/
Agent

Agent

Agents are configurable objects you can have to scale ChatGPT.

To configure an agent, all you need is an OpenAI API key and some basic configuration to make him understand what you want to do.

The usage of an agent can be for interacting with tickets (by getting data to edit tickets) or even as a JSM chat bot, that will consume your information and use as a response.

To invoke an agent

# Base Configuration api_key = "YOUR_OPENAI_API_KEY" agent_name = "Support Bot" # Getting your Agent agent = Agent(api_key, agent_name) # Set his knowledge agent.set_system_instructions("Please provide a response based on the examples.") agent.add_example_output("I'm sorry to hear that. Let me see what I can do to help.") agent.add_example_output("Thank you for reaching out. I'll assist you with this.") agent.add_example_output("Sure, I can help you with that. Let's find a solution together.") # Get your response response = agent.get_response("I'm having trouble accessing my account.")

The base configuration to your agent is

temperature = 0.41 max_tokens = 256 top_p = 1 frequency_penalty = 0.0 presence_penalty = 0.0

To override any of those configurations

agent.temperature = 0.41 agent.max_tokens = 256 agent.top_p = 1 agent.frequency_penalty = 0.0 agent.presence_penalty = 0.0

 

Related content

OpenAI
More like this
Telegram
More like this
Environment Variables
Environment Variables
More like this
Conditions & Validators
Conditions & Validators
More like this
Jira Align
Jira Align
More like this
Limitations in Automation for Jira usage, what to do? Roll to Premium or get an app instead?
Limitations in Automation for Jira usage, what to do? Roll to Premium or get an app instead?
More like this

Easy for Jira - Python Automations, 2023