The GPT-4 block is powered by OpenAI’s GPT-4 conversation model. It is the most powerful model that we offer. It can be used for virtually any use case from problem solving to being a knowledge manager.

The GPT-4 block has 2 inputs and 1 output.

Inputs:

  • Prompt: The prompt has all the context the AI model needs to make any computation. For example, a prompt can be: “rank these resumes from best to worst” along with the resume files.
  • Instruction: The instruction is used to describe the assistant’s role in detail so it knows how you want it to act. You can reference the profession, personality traits, or behaviors you expect. For example, an instruction can be: “you are an assistant skilled at evaluating resumes based on quality of content.”

Output:

  • Response: The response returns the output from the GPT-4 model based on the instructions and prompt inputs provided for computation.

To make more powerful prompts, try using the Combine Text block

GPT-3.5 Turbo 16k CompliantGPT-4 8k Compliant