Skip to main content
A single organization toggle unlocks AI-assisted survey translation and AI chart creation across the app. Requires AI_PROVIDER, AI_MODEL, and the matching provider configuration on the instance.

​
Kubernetes Helm

The Formbricks Helm chart can deploy a bundled Qwen/vLLM runtime for Smart functionality. This path is disabled by default and requires GPU-capable Kubernetes nodes. 
llm:
  enabled: true
When llm.enabled is true, the chart deploys the vLLM router and Qwen serving engine. By default it also points the Formbricks app at the in-cluster OpenAI-compatible endpoint by injecting the required AI_* environment variables. Set llm.autoConfigureApp=false if you want the chart to deploy Qwen/vLLM but prefer to configure the app provider manually.

​
Docker Compose

The Docker stack can deploy the same Qwen/vLLM runtime through an opt-in Compose profile. This path is disabled by default and requires a GPU-capable Docker host with the NVIDIA Container Toolkit installed. 
COMPOSE_PROFILES=qwen
AI_PROVIDER=openai-compatible
AI_MODEL=qwen3-14b-awq
AI_OPENAI_COMPATIBLE_BASE_URL=http://vllm:8000/v1
AI_OPENAI_COMPATIBLE_PROVIDER_NAME=vllm
AI_OPENAI_COMPATIBLE_SUPPORTS_STRUCTURED_OUTPUTS=1
If you use the optional taxonomy service and want it to share the bundled Qwen runtime, start Docker Compose with COMPOSE_PROFILES=qwen,taxonomy and point TAXONOMY_LLM_BASE_URL at http://vllm:8000/v1.

​
External Providers

Keep llm.enabled=false when you use Google Vertex, Azure, AWS Bedrock, or your own OpenAI-compatible runtime. Configure those providers with deployment.env in your Helm values or with environment variables in your deployment platform. Read the full guide: AI Features.