OpenAI

Configure HolmesGPT to use OpenAI's GPT models.

Setup

Get a paid OpenAI API key.

Note

Requires a paid OpenAI API key, not a ChatGPT Plus subscription.

Configuration

Holmes CLIHolmes Helm ChartRobusta Helm Chart

Using Environment Variables:

export OPENAI_API_KEY="your-openai-api-key"
holmes ask "what pods are failing?"

Using Command Line Parameters:

You can also pass the API key directly as a command-line parameter:

holmes ask "what pods are failing?" --api-key="your-api-key"

Create Kubernetes Secret:

kubectl create secret generic holmes-secrets \
  --from-literal=openai-api-key="sk-..." \
  -n <namespace>

Configure Helm Values:

# values.yaml
additionalEnvVars:
  - name: OPENAI_API_KEY
    valueFrom:
      secretKeyRef:
        name: holmes-secrets
        key: openai-api-key

# Configure at least one model using modelList
modelList:
  gpt-4.1:
    api_key: "{{ env.OPENAI_API_KEY }}"
    model: openai/gpt-4.1
    temperature: 0

  gpt-5:
    api_key: "{{ env.OPENAI_API_KEY }}"
    model: openai/gpt-5
    temperature: 1
    reasoning_effort: medium

# Optional: Set default model (use modelList key name)
config:
  model: "gpt-4.1"  # This refers to the key name in modelList above

Create Kubernetes Secret:

kubectl create secret generic robusta-holmes-secret \
  --from-literal=openai-api-key="sk-..." \
  -n <namespace>

Configure Helm Values:

# values.yaml
holmes:
  additionalEnvVars:
    - name: OPENAI_API_KEY
      valueFrom:
        secretKeyRef:
          name: robusta-holmes-secret
          key: openai-api-key

  # Configure at least one model using modelList
  modelList:
    gpt-4.1:
      api_key: "{{ env.OPENAI_API_KEY }}"
      model: openai/gpt-4.1
      temperature: 0

    gpt-5:
      api_key: "{{ env.OPENAI_API_KEY }}"
      model: openai/gpt-5
      temperature: 1
      reasoning_effort: medium

  # Optional: Set default model (use modelList key name)
  config:
    model: "gpt-4.1"  # This refers to the key name in modelList above

Available Models

Most OpenAI models are supported. For example:

# GPT-4.1 (default) - fast and decent responses
holmes ask "what pods are failing?"

# GPT-5 (more accurate but much slower)
holmes ask "what pods are failing?" --model="gpt-5"

Best Results

For more accurate results, consider using Anthropic's Claude models.

See benchmark results for a comparison.

GPT-5 Reasoning Effort

When using GPT-5 models, you can control the reasoning effort level. This allows you to balance between response quality and processing time/cost.

Holmes CLIHolmes Helm ChartRobusta Helm Chart

Using Environment Variables:

# Use minimal reasoning effort for faster responses
export REASONING_EFFORT="minimal"
holmes ask "what pods are failing?" --model="gpt-5"

# Use default reasoning effort
export REASONING_EFFORT="medium"
holmes ask "what pods are failing?" --model="gpt-5"

# Use high reasoning effort for complex investigations
export REASONING_EFFORT="high"
holmes ask "what pods are failing?" --model="gpt-5"

Configure in modelList:

# values.yaml
modelList:
  gpt-5-minimal:
    api_key: "{{ env.OPENAI_API_KEY }}"
    model: openai/gpt-5
    temperature: 1
    reasoning_effort: minimal  # Fast responses

  gpt-5-medium:
    api_key: "{{ env.OPENAI_API_KEY }}"
    model: openai/gpt-5
    temperature: 1
    reasoning_effort: medium  # Balanced (default)

  gpt-5-high:
    api_key: "{{ env.OPENAI_API_KEY }}"
    model: openai/gpt-5
    temperature: 1
    reasoning_effort: high  # Complex investigations

# Use the appropriate model based on your needs
config:
  model: "gpt-5-medium"

Configure in modelList:

# values.yaml
holmes:
  modelList:
    gpt-5-minimal:
      api_key: "{{ env.OPENAI_API_KEY }}"
      model: openai/gpt-5
      temperature: 1
      reasoning_effort: minimal  # Fast responses

    gpt-5-medium:
      api_key: "{{ env.OPENAI_API_KEY }}"
      model: openai/gpt-5
      temperature: 1
      reasoning_effort: medium  # Balanced (default)

    gpt-5-high:
      api_key: "{{ env.OPENAI_API_KEY }}"
      model: openai/gpt-5
      temperature: 1
      reasoning_effort: high  # Complex investigations

  # Use the appropriate model based on your needs
  config:
    model: "gpt-5-medium"

Available reasoning effort levels:

• minimal - Fastest responses, suitable for simple queries
• low - Balance between speed and quality
• medium - Standard reasoning depth (default)
• high - Deeper reasoning for complex problems

For more details on reasoning effort levels, refer to the OpenAI documentation.

Additional Resources

HolmesGPT uses the LiteLLM API to support OpenAI provider. Refer to LiteLLM OpenAI docs for more details.