ADR 0051 - Evaluating vector databases as AppCat services

OpenSearch/ElasticSearch provides vector capabilities out of the box. Either one of these products are already on the roadmap for AppCat.

StackGres and CNPG both already provide the pgvector extension. For StackGres it needs to be installed via the extensions stanza. CNPG pre-installs it in their default image. So the vector capabilities of our PostgreSQL offering is already there. Additional documentation to make users aware of this feature is recommended though.

Redis also provides vector capabilities out of the box. Redis provides documentation on how to use it: redis.io/docs/latest/develop/get-started/vector-database/#prepare-the-demo-dataset

Chroma’s maturity doesn’t seem to be there, many things are not documented on the official page but rather on a community driven page. Only a rudimentary helm chart is available. The recent rewrite in rust dropped features that were previously available.

Qdrant’s documentation is excellent. However, there’s a lot of "available on our cloud offering" there as well for features like cluster backups, which might be concerning for future anti-consumer decisions. The overall architecture and concepts are very inspired by ElasticSearch.

Milvus is by far the most complex solution of the three. Although it provides an operator to handle the deployment, the amount of services it needs and deploys is extensive:

This rivals Kafka in complexity.