Great database for generative AI applications
June 20, 2024

Great database for generative AI applications

Anonymous | TrustRadius Reviewer
Score 7 out of 10
Vetted Review
Verified User

Overall Satisfaction with IBM watsonx.data

We use IBM watsonx.data in conjunction with watsonx.ai mainly to create demos and proof-of-concpets (PoC) of generative AI applications. In our case we mainly use Milvus, the vector database implemented in IBM watsonx.data.

Pros

  • Seamless integration between vector data and the AI engines
  • Pretty good search performance even on large data sets
  • Good cost performance/cost optimization overall

Cons

  • The UI can be slow to respond at times (just like many cloud services thought)
  • Semantic automation is still in beta and has no Japanese support yet
  • Loading data to the platform can be slow at times
  • Speed up and reduce the cost of building vector databases for generative AI applications
  • Helps training engineers on latest AI technologies
Pinecone and IBM watsonx.data (Milvus in our case) both work great as a full-managed cloud-based vector database.
We selected IBM watsonx.data because it integrates well with watson.ai and is a little more beginner friendly than Pinecone, but I think both are great anyway.

Do you think IBM watsonx.data delivers good value for the price?

Yes

Are you happy with IBM watsonx.data's feature set?

Yes

Did IBM watsonx.data live up to sales and marketing promises?

Yes

Did implementation of IBM watsonx.data go as expected?

Yes

Would you buy IBM watsonx.data again?

Yes

Obviously IBM watsonx.data has been designed to work well with other watson products (mainly watsonx.ai), so it makes sense to use it as a vector database for watson.ai.
The semantic automation feature is promising, but I think it is not ready yet for a large scale rollout so I would recommend using it only for demos/proof of concepts.

Comments

More Reviews of IBM watsonx.data