- Added Qwen3-VL-Embedding-2B and Qwen3-Reranker-4B models to SageMaker JumpStart for multimodal retrieval pipelines
- Embedding model generates shared visual‑text vectors for recall; reranker provides relevance scores for re‑ranking
- Models can be deployed in a few clicks or via the SageMaker Python SDK, with docs linked for guidance
Qwen3 embedding and reranking models for retrieval are now available in Amazon SageMaker JumpStart
Official AWS changelog summary with source attribution, release tags, and community reactions.
Track this AWS release note alongside related changelog updates, risky changes, and weekly digest signals from the developer community.
Verify the original release note
Every summary should remain traceable to the original changelog or release source.
Follow this in context
Turn this AWS release note into a weekly digest for the tools you actually use.
Create digestMore AWS changelog updates
Amazon Bedrock lowers GPT-5.6 Sol pricing to $4 per million input tokens (‑20%) and $20 per million output tokens (‑33.3%).
Introduces natural‑language chat for managers to query Amazon Connect Customer data and receive answers, evidence, and remediation steps
Adds a Download status column in the Deadline Cloud Monitor for jobs and tasks, showing progress and health of automatic file downloads.