IBM watsonx.data to test out a RAG solution
October 09, 2025
IBM watsonx.data to test out a RAG solution
Score 8 out of 10
Vetted Review
Verified User
Overall Satisfaction with IBM watsonx.data
As the database behind our RAG (Retrieval-Augmented Generation) solution. All of our unstructured content gets migrated to IBM watsonx.data and transformed to vectors to allow for easy searching. Though we may only have 1 million records that get migrated to IBM watsonx.data, the unstructured content can consists out of thousands of words. This gets chunked and vectorized creating a big data set within IBM watsonx.data.
Pros
- Big data
- Vectorization
- Search
- Filtering
Cons
- Cloud based is the easy solution, though not always preferred
- Slow importing of data due to the chunks causing many records
- IBM watsonx.data is not yet profitable for us, as we are using it in combination with RAG which in itself is not that perfect yet
- Great to see a competitor to ElasticSearch
The automatic chunking an vectorization is very valuable to us.
Easy integration with the other IBM components that previously we had to use APIs for. Now it is a more streamlined process.
The three pair nicely together to create my own RAG solution in a controlled manner.
Do you think IBM watsonx.data delivers good value for the price?
Not sure
Are you happy with IBM watsonx.data's feature set?
Yes
Did IBM watsonx.data live up to sales and marketing promises?
I wasn't involved with the selection/purchase process
Did implementation of IBM watsonx.data go as expected?
Yes
Would you buy IBM watsonx.data again?
Yes
Comments
Please log in to join the conversation