Documentation
Characters

Characters

A character is essentially an AI assistant with a knowledge base and a specific set of capabilities. Technically, a character is a set of models (typically large language models) from a particular AI platform (OpenAI, Google AI, etc.) working together towards a common goal, using the custom data and functions available to them. For instance, an OpenAI character may use gpt-4-1106-preview for chat completion and whisper-1 for audio transcriptions.

Creating an Account and a Character

Currently, all characters use OpenAI assistants behind the scenes. Whenever you create a character on ProteusAI, a corresponding assistant is created in your OpenAI Playground (opens in a new tab). You can also attach a new ProteusAI character to an existing OpenAI assistant.

More AI platforms will be supported in the future.

Click the New Character button and fill in the required fields in the pop up modal.

This opens the character configuration page with 4 important menus: Instruction, Knowledge, Customizations, and Integrations.

Test Characters

It is now possible to create a free test character which does not require you to provide API credentials. To do so, simply turn on the Create as free test character option. Each account is entitled to a a maximum of one test character.

Test characters can be identified by the presence of the test tube icon.

🚫

Note that all test characters from all ProteusAI accounts are created in a shared environment. Consequently, integrations based on test characters may suffer performance degradation or API request rate limiting. Also, test characters may stop working or may be deleted at any time and without prior notice.

Computationally-Optimized Characters

It is now possible to create a character that is optimized for computation to enable features like advanced math calculations and code execution. To do so, simply turn on the Optimize for computation option. This behavior cannot be changed after the character is created.

Computationally-optimized characters are able to iteratively to solve challenging code and math problems. They typically do so by writing and running Python code in a sandboxed execution environment, and can generate files with data and images of graphs.

Computationally-optimized characters can accept these file types (which other characters may not be able to handle):

  • .csv
  • .jpeg, .jpg
  • .gif
  • .png
  • .pkl
  • .tar
  • .xlsx
  • .xml
  • .zip

Computationally-optimized characters can be identified by the presence of the math icon.


© 2024 ProteusAI. All rights reserved