Import

Automatically version and manage your prompts from your codebase, or create and edit them in the UI.

What is Prompt Management?

Helicone’s prompt management provides a seamless way for users to version, track and optimize their prompts used in their AI applications.

Example: A prompt template designed for a course generation application.

Why manage prompts in Helicone?

Once you set up prompts in Helicone, your incoming requests will be matched to a helicone-prompt-id, allowing you to:

• version and track iterations of your prompt over time.
• maintain a dataset of inputs and outputs for each prompt.
• generate content using predefined prompts through our Generate API.

Quick Start

Prerequisites

Please set up Helicone in proxy mode using one of the methods in the Starter Guide.

Not sure if proxy is for you? We’ve created a guide to explain the difference between Helicone Proxy vs Helicone Async integration.

Create prompt templates

As you modify your prompt in code, Helicone automatically tracks the new version and maintains a record of the old prompt. Additionally, a dataset of input/output keys is preserved for each version.

• Typescript / Javascript
• Python
• Packageless (cURL)

1

Install the package

npm install @helicone/prompts

2

Import hpf

import { hpf } from "@helicone/prompts";

3

Add `hpf` and identify input variables

By prefixing your prompt with hpf and enclosing your input variables in an additional {}, it allows Helicone to easily detect your prompt and inputs. We’ve designed for minimum code change to keep it as easy as possible to use Prompts.

const location = "space";
const character = "two brothers";
const promptInput = hpf`
Compose a movie scene involving ${{ character }}, set in ${{ location }}
`;

Static Prompts with hpstatic

In addition to hpf, Helicone provides hpstatic for creating static prompts that don’t change between requests. This is useful for system prompts or other constant text that you don’t want to be treated as variable input.

To use hpstatic, import it along with hpf:

import { hpf, hpstatic } from "@helicone/prompts";

Then, you can use it like this:

const systemPrompt = hpstatic`You are a helpful assistant.`;
const userPrompt = hpf`Write a story about ${{ character }}`;

The hpstatic function wraps the entire text in <helicone-prompt-static> tags, indicating to Helicone that this part of the prompt should not be treated as variable input.

Change input name

To rename your input or have a custom input, change the key-value pair in the passed dictionary to the string formatter function:

content: hpf`Write a story about ${{ "my_magical_input": character  }}`,

4

Assign an id to your prompt

Assign a Helicone-Prompt-Id header to your LLM request.

Assigning an id allows us to associate your prompt with future versions of your prompt, and automatically manage versions on your behalf.

headers: {
  "Helicone-Prompt-Id": "prompt_story",
},

1

Install the package

npm install @helicone/prompts

2

Import hpf

import { hpf } from "@helicone/prompts";

3

Add `hpf` and identify input variables

By prefixing your prompt with hpf and enclosing your input variables in an additional {}, it allows Helicone to easily detect your prompt and inputs. We’ve designed for minimum code change to keep it as easy as possible to use Prompts.

const location = "space";
const character = "two brothers";
const promptInput = hpf`
Compose a movie scene involving ${{ character }}, set in ${{ location }}
`;

Static Prompts with hpstatic

In addition to hpf, Helicone provides hpstatic for creating static prompts that don’t change between requests. This is useful for system prompts or other constant text that you don’t want to be treated as variable input.

To use hpstatic, import it along with hpf:

import { hpf, hpstatic } from "@helicone/prompts";

Then, you can use it like this:

const systemPrompt = hpstatic`You are a helpful assistant.`;
const userPrompt = hpf`Write a story about ${{ character }}`;

The hpstatic function wraps the entire text in <helicone-prompt-static> tags, indicating to Helicone that this part of the prompt should not be treated as variable input.

Change input name

To rename your input or have a custom input, change the key-value pair in the passed dictionary to the string formatter function:

content: hpf`Write a story about ${{ "my_magical_input": character  }}`,

4

Assign an id to your prompt

Assign a Helicone-Prompt-Id header to your LLM request.

Assigning an id allows us to associate your prompt with future versions of your prompt, and automatically manage versions on your behalf.

headers: {
  "Helicone-Prompt-Id": "prompt_story",
},

1

Install the package

pip install helicone_prompts

2

Import hpf

from helicone_prompts import hpf, hpstatic

3

Add `hpf` and identify input variables

By prefixing your prompt with hpf and providing your input variables as keyword arguments, it allows Helicone to easily detect your prompt and inputs. We’ve designed for minimum code change to keep it as easy as possible to use Prompts.

location = "space"
character = "two brothers"
prompt_input = hpf(
    "Compose a movie scene involving {character}, set in {location}",
    character=character,
    location=location
)

Static Prompts with hpstatic

In addition to hpf, Helicone provides hpstatic for creating static prompts that don’t change between requests. This is useful for system prompts or other constant text that you don’t want to be treated as variable input.

To use hpstatic, import it along with hpf:

from helicone_prompts import hpf, hpstatic

Then, you can use it like this:

system_prompt = hpstatic("You are a helpful assistant.")
user_prompt = hpf("Write a story about {character}", character=character)

The hpstatic function wraps the entire text in <helicone-prompt-static> tags, indicating to Helicone that this part of the prompt should not be treated as variable input.

Change input name

To rename your input or have a custom input, use a different keyword argument name:

content = hpf(
    "Write a story about {my_magical_input}",
    my_magical_input=character
)

4

Assign an id to your prompt

Assign a Helicone-Prompt-Id header to your LLM request.

Assigning an id allows us to associate your prompt with future versions of your prompt, and automatically manage versions on your behalf.

headers = {
    "Helicone-Prompt-Id": "prompt_story"
}

Currently, we only support packages for TypeScript and JavaScript for easy integration. For other users, we recommend manually implementing input variables as follows:

1

Identify the input variable, and create a key name.

Given the below string, let’s say a secret agent is our inputted variable. Let’s name our key character.

Write a story about a secret agent

2

Add helicone-prompt-input tags

Add <helicone-prompt-input key="<INPUT_ID>"> before your input variable, and </helicone-prompt-input> after, where INPUT_ID is your key name. In this example, key="character":

Write a story about <helicone-prompt-input key="character" >a secret agent</helicone-prompt-input>

Don’t worry, Helicone will remove these tags for you before your prompt is sent to your LLM.

It is crucial that each key has a unique identifier; otherwise, the same variable will be replaced in multiple places.

Static Prompts

For static prompts, you can manually wrap static parts of your prompt in <helicone-prompt-static> tags:

<helicone-prompt-static>You are a helpful assistant.</helicone-prompt-static>
Write a story about <helicone-prompt-input key="character">a secret agent</helicone-prompt-input>

This tells Helicone that the first part of the prompt is static and should not be treated as variable input.

3

Tag your prompt

In order to securely ensure that we know when and how to parse and categorize your prompt, please append the following header to your LLM request.

Helicone-Prompt-Id: you_prompt_id

The id must not include any spaces or special characters. Underscores and dashes are acceptable.

4

Make a request

You just created a prompt template! Helicone will now keep track of all of your inputs for you. Rest assured that all of the helicone-prompt-input tags will be removed before your prompt is sent to your LLM.

Put it together

Let’s say we have an app that generates a short story, where users are able to input their own character. For example, the prompt is “Write a story about a secret agent”, where the character is “a secret agent”.

• Typescript / Javascript example
• Python example
• Packageless (cURL) example

// 1. Add imports
import { hpf, hpstatic } from "@helicone/prompts";

const chatCompletion = await openai.chat.completions.create(
  {
    messages: [
      {
        role: "system",
        // 2. Use hpstatic for static prompts
        content: hpstatic`You are a creative storyteller.`,
      },
      {
        role: "user",
        // 3: Add hpf to any string, and nest any variable in additional brackets `{}`
        content: hpf`Write a story about ${{ character }}`,
      },
    ],
    model: "gpt-3.5-turbo",
  },
  {
    // 4. Add Prompt Id Header
    headers: {
      "Helicone-Prompt-Id": "prompt_story",
    },
  }
);

// 1. Add imports
import { hpf, hpstatic } from "@helicone/prompts";

const chatCompletion = await openai.chat.completions.create(
  {
    messages: [
      {
        role: "system",
        // 2. Use hpstatic for static prompts
        content: hpstatic`You are a creative storyteller.`,
      },
      {
        role: "user",
        // 3: Add hpf to any string, and nest any variable in additional brackets `{}`
        content: hpf`Write a story about ${{ character }}`,
      },
    ],
    model: "gpt-3.5-turbo",
  },
  {
    // 4. Add Prompt Id Header
    headers: {
      "Helicone-Prompt-Id": "prompt_story",
    },
  }
);

# 1. Add imports
from helicone_prompts import hpf, hpstatic

response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {
            "role": "system",
            # 2. Use hpstatic for static prompts
            "content": hpstatic("You are a creative storyteller.")
        },
        {
            "role": "user",
            # 3. Call hpf with a string and provide variables as keyword arguments
            "content": hpf("Write a story about {character}", character="a secret agent")
        }
    ],
    # 4. Add Prompt Id Header
    headers={
      "Helicone-Prompt-Id": "prompt_story",
    }
)

openai.ChatCompletion.create(
  model="[DEPLOYMENT]",
  # Manually add starting and ending tags with before and after variables
  messages=[{"role": "User", "content": f'Write a story about <helicone-prompt-input key="character" >{character} </helicone-prompt-input>'}],
  headers={
    # Add Prompt Id header
    "Helicone-Prompt-Id": "[my_prompt_id]",
  }
)

If you want more package support, please reach out to [e-mail].

Run experiments

Once you’ve set up prompt management, you can use Helicone’s Experiments feature to test and improve your prompts.

Local testing

Many times in development, you may want to test your prompt locally before deploying it to production and you don’t want Helicone to track new prompt versions.

• Typescript / Javascript
• Python

To do this, you can set the Helicone-Prompt-Mode header to testing in your LLM request. This will prevent Helicone from tracking new prompt versions.

headers: {
  "Helicone-Prompt-Mode": "testing",
},

To do this, you can set the Helicone-Prompt-Mode header to testing in your LLM request. This will prevent Helicone from tracking new prompt versions.

headers: {
  "Helicone-Prompt-Mode": "testing",
},

To do this, you can set the Helicone-Prompt-Mode header to testing in your LLM request. This will prevent Helicone from tracking new prompt versions.

headers={
        "Helicone-Prompt-Mode": "testing"
    },

FAQ

How can I improve my LLM app's performance?

Improving your LLM app primarily revolves around sophisticated prompt engineering. Here are some key techniques to optimize your prompt:

1. Be specific and clear.
2. Use structured formats.
3. Leverage role-playing.
4. Implement few-shot learning.

For more best practices, see best practices of prompt engineering.

Does Helicone own my prompts?

Helicone does not own your prompts. We simply provide a logging and observability platform that captures and securely stores your LLM interaction data. When you use our UI, prompts are temporarily stored in our system, but when using code-based integration, prompts remain exclusively in your codebase. Our commitment is to offer transparent insights into your LLM interactions while ensuring your intellectual property remains completely under your control.

How does the version indexing work?

In Helicone, you may notice that some of your prompt versions are labeled as V2.0, while others are labeled V2.1. Major versions (i.e., V1.0, V2.0, V3.0) are your prompts in production. Minor versions (V1.1, V1.2, V1.3) are experiment versions that are created in Helicone, which were forked off of your production version V1.0 in this example.