πText Block
Text blocks generate text based on a text prompt.
Title
Click the pencil icon next to the blockβs title to edit it. This is also the blockβs variable name, which can be used to dynamically populate data in other blocks.
Prompt
Write a prompt that guides the AI to generate your desired text.
Use variables within your prompt to dynamically add data from other blocks.
Variables
Variables can be used to dynamically populate data supplied by other blocks. Click on a variable name from the list to add it to anywhere in your prompt. Variable names match a blockβs title.
Advanced Text Block Controls
Model
Select which text generation model youβd like your glif to use. Supported models, as of 6/12/24, are:
Claude 3 - Opus (Anthropic) |
Claude 3 - Sonnet (Anthropic) |
Gemini Pro 1.5 (Google) |
Gemma - 7B - IT on Groq |
Llama 3 - 70B - Instruct (Meta) |
Llama 3 - 70B - 8192 on Groq |
Llama 3 - 8B - 8192 on Groq |
Mistral Large (Mistral AI) |
Nous Hermes 2 Mixtral 8x7B SFT (Nous Research) |
Chat GPT-3.5 Turbo (OpenAI) |
Chat GPT-4 (OpenAI) |
Chat GPT-4o (OpenAI) |
Sonar Medium Online (Perplexity AI) |
Text Output
Use the slider to amp up the creativity of the text output from βPredictableβ to βInsane.β
Max Tokens
Tokens are the individual units of text that the model processes. One token equals approximately four characters in the English language. More tokens = more characters in the output.
Last updated