Significant-Gravitas/AutoGPT · error · ValueError

Missing Ideogram API key

Error message

Missing Ideogram API key

What it means

ValueError raised in generate_agent_image_v2() when the Ideogram credentials object has an empty/None api_key. It is a hard precondition: the v2 image-generation path (chosen when the deployment uses Ideogram) refuses to run without the key, and the ValueError then propagates (typically wrapped by the route into a 500/400 depending on handlers).

Source

Thrown at autogpt_platform/backend/backend/api/features/store/image_gen.py:42

class ImageStyle(str, Enum):
    DIGITAL_ART = "digital art"


async def generate_agent_image(agent: GraphBaseMeta | AgentGraph) -> io.BytesIO:
    if settings.config.use_agent_image_generation_v2:
        return await generate_agent_image_v2(graph=agent)
    else:
        return await generate_agent_image_v1(agent=agent)


async def generate_agent_image_v2(graph: GraphBaseMeta | AgentGraph) -> io.BytesIO:
    """
    Generate an image for an agent using Ideogram model.
    Returns:
        str: The URL of the generated image
    """
    if not ideogram_credentials.api_key:
        raise ValueError("Missing Ideogram API key")

    from backend.blocks.ideogram import (
        AspectRatio,
        ColorPalettePreset,
        IdeogramModelBlock,
        IdeogramModelName,
        MagicPromptOption,
        StyleType,
        UpscaleOption,
    )

    name = graph.name
    description = f"{name} ({graph.description})" if graph.description else name

    prompt = (
        "Create a visually striking retro-futuristic vector pop art illustration "
        f'prominently featuring "{name}" in bold typography. The image clearly and '
        f"literally depicts a {description}, along with recognizable objects directly "

View on GitHub (pinned to 9c8bb5550f)

Solutions

1. Set the Ideogram API key in backend settings/secrets (env var per backend/.env.default naming) for the environment running image generation.
2. Restart/redeploy the backend so Settings picks up the new value.
3. If Ideogram is not available, disable the v2 path so the code falls back to generate_agent_image_v1 (which needs the Replicate key instead).

Example fix

// before: key missing, v2 path raises ValueError
# .env / environment
# IDEOGRAM_API_KEY=

// after
IDEOGRAM_API_KEY=<your-ideogram-key>

from backend.util.settings import Settings

def ideogram_ready() -> bool:
    return bool(Settings().secrets.ideogram_api_key)  # adjust attr to credentials source

try:
    image = await store_image_gen.generate_agent_image(agent=graph)
except ValueError as e:
    if "Ideogram" in str(e):
        raise HTTPException(503, "Image generation is not configured") from e
    raise

When it happens

Trigger: POST to the agent-image generation endpoint on a deployment flagged for v2 while IDEOGRAM_API_KEY is unset/empty in the backend settings/secrets (env var missing in docker-compose, .env not loaded, or secret not provisioned in the deployed environment).

Common situations: New environment bootstrap where only the Replicate key was configured; v1→v2 rollout toggled before secrets were added; local dev copying .env.default without adding the Ideogram key.

Related errors

• Missing Replicate API key in settings
• Invalid Replicate API token
• Unexpected output format from the model.
• Image generation failed: {str(e)}
• GCS media bucket is not configured

AI-assisted analysis of Significant-Gravitas/AutoGPT@9c8bb5550f (2026-08-14). Data as JSON: /api/errors/5d8f9bd6f6726bd8. Report an issue: GitHub.