Skip to content

Commit 1ef84bc

Browse files
committed
add docs about multiple providers
1 parent a030931 commit 1ef84bc

1 file changed

Lines changed: 38 additions & 0 deletions

File tree

docs/configuration/holmesgpt/index.rst

Lines changed: 38 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -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+
226264
Configuring HolmesGPT Access to SaaS Data
227265
----------------------------------------------------
228266

0 commit comments

Comments
 (0)