Amazon DynamoDB (DocStore)

Summary and motivation

Amazon DynamoDB added native vector similarity search (SearchVectors API, GA 2026-08-05), turning it into a real vector store for the first time — previously it could store a vector as a plain number array but had no native similarity-search capability. This closes the gap that made DynamoDB unsuitable for RAG-style retrieval, and it would be a useful addition to the existing DocStore integrations.

Detailed design

The design of the docstore should include the necessary actions from the DynamoDB client: https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb.html

At minimum: creating the DocStore, writing/inserting documents, and querying via embedding retrieval (Embedding Retriever). Filtering will follow DynamoDB's SearchVectors index-schema constraints for attribute filters.

Checklist

If the request is accepted, ensure the following checklist is complete before closing this issue.

Tasks

• The code is documented with docstrings and was merged in the main branch
• Docs are published at https://docs.haystack.deepset.ai/
• There is a Github workflow running the tests for the integration nightly and at every PR
• A new label named like integration:<your integration name> has been added to the list of labels for this repository
• The labeler.yml file has been updated
• The package has been released on PyPI
• An integration tile has been added to https://github.com/deepset-ai/haystack-integrations
• The integration has been listed in the Inventory section of this repo README
• There is an example available to demonstrate the feature
• The feature was announced through social media