Text Generation

Text Generation

Text Generation services support Home Assistant Assist, AI Tasks, and direct automation calls through response services.

Common Uses

• Use the generated Conversation entity with Assist.
• Use the generated AI Task entity for data generation.
• Call groq.generate_text from scripts and automations.
• Call groq.generate_structured when an automation needs JSON that follows a schema.

Basic Service Call

action: groq.generate_text
data:
  prompt: Summarize the current home status for a dashboard notification.
  model: llama-3.1-8b-instant
  temperature: 0.2
response_variable: groq_text

Advanced Request Options

The Text Generation setup flow includes options for:

• model
• system prompt
• temperature
• maximum completion tokens
• top-p
• stop sequences
• seed
• service tier
• streaming Assist responses
• reasoning effort and reasoning format for supported models
• prompt caching for supported models
• structured outputs for supported models
• additional request body options

Use request_body_options for Groq chat completion fields that are not exposed as dedicated Home Assistant controls.

action: groq.generate_text
data:
  prompt: Create a short goodnight message.
  model: openai/gpt-oss-20b
  request_body_options:
    user: home-assistant
    metadata:
      workflow: bedtime
response_variable: groq_text

Structured Outputs

Use groq.generate_structured when you want the response to follow a JSON Schema.

action: groq.generate_structured
data:
  prompt: Extract the room, device, and requested action from "turn off the kitchen lights".
  model: openai/gpt-oss-20b
  strict: true
  schema_name: home_intent
  schema:
    type: object
    properties:
      room:
        type: string
      device:
        type: string
      action:
        type: string
    required:
      - room
      - device
      - action
    additionalProperties: false
response_variable: groq_structured

Built-In Fallback Models

The setup flow prefers live Groq model discovery. If discovery is unavailable, the integration has built-in fallback model IDs including:

• llama-3.1-8b-instant
• llama-3.3-70b-versatile
• openai/gpt-oss-20b
• openai/gpt-oss-120b
• openai/gpt-oss-safeguard-20b
• qwen/qwen3-32b
• groq/compound
• groq/compound-mini

Reasoning and prompt caching options are only offered for models known to support them.