Restrictions
- AWS Bedrock doesn’t accept requests with an empty or whitespace-only system prompt and returns an HTTP 400 error. This behavior applies to the following nodes where system prompts are configured:
- LLM Prompt node: System Prompt field.
- Question node: LLM Instructions field.
- AI Agent node: the system prompt is built from Persona, Job Description, and Instructions and Context. The restriction applies only when all three fields are empty.
Add models
You can add a model using one of the following interfaces:Add models via GUI
You can add a model provided by Amazon Bedrock to Cognigy in Manage > AI & Voice Providers > Language Models. In Generative AI Connection, select an existing connection or click the + button to create one. The connection stores the credentials. To add the model, you’ll need the following parameters:- Standard model
- Custom model
Add models via the API
You can add either a standard or custom model using the Cognigy API POST /v2.0/largelanguagemodels request. Then, test your connection for the created model via the Cognigy API POST /v2.0/largelanguagemodels//test.Apply the model
To apply a model, follow these steps:- In the navigation menu of the project, go to Manage > AI & Voice Providers > Language Models.
- Click Assignments.
- Find the capability that should use the model. Capabilities are grouped under Runtime Features, Design-Time, and Knowledge. For Knowledge AI, select a model for Knowledge Search and Answer Extraction. To find models that support these features, refer to Model support by feature.
- Select the model in the capability’s list. If no model in the project supports the capability, None is selected and the list shows No model in this project supports this capability.
- Click Save changes.