Role
Role
Embedded Files
WorkGPT allows you to configure and deploy an Autonomous AI role. Name your custom AI and have it embark on any goal imaginable. WorkGpT is user-friendly compared to AutoGPT due to its UI and can be used by people from non-programming backgrounds. WorkGPT can create its own prompts while AutoGPT depends on user inputs.
Create Role
WorkGPT lets you create Characters and talk to them.Create Role
Select Role
Select and change the role during the chat.Select Role
App
App
Connect the apps you use every day to automate your work and be more productive.
Authentication
You can select one or more app by clicking the “Configuration” button next to each. Authentication
Connect Internal Server/Data
While WorkGPT does not limit you to using a maximum of services per chat, you can select as many services as you want.Connect Internal Server/Data
Task
Task
Task is a built-in feature of WorkGPT that lets you set up a task to run at a specific time.
Frequency:
Daily
Weekly
Monthly
Annually
Not repeat
Configuration
Configuration
OpenAI API Key
OpenAI API Key
Use your own OpenAI API key, you will have access to all models available without any token limits.
GPT Configuration
GPT Configuration
GPT model
- GPT 3.5
- GPT 3.5 16K
- GPT 4
Max HistoryThe number of previous utterances to include in the dialogue history used to generate the bot's response.
Max TokensThe maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length
Token limit for GPT 3.5: 4096 tokens
Token limit for GPT 3.5 16K: 16,384 tokens tokens
Token limit for GPT 4: 8192 tokens
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.
Frequency Penalty
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 to repeat the same line verbatim.
Presence Penalty
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with presence_penalty probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Function Call Configuration
Function Call Configuration
- Auto Run
- Auto Continue
Page updated
Report abuse