...
We are already on AWS, we know how to use it and we do not have to learn another cloud platform/api
There is no easy way to test this out today quickly and compare across solutions. Ideally with a first prototype we could build a static knowledge base that can be reused, including the indexed content and the questions/answers plus feedback.
Bedrock seems to be the most comprehensive and easier to integrate solution out there, despite that it might not have the best models availablewith several tools that include model evaluation (https://docs.aws.amazon.com/bedrock/latest/userguide/model-evaluation.html ), prompt management (https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html ), content filtering (See https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html ) etc.
Bedrock provide access to several different foundation models that can be tried (See https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html )
Bedrock has native support for metadata filtering (https://aws.amazon.com/about-aws/whats-new/2024/03/knowledge-bases-amazon-bedrock-metadata-filtering/) that could be used for access control in a similar way we do with CloudSearch today.
We could potentially reuse OpenSearch for both normal search and the backing vector database
Pricing is a bit of a complex topic as in all the above solutions it follows a pay-for-what-you-use model that depends on the user input, number of tokens, type of model used and amount of data. Given my recommendation I can estimate the cost of bedrock to be around $1k-$2k/month depending on usage (the default vector database is AWS OpenSearch, which should cost between $400 and $800/month).
...