AI Providers

Hedhog's built-in AI chat (AiService, POST /ai/chat) talks directly to OpenAI and Google Gemini — these are the only two providers the core module supports today.

Status: ✅ Implemented — OpenAI and Gemini both work through /ai/chat.

Quick Setup

Create an Integration Profile (type AI, provider openai or gemini) with an api_key at Settings → Integration Profiles
Go to Settings → Configurations → General, find AI Configuration, and point ai-openai-profile-id and/or ai-gemini-profile-id at that profile
Call POST /ai/chat with { message, provider } (provider defaults to openai) and confirm you get a real completion back

How It Works

Create an Integration Profile of type AI, provider openai or gemini, with an api_key in its config
Go to Settings → Configurations → General, find the AI Configuration section, and set the matching field — ai-openai-profile-id (OpenAI Profile) or ai-gemini-profile-id (Gemini Profile) — to that profile
AiService reads whichever profile is configured for the provider the caller requests (data.provider defaults to openai) and calls the corresponding API directly

If neither ai-openai-profile-id nor ai-gemini-profile-id is set, the server logs a warning on boot ("No AI profiles configured") but still starts — calls to /ai/chat simply fail until you configure at least one.

Default Models

data.model is optional on POST /ai/chat — if you leave it out, AiService falls back to:

Provider	Default model if `model` is left empty
`openai`	`gpt-4o-mini`
`gemini`	`gemini-1.5-flash`

Supported Providers

Provider	`integration_provider` slug	Model family
OpenAI	`openai`	GPT-4o, GPT-4, GPT-3.5 Turbo
Google Gemini	`gemini`	Gemini 2.0 Flash, Gemini 1.5 Pro/Flash

OpenAI

Console: platform.openai.com

Go to API keys and create a new secret key
Optionally create a project and restrict the key to it, and set usage limits under Settings → Limits so a bug somewhere can't run away with your budget

Config field	Description
`api_key`	OpenAI API key (`sk-…`)
`organization`	Optional — organization ID, only needed for multi-org accounts

Google Gemini

Console: aistudio.google.com or console.cloud.google.com

In AI Studio, click Get API key for the fastest path, or in GCP enable the Generative Language API and create credentials if you need the key tied to a billing project

Config field	Description
`api_key`	Gemini API key

Cost Considerations

Both providers charge per token (input + output) directly to your account — Hedhog adds no markup. Set a model per use case rather than defaulting everything to the most expensive option:

High quality / complex tasks: gpt-4o, gemini-1.5-pro
Balanced / default: gpt-4o-mini, gemini-1.5-flash
High volume / simple tasks: gpt-3.5-turbo, gemini-2.0-flash

Verify It Worked

Call /ai/chat with provider: "openai" and confirm you get a real completion back, not a 400
Call it again with provider: "gemini" and confirm the same

Troubleshooting

Symptom	Likely cause
"No AI profiles configured" warning on boot	Neither `ai-openai-profile-id` nor `ai-gemini-profile-id` is set — harmless until something calls `/ai/chat`
`400` from `/ai/chat`	The profile for the requested `provider` isn't set, doesn't exist, or has no `api_key` in its config
Response uses a different model than expected	You left `model` empty — Hedhog applied the per-provider default instead (see table above)