AI Write
Controlled node
Overview
A workhorse node for text generation tasks, AI Write uses a large language model to generate text based on a provided prompt. By default the output of the generation is locked to a seed (1) meaning it should generate the same output everytime, although occasionally this system fails. If you want a different output everytime then you can select randomize output. If none of the node inputs change, and randomize is unchecked, then the generation output is cached to allow for faster development.
Model options
Intellectible provides a number of different text generation models to choose from for AI Write. Each has a different token cost and performance profile.
| Model | Description | Context Size |
|---|---|---|
| ultra light | Cheap and fast lightweight model, great for summarizing. Uses fewer tokens. | 128000 |
| standard | State of the art instruction tuned model suitable for most text generation tasks | 128000 |
| advanced reasoning | Excellent for reasoning tasks but nearly 10x more expensive than standard. Use sparingly. | 128000 |
| large context | Very large context window model | 10000000 |
Your AI Write operation won't work if you exceed the model context window size. The sum of your token input and maximum output should be less than the context window size. Use the Token Count node to check the token count of any text.
Output events
There are two output event options for this node.
- Stream: This allows you to receive the output as it is generated, this is useful for output into chat interfaces or other applications where you want to see the text as it is being generated.
- Done: This fires when the node has finished running, this is useful for triggering other nodes or actions in your workflow.
Inputs
| Input | Type | Description | Default |
|---|---|---|---|
| Model | Enum | The model to use for text generation. | standard |
| Prompt | Text | Provides the context or topic for the AI to write about. | - |
| Max Tokens | Number | Specifies the maximum number of tokens (words or characters) to be generated. | 2000 |
| Temperature | Number | Controls the level of randomness or creativity in the generated text. | 0.7 |
| Seed | Number | Sets the random seed for the AI model, allowing for reproducibility of results. | 1 |
| Randomize Output | Boolean | Determines whether the output should be randomized or not. If randomized the seed is ignored. | - |
| Run | Event | Fires when the node starts running | - |
Outputs
| Output | Type | Description |
|---|---|---|
| Output | Text | Contains the generated text. |
| Stream | Event | Fires each time the output accumulates. |
| Done | Event | Fires when the node has finished |