In this guide, we will walk you through the process of creating a new prompt in Keywords AI and how to collaborate with your team.

​
Create a prompt in the API

You can also create a prompt in the API. Here are the 2 endpoints you need to use to create a prompt:

  1. https://api.keywordsai.co/api/prompts/ - Create a new prompt.
  2. https://api.keywordsai.co/api/prompts/<prompt_id>/versions/ - Create a new version of a prompt.

​
1. Create a new prompt

You can use the POST /prompts/ endpoint to create a new prompt. You need to provide the name, and description of the prompt.

import requests

url = "https://api.keywordsai.co/api/prompts/"
api_key = "YOUR_KEYWORDS_AI_API_KEY" # Replace with your actual Keywords AI API key
data = {
    "name": "Your Prompt Name",
    "description": "Your Prompt Description"
}
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

​
2. Find the prompt ID

Once you have created a prompt, you can find the prompt ID in the response, or you can go to the Prompts page and find the prompt ID in the prompt details.

​
3. Create a new version of the prompt

You can use the POST /api/prompts/<prompt_id>/versions/ endpoint to create a new version of a prompt. You need to provide the content of the prompt.

import requests

url = "https://api.keywordsai.co/api/prompts/<prompt_id>/versions/"
api_key = "YOUR_KEYWORDS_AI_API_KEY" # Replace with your actual Keywords AI API key
data = {
"description": "A description of the prompt version",
  "messages": [
    {"role": "system", "content": "You are a helpful {{role}}."},
    {"role": "user", "content": "Hello, how are you?"}
  ],
  "model": "gpt-3.5-turbo",
  "stream": false,
  "temperature": 0.7,
  "max_tokens": 256,
  "top_p": 1.0,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.0,
  "variables": {},
}
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

You just finished creating your first prompt in the code!

Was this page helpful?

Suggest editsRaise issue
Prompt in LLM proxyPrompt Playground