Change this:
While AI Assistant is compatible with many different models, our testing found increased quality with Azure 32k, and faster, more cost-effective responses with Claude 3 Haiku and OpenAI GPT4 Turbo. For more information, refer to the Large language model performance matrix.
To this:
While AI Assistant is compatible with many different models, we recommend referencing the Large language model performance matrix for leveraging a model that performs well with a desired feature set.
From within your Azure OpenAI deployment, select Model deployments, then click Manage deployments.
On the Deployments page, select Create new deployment.
Under Select a model, choose gpt-4 or gpt-4-32k.
If you select gpt-4, set the Model version to 0125-Preview.
If you select gpt-4-32k, set the Model version to default.
To this.
Now, set up the Azure OpenAI model:
From within your Azure OpenAI deployment, select Model deployments, then click Manage deployments.
On the Deployments page, select Create new deployment.
Under Select a model, choose gpt-4o or gtp-4 turbo.
Set the model version to "Auto-update to default".
Charelzard
commented
2 weeks ago
Description
The following pages need updated:
AI Assistant: https://www.elastic.co/guide/en/security/8.15/security-assistant.html#set-up-ai-assistant
Change this: While AI Assistant is compatible with many different models, our testing found increased quality with Azure 32k, and faster, more cost-effective responses with Claude 3 Haiku and OpenAI GPT4 Turbo. For more information, refer to the Large language model performance matrix.
To this: While AI Assistant is compatible with many different models, we recommend referencing the Large language model performance matrix for leveraging a model that performs well with a desired feature set.
Azure OpenAI: https://www.elastic.co/guide/en/security/8.15/assistant-connect-to-azure-openai.html
Change this: Now, set up the Azure OpenAI model:
From within your Azure OpenAI deployment, select Model deployments, then click Manage deployments. On the Deployments page, select Create new deployment. Under Select a model, choose gpt-4 or gpt-4-32k.
If you select gpt-4, set the Model version to 0125-Preview. If you select gpt-4-32k, set the Model version to default.
To this.
Now, set up the Azure OpenAI model:
From within your Azure OpenAI deployment, select Model deployments, then click Manage deployments. On the Deployments page, select Create new deployment. Under Select a model, choose gpt-4o or gtp-4 turbo.
Set the model version to "Auto-update to default".
Background & resources
See Comments Above
Which documentation set does this change impact?
ESS and serverless
ESS release
N/A
Serverless release
N/A
Feature differences
See Above
API docs impact
N/A
Prerequisites, privileges, feature flags
N/A