Documentation
  • Installation
  • Support
  • AnyAssistant Builder
    • Basics
    • Node Inspector
    • Functions & Skills
    • Working with Skills
    • Memory
    • Planning
    • Nodes
      • Control
        • User Input
        • Show User
        • Get Variable
        • Set Variable
        • Start
      • Invoke
        • Invoke Chat LLM
        • Invoke LLM With Planner
        • Invoke Planner
        • Invoke Native Function
        • Invoke Semantic Function
      • Model
        • ChatGPT
        • OpenAI Text
        • OpenAI Embedding
        • Hugging Face Embedding
        • Hugging Face Text
        • Load GGML Model
      • Memory
        • Simple Chat Memory
        • Contextual Chat Memory
      • Planner
        • Action Planner
        • Sequential Planner
      • Skills
        • Load Assistant Skills
        • Load Native Skills (C#)
        • Load Native Skills (Python)
        • Load Semantic Skills
      • OCR
        • Tesseract OCR
      • Data Source
        • Load CSV
        • Load PDF Files
        • Read Text File
        • Map Data Source
      • Vector Store
        • Postgres
        • Qdrant
        • Get Similar Vectors
        • Update Vector Store
Powered by GitBook
On this page
  • Inputs
  • Outputs

Was this helpful?

  1. AnyAssistant Builder
  2. Nodes
  3. Model

ChatGPT

Configures an instance representation of the Chat GPT model with the specified parameters. This is the same as configuring OpenAI Text node with the Chat GPT model name.

PreviousModelNextOpenAI Text

Last updated 1 year ago

Was this helpful?

Inputs

API Key

The OpenAI Api key. Please visit your page to retrieve the API key.

Temperature

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

Top P

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

Presence Penalty

A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood of talking about new topics.

Frequency Penalty

A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood of repeating the same line verbatim.

Max Tokens

The model's context length limits the input and generated tokens' total length.

Stop Words

Up to 4 sequences of comma-separated text where the API will stop generating further tokens.

Outputs

Language Model

An instance of the Chat GPT model with the specified parameters.

The maximum number of to generate in the chat completion.

API Keys
See more information about frequency and presence penalties.
See more information about frequency and presence penalties.
tokens