OpenAI Batch Agent#

This guide provides an overview of how to set up the OpenAI Batch agent in your Flyte deployment.

Specify agent configuration#

Edit the relevant YAML file to specify the agent.

kubectl edit configmap flyte-sandbox-config -n flyte
tasks:
  task-plugins:
    enabled-plugins:
      - container
      - sidecar
      - k8s-array
      - agent-service
    default-for-task-types:
      - container: container
      - container_array: k8s-array
      - openai-batch: agent-service

Add the OpenAI API token#

  1. Install flyteagent pod using helm:

helm repo add flyteorg https://flyteorg.github.io/flyte
helm install flyteagent flyteorg/flyteagent --namespace flyte
  1. Set Your OpenAI API Token as a Secret (Base64 Encoded):

SECRET_VALUE=$(echo -n "<OPENAI_API_TOKEN>" | base64) && \
kubectl patch secret flyteagent -n flyte --patch "{\"data\":{\"flyte_openai_api_key\":\"$SECRET_VALUE\"}}"
  1. Restart development:

kubectl rollout restart deployment flyteagent -n flyte

Upgrade the Flyte Helm release#

helm upgrade <RELEASE_NAME> flyteorg/flyte-binary -n <YOUR_NAMESPACE> --values <YOUR_YAML_FILE>

Replace <RELEASE_NAME> with the name of your release (e.g., flyte-backend), <YOUR_NAMESPACE> with the name of your namespace (e.g., flyte), and <YOUR_YAML_FILE> with the name of your YAML file.

You can refer to the documentation to run the agent on your Flyte cluster.