Actions2
Overview
This node enables chat interactions with Pollinations.AI models, supporting two main operations: sending a chat message and receiving a response, or chatting with a custom system prompt to set the AI's behavior. It is useful for integrating AI-driven conversational agents into workflows, allowing users to specify the AI model, conversation history, and various parameters like creativity, response length, and reasoning depth. Practical examples include customer support bots, virtual assistants, and AI-driven content generation.
Use Case Examples
- A customer support bot that uses the 'Chat' operation to respond to user queries with context from previous messages.
- An AI assistant that uses the 'Chat with System Prompt' operation to maintain a specific persona or behavior defined by a system prompt while interacting with users.
Properties
| Name | Meaning |
|---|---|
| Model | The AI model to use for chat, such as OpenAI GPT-5 Nano, Mistral, Gemini Search, or DeepSeek V3.1. |
| System Prompt | System prompt to set the AI's behavior, used only in the 'Chat with System Prompt' operation. |
| User Message | The user's chat message, required for the 'Chat with System Prompt' operation. |
| Conversation History | Previous conversation messages for context, including roles (user or assistant) and content. |
| Temperature | Controls creativity of the AI response, from 0.0 (strict) to 3.0 (wild). |
| Max Tokens | Maximum length of the AI's response in tokens. |
| Reasoning Effort | How deeply the AI thinks before responding, ranging from minimal to high. |
| Stream | Whether to get the response in real-time chunks for streaming. |
Output
JSON
response- The AI-generated response text.model- The AI model used for generating the response.messages- The array of messages sent to the AI, including system, user, and conversation history.assistantMessagerole- Role of the assistant in the response message.content- Content of the assistant's response message.
conversation- The full conversation including all messages and the assistant's response.fullResponse- The complete raw response object returned from the Pollinations.AI API.
Dependencies
- Pollinations.AI API token required in credentials
Troubleshooting
- Error if API token is missing: Ensure the Pollinations.AI API token is correctly added in the node credentials.
- If the API request times out or fails, check network connectivity and API service status.
- Invalid parameter values (e.g., temperature out of range) may cause errors; ensure inputs are within specified limits.