Skip to main content
POST
https://api.jigsawstack.com
/
v1
/
prompt_engine
import { JigsawStack } from "jigsawstack";

const jigsaw = JigsawStack({ apiKey: "your-api-key" });

const response = await jigsaw.prompt_engine.create({
  "prompt": "Tell me a story about {about}",
  "inputs": [
        {
              "key": "about",
              "optional": false,
              "initial_value": "Leaning Tower of Pisa"
        }
  ],
  "return_prompt": "Return the result in a markdown format",
  "prompt_guard": [
        "sexual_content",
        "defamation"
  ]
})

{
  "success": true,
  "prompt_engine_id": "dea57da0-eea1-400f-b5df-2f6216a4c2b9",
  "optimized_prompt": "Write a detailed and engaging story about {about}, including vivid descriptions, well-developed characters, and a clear beginning, middle, and end.",
  "_usage": {
        "input_tokens": 58,
        "output_tokens": 61,
        "inference_time_tokens": 1121,
        "total_tokens": 1240
  }
}
🎉 Exciting News! We’ve enhanced Prompt Engine with powerful new capabilities. Meet Interfaze - our advanced LLM that takes your AI workflows to the next level, built for debvelopers, with improved performance better organization, and enhanced features.
​
x-api-key
string
required
Your JigsawStack API key

​
Body

​
name
string
Name of the prompt engine. Maximum 300 characters.
​
prompt
string
required
The prompt. Maximum character limit is 500000. Prompt supports dynamic inputs. See example below.
​
inputs
array<object>
The prompt inputs. See example below.
​
return_prompt
string | array | object
How the prompt result should be returned or formatted. See examples below
​
prompt_guard
array<string>
Include this to guard against unsafe inputs from users. Supported values:
  • defamation
  • privacy
  • hate
  • sexual_content
  • elections
  • code_interpreter_abuse
  • indiscrimate_weapons
  • specialized_advice
​
optimize_prompt
boolean
Include this to optimize the prompt for best results. True by default.
​
use_internet
boolean
Include this to allow prompt engine to use the internet.

​
Sample Prompt Payload

  • String return_prompt
{
    prompt: "Tell me a story about {about}",
    inputs: [
      {
        key: "about",
        optional: false,
        initial_value: "Leaning Tower of Pisa",
      },
    ],
    return_prompt: "Return the result in a markdown format",
    "prompt_guard": ["sexual_content", "defamation"]
  }
  • Array<object> return_prompt

{
    prompt: "Tell me a story about {about}",
    inputs: [
      {
        key: "about",
        optional: "false",
        initial_value: "Leaning Tower of Pisa",
      },
    ],
    return_prompt: [{ excerpt: "short story text", summary: "summary of story" }],
    "prompt_guard": ["sexual_content", "defamation"]
  }
  • Object return_prompt
{
    prompt: "Tell me a story about {about}",
    inputs: [
      {
        key: "about",
        optional: false,
        initial_value: "Leaning Tower of Pisa",
      },
    ],
    return_prompt: { excerpt: "short story text", summary: "summary of story" },
    "prompt_guard": ["sexual_content", "defamation"]
  }

​
Header

​
x-api-key
string
required
Your JigsawStack API key

​
Response

​
success
boolean
Indicates whether the call was successful.
​
_usage
object
Usage information for the API call.
​
log_id
string
A unique identifier for the request
import { JigsawStack } from "jigsawstack";

const jigsaw = JigsawStack({ apiKey: "your-api-key" });

const response = await jigsaw.prompt_engine.create({
  "prompt": "Tell me a story about {about}",
  "inputs": [
        {
              "key": "about",
              "optional": false,
              "initial_value": "Leaning Tower of Pisa"
        }
  ],
  "return_prompt": "Return the result in a markdown format",
  "prompt_guard": [
        "sexual_content",
        "defamation"
  ]
})

{
  "success": true,
  "prompt_engine_id": "dea57da0-eea1-400f-b5df-2f6216a4c2b9",
  "optimized_prompt": "Write a detailed and engaging story about {about}, including vivid descriptions, well-developed characters, and a clear beginning, middle, and end.",
  "_usage": {
        "input_tokens": 58,
        "output_tokens": 61,
        "inference_time_tokens": 1121,
        "total_tokens": 1240
  }
}