Prompts

Prompts are essential for interacting effectively with Large Language Models (LLMs). They serve as a specific way to communicate with LLMs, guiding them to generate desired responses. AI models often require fine-tuning of prompts to enhance performance.

In kis.ai, prompts are managed through YAML files in a product, located in the folder ai/prompts. As these files are part of the product git repository, their changes can be tracked over time. Prompts can be categorized, tagged, and searched for quick retrieval. kis.ai provides analytics and feedback mechanisms to help developers refine their prompts, ensuring high-quality responses from the LLMs.

Simple Prompts

Developers can define prompts in a structured manner, in multiple folders and YAML files to match the complexity of the product and its context. Each prompt has a name and some natural language text to be sent to the LLM. Prompts are also essentially string templates, written in liquid, allowing developers to dynamically change the prompts to match the information passed by the end-users.

For most models, system-prompt and user-prompt are available and give the way to request the LLM on what is expected. The {{ parameter }} notation of liquid templates can be used to demarcate the dynamic sections of the prompt.

Example: ai/prompts/simple-prompts.yaml

prompts:
- name: email-template-gen
  system-prompt: You are an helpful executive assistant
  user-prompt: |
    Write {{ templatecount }} email templates to introduce {{your-brand}} in {{ charactercount }} characters or less
    by weaving in the specific trigger to {{ topic }} on {{ brand }}. Customer's firstname is {{ firstname }}
    and lastname is {{ lastname }}. My signature is {{ signature }}.
- name: linkedin-post-gen
  user-prompt: |
    Suggest titles of {{ count }} LinkedIn posts to introduce {{ product }} in sequence one for each day. The
    features to be highlighted are {{ featurelist }}.

In the above example, email-template-gen’s user-prompt will be translated into:

Write 5 email templates to introduce kis.ai in 150 characters or less
by weaving in the specific trigger to hotel management software on Sun and Sands Resorts.
Customer's firstname is Joe and lastname is Pescano. My signature is Wishing a sunny day, AP

With the following JSON payload to AI Gateway or AI Flow:

{
  "prompt": "email-template-gen",
  "parameters": {
    "templatecount": 5,
    "your-brand": "kis.ai",
    "charactercount": 150,
    "topic": "hotel management software",
    "brand": "Sun and Sands Resorts",
    "firstname": "Joe",
    "lastname": "Pescano",
    "signature": "Wishing a sunny day, AP"
  }
}

Few-shot Prompts

Few-shot prompting is a technique in natural language processing where a language model is provided with a small number of examples (typically a few) to understand the context or task it needs to perform.

With Plain Text

Question & Answer example

ai/prompts/few-shot-text.yaml

prompts:
- name: few-shot-prompt
  type: few-shot
  system-prompt: You are an helpful assistant, but give precise answers.
  samples-prefix: Give the response as a simple one or two word answer.
  samples-suffix: Do not respond with anything in addition to what is asked. Do not be too verbose.
  samples:
  - prompt: The Eiffel Tower, located in Paris, France, was completed in 1889 and stands 324 meters tall. Where is Eiffel tower located?
    content-type: text # default is text
    response: Paris, France.
  - prompt: The Eiffel Tower, located in Paris, France, was completed in 1889 and stands 324 meters tall. How tall is the Eiffel tower?
    response: 324 meters

When the user prompts:

In 1873, the three cities of Buda, Óbuda (Old Buda), and Pest were united to form Budapest, which was originally named "Pest-Buda". Budapest has a population of about 1.7 million people. What is the popoulation of Budapest?

They get the response:

1.7 million

This will be the sample JSON being sent to the AI Gateway:

{
    "prompt": "few-shots-prompt",
    "parameters": {
        "user-prompt": "please tell me a good story"
    }
}

Text generation example

The same YAML structure applies for text generation tasks.

With Inline Code

Generate YAML with inline samples

ai/prompts/entity-few-shot.yaml

prompts:
- name: few-shot-entity
  type: few-shot
  system-prompt: You are an helpful developer, helping a developer create a valid yaml.
  samples-prefix: Give a valid yaml as output.
  samples-suffix: Do not respond with anything in addition YAML. Include the YAML in triple backticks and also add the type yaml when after starting the triple backticks.
  backticks: true
  content-type: yaml
  samples:
  - prompt: Create entity person with fields id, firstname, lastname, age and address
    response: |
      entities:
      - name: person
        fields:
          - name: id
            type: int
            validations: []
          - name: firstname
            type: string
            validations:
              - type: length
                max: 12
          - name: lastname
            type: string
            validations:
              - type: length
                max: 12
          - name: age
            type: int
            validations: []
          - name: address
            type: string
            validations:
              - type: length
                max: 255
  - prompt: Create entity car with fields id, name, brand, type, price
    response: |
      entities:
        - name: car
          fields:
            - name: id
              type: int
              validations:
                - type: required
                - type: unique
                  message: should me unique for all entries
                - type: final
                  message: field cannot be updated
            - name: name
              type: string
              validations: []
            - name: brand
              type: string
              validations: []
            - name: type
              type: string
              validations: []
            - name: price
              type: string
              validations: []

When the user prompts:

create entity address with fields id, building, street, locality, city, state, country, code

The following YAML response is generated:

entities:
  - name: address
    fields:
      - name: id
        type: int
        validations:
          - type: required
          - type: unique
            message: should me unique for all entries
          - type: final
            message: field cannot be updated
      - name: building
        type: string
        validations: []
      - name: street
        type: string
        validations: []
      - name: locality
        type: string
        validations: []
      - name: city
        type: string
        validations: []
      - name: state
        type: string
        validations: []
      - name: country
        type: string
        validations: []
      - name: code
        type: string
        validations: []

With File Inclusion

Generate Vue Code

In this example prompt, user prompt will generate Vue code, based on the samples provided through code file inclusions.

ai/prompts/vue-kanban-prompt.yaml

- name: few-shot-kanbam
  type: few-shot
  system-prompt: You are an helpful developer, helping a developer create valid vue code.
  samples-prefix: Give a valid Vuejs code as output.
  samples-suffix: Do not respond with anything in addition to Vue code.
  backticks: true
  content-type: vue
  samples:
  - prompt: Create a kanban board for bug entity with states new, inprogress, fixed, closed. The attribute values are access-key:aid, discriminator:state, date-key:date
    file: vue-kis-kanban/Example01.vue
  - prompt: Another example, a kanban board for a bug-detection entity, having 3 states detected, danger_level, fixed would be like
    file: vue-kis-kanban/Example02.vue

When user prompts:

Create a kanban board for task entity with states new, inprogress, fixed, closed. The attribute values are access-key:id, discriminator:state, date-key:duedate

The following Vue code response is generated:

<template>
  <div>
    <KisKanbanViewer ref="kanban" :width=1400 :height=800 access-key="id" discriminator="state" date-key="duedate"
      :buckets="buckets" :data="data" />
  </div>
</template>
<script setup>
import { useEntityDataSource } from '@kis.ai/vue-data'

const { loading, loaded, data, fetchData, previousPage, nextPage, gotoPage } = useEntityDataSource('task', null, { immediate: true, pagesize: 1000 })

const buckets = [
  {
    title: 'New',
    value: 'new',
    style: {
      headerStyle: 'bg-blue-100 text-black items-center p-3',
      bucketStyle: 'bg-blue-100 px-4 rounded-lg'
    }
  },
  {
    title: 'In Progress',
    value: 'inprogress',
    style: {
      headerStyle: 'bg-blue-100 text-black p-3',
      bucketStyle: 'bg-blue-100 px-4 rounded-lg'
    }
  },
  {
    title: 'Fixed',
    value: 'fixed',
    style: {
      headerStyle: 'bg-blue-100 text-black p-3',
      bucketStyle: 'bg-blue-100 px-4 rounded-lg'
    }
  },
  {
    title: 'Closed',
    value: 'closed',
    style: {
      headerStyle: 'bg-green-100 text-black p-3',
      bucketStyle: 'bg-green-100 px-4 rounded-lg'
    }
  }
]
</script>