Icon

2.1 - Simple ChatGPT prompt

You can easily download and run the workflow directly in your KNIME installation. We recommend that you use the latest version of the KNIME Analytics Platform for optimal performance.

This workflow shows how to connect to the model behind ChatGPT and send prompts to it.

The key difference between a LLM and a ChatModel is that a ChatModel can refer to previous messages (conversation)

In order to run the workflow you need an OpenAI API key. If you don't have one already, register with OpenAI and create a new API key under https://platform.openai.com/account/api-keys

URL: OpenAI API Keys https://platform.openai.com/account/api-keys

Prompt OpenAI's ChatGPT

  • This workflow shows how to connect to the model behind ChatGPT and send prompts to it.

  • In order to run the workflow you need an OpenAI API key. If you don't have one already, register with OpenAI and create a new API key under https://platform.openai.com/account/api-keys

  • To learn more about the workflow, click the left bar and check the description section.



Provide an (empty) conversation table that has two string columns (Type, Message)
Table Creator
OpenAI API Key
Credentials Configuration
Authenticate withAPI key
OpenAI Authenticator
Choose a model e.g.gpt-3.5-turbo
OpenAI Chat Model Connector
First message withempty conversation,but with system prefix
Chat Model Prompter
Second (human) messagewith conversation history
Chat Model Prompter
What was myfirst message?
Chat Model Prompter

Nodes

Extensions

Links