And 3 more inside the class, in Pro.

How the class is laid out

  1. The problem
  2. The prep station
  3. Convert to text, or embed as it is
  4. Bedrock Data Automation
  5. The primitives, and the parser choice
  6. Check your understanding