Triggers, integrations and model nodes
A short map of what ships. Every node's config fields are in the node reference.
Tier 1 integrations
Exposed through GET /api/integrations:
- HTTP request, configured webhook input, and webhook response
- Slack send message and Slack Events API trigger
- SMTP send email and IMAP email trigger
- Google Sheets read, append and update, and a polling trigger
- PostgreSQL query and polling trigger
- MySQL query
- MongoDB find, insert, update and aggregate
- Redis commands and Redis trigger
- GitHub issue, pull request and repository actions, and a signed GitHub webhook trigger
Trigger nodes
schedule_trigger, manual_trigger, webhook_input, form_trigger, chat_trigger, file_trigger, rss_trigger, sse_trigger, mcp_server_trigger, slack_trigger, github_webhook_trigger, google_sheets_trigger, postgres_trigger, redis_trigger, imap_email_trigger and error_trigger.
Message queue trigger nodes are registered for Kafka, RabbitMQ and MQTT with optional-dependency detection. Their long-lived consumers are intentionally held back until the corresponding client dependency and deployment path are configured.
To call a webhook, see Secure webhooks.
Chat model nodes
An Agent's chat_model attachment can use a dedicated provider node:
OpenAI Chat Model(openai_chat_model)Anthropic Chat Model(anthropic_chat_model)Ollama Chat Model(ollama_chat_model)OpenAI Compatible Chat Model(openai_compatible_chat_model)AI Gateway Chat Model(ai_gateway_chat_model)Azure OpenAI Chat Model(azure_openai_chat_model)Google Gemini Chat Model(google_gemini_chat_model)- The legacy generic
LLM Call(llm_call)
Azure node suite
Azure OpenAI Chat Model(azure_openai_chat_model)Embeddings Azure OpenAI(embeddings_azure_openai)Azure Storage(azure_storage)Azure Cosmos DB(azure_cosmos_db)Microsoft Azure Monitor(azure_monitor_http)Azure AI Search Vector Store(azure_ai_search_vector_store)
Credentials and operations: Azure nodes.
Qdrant
Qdrant Vector Store (qdrant_vector_store) has the actions get_ranked_documents, add_documents, retrieve_for_chain_tool and retrieve_for_ai_agent_tool. Qdrant is also available in RAG Retrieve with vectorStoreId = qdrant-vector-store. For env-backed local defaults, set QDRANT_ENDPOINT and QDRANT_API_KEY. See Vector stores.
What the connector and model nodes include
- Structured config forms in the editor (no free-form JSON for normal use)
- Dedicated node icons on the canvas and in the node library
- Secret-backed credentials via
secretRef.secretId - A
Test Connectionaction on connector nodes (POST /api/connectors/test) - A
Test Connectionaction on model nodes (POST /api/providers/test) - Execution support in the workflow engine, including a demo fallback mode for local development