This node establishes a connection with an OpenAI Large Language Model (LLM). After successfully authenticating using the OpenAI Authenticator node, you can select an LLM from a predefined list or explore advanced options to get a list of all models available for your API key (including fine-tunes). Note that only models compatible with OpenAI's Completions API will work with this node (unfortunately this information is not available programmatically).
If you a looking for gpt-3.5-turbo (the model behind ChatGPT) or gpt-4, check out the OpenAI Chat Model Connector node.
Select the OpenAI model ID to be used.
Select from a list of all available OpenAI models. The model chosen has to be compatible with OpenAI's Completions API.
The maximum number of tokens to generate.
The token count of your prompt plus max_tokens cannot exceed the model's context length.
Sampling temperature to use, between 0.0 and 2.0. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 for ones with a well-defined answer. It is generally recommend altering this or top_p but not both.
How many chat completion choices to generate for each input message. This parameter generates many completions and can quickly consume your token quota.
An alternative to sampling with temperature, where the model considers the results of the tokens (words) with top_p probability mass. Hence, 0.1 means only the tokens comprising the top 10% probability mass are considered.
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.
A zipped version of the software site can be downloaded here.
Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.Try NodePit Runner!
Do you have feedback, questions, comments about NodePit, want to support this platform, or want your own nodes or workflows listed here as well? Do you think, the search results could be improved or something is missing? Then please get in touch! Alternatively, you can send us an email to firstname.lastname@example.org, follow @NodePit on Twitter or botsin.space/@nodepit on Mastodon.
Please note that this is only about NodePit. We do not provide general support for KNIME — please use the KNIME forums instead.