@@ -223,6 +223,44 @@ Choose an AI provider below and follow the instructions:
223223
224224 Run a :ref: `Helm Upgrade <Simple Upgrade >` to apply the configuration.
225225
226+ .. tab-item :: Multiple providers
227+ :name: multiple-providers
228+
229+ Starting from version *0.22.1 *, Robusta supports an alternative way to configure AI models: using a YAML dictionary in your Helm values file.
230+
231+ This method allows you to configure multiple models at once, each with its own credentials.
232+
233+ Update your Helm values (``generated_values.yaml `` file) with the following configuration.
234+
235+ When multiple models are defined, the Robusta UI will allow users to choose a specific model when initiating an AI-based investigation.
236+
237+ .. admonition :: Model info
238+ :class: warning
239+
240+ When using multiple providers, the keys differ slightly from the single-provider case.
241+
242+ .. code-block :: yaml
243+
244+ enableHolmesGPT : true
245+
246+ holmes :
247+ modelCredentials : # sample configuration.
248+ openai :
249+ model : openai/gpt-4o
250+ api_key : <your-api-key>
251+ azure-low-budget :
252+ model : azure/team-low-budget
253+ api_base : <your-api-base> # fill in the base endpoint url of your azure deployment - e.g. https://my-org.openai.azure.com/
254+ api_version : " 2024-06-01"
255+ api_key : " {{ env.AZURE_API_KEY }}" # you can load the values from an environment variable as well.
256+ bedrock-devops :
257+ model : bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0 # your bedrock model.
258+ aws_region_name : us-east-1
259+ aws_access_key_id : <your-aws-access-key-id>
260+ aws_secret_access_key : <your-aws-secret-access-key>
261+
262+ Run a :ref: `Helm Upgrade <Simple Upgrade >` to apply the configuration.
263+
226264Configuring HolmesGPT Access to SaaS Data
227265----------------------------------------------------
228266
0 commit comments