Using the watsonx.ai account provided with the Content Assistant

The Content Assistant, by default, uses a specific watsonx.ai account.
This default watsonx.ai account that is provided with the Content Assistant has the following capabilities:

License-related restrictions with the watsonx.ai account provided with Content Assistant

The following restrictions apply when you use the watsonx.ai account that is provided with the Content Assistant:
  • When you are using the default watsonx.ai account, you may not increase the default number of GenAI queue sweep worker threads. The default value is one worker thread per Content Platform Engine server. This limitation impacts both the throughput for documentation vector indexing and the throughput for document summarization.
  • If you run high volume production workloads, you need to continue to use your own watsonx.ai account.
When you use your own watsonx.ai account instead of the default watsonx.ai account, these restrictions no longer apply.

Content Assistant supported foundation models

The following table lists the large language models supported by the Content Assistant:

Table 1. Large language models
Model name Dallas Frankfurt
granite-4-h-small
llama-3-3-70b-instruct
llama-4-maverick-17b-128e-instruct-fp8
mistral-medium-2505
gpt-oss-120b  
Note: For more information about the availability of a supported model across a data center, see Regional availability of foundation models.

The following table lists the embedding models supported by the Content Assistant:

Table 2. Embedding models
Model name Dallas Frankfurt
slate-125m-english-rtrvr-v2
granite-embedding-278m-multilingual
multilingual-e5-large