ChatCompletion

yaml

type: "io.kestra.plugin.openai.ChatCompletion"

Given a prompt, get a response from an LLM using the OpenAI’s Chat Completions API.

For more information, refer to the Chat Completions API docs.

Examples

Based on a prompt input, generate a completion response and pass it to a downstream task.

yaml

id: openAI
namespace: dev

inputs:
  - id: prompt
    type: STRING
    defaults: What is data orchestration?

tasks:
  - id: completion
    type: io.kestra.plugin.openai.ChatCompletion
    apiKey: "yourOpenAIapiKey"
    model: gpt-3.5-turbo-0613
    prompt: "{{inputs.prompt}}"

  - id: response
    type: io.kestra.core.tasks.debugs.Return
    format: "{{outputs.completion.choices[0].message.content}}"

Based on a prompt input, ask OpenAI to call a function that determines whether you need to respond to a customer's review immediately or wait until later, and then comes up with a suggested response.

yaml

id: openAI
namespace: dev

inputs:
  - id: prompt
    type: STRING
    defaults: I love your product and would purchase it again!

tasks:
  - id: prioritize_response
    type: io.kestra.plugin.openai.ChatCompletion
    apiKey: "yourOpenAIapiKey"
    model: gpt-4
    messages:
      - role: user
        content: "{{inputs.prompt}}"
    functions:
      - name: respond_to_review
        description: Given the customer product review provided as input, determines how urgently a reply is required and then provides suggested response text.
        parameters:
          - name: response_urgency
            type: string
            description: How urgently this customer review needs a reply. Bad reviews 
                         must be addressed immediately before anyone sees them. Good reviews can 
                         wait until later.
            required: true
            enumValues: 
              - reply_immediately
              - reply_later
          - name: response_text
            type: string
            description: The text to post online in response to this review.
            required: true

  - id: response_urgency
    type: io.kestra.core.tasks.debugs.Return
    format: "{{outputs.prioritize_response.choices[0].message.function_call.arguments.response_urgency}}"

  - id: response_text
    type: io.kestra.core.tasks.debugs.Return
    format: "{{outputs.prioritize_response.choices[0].message.function_call.arguments.response_text}}"

Properties

`apiKey`

Type: string
Dynamic: ✔️
Required: ✔️

The OpenAI API key.

`model`

Type: string
Dynamic: ✔️
Required: ✔️

ID of the model to use e.g. 'gpt-4'

See the OpenAI model's documentation page for more details.

`clientTimeout`

Type: integer
Dynamic: ❓
Required: ❌
Default: 10

The maximum number of seconds to wait for a response.

`frequencyPenalty`

Type: number
Dynamic: ❌
Required: ❌

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far. Defaults to 0.

`functionCall`

Type: string
Dynamic: ❌
Required: ❌

The name of the function OpenAI should generate a call for.

Enter a specific function name, or 'auto' to let the model decide. The default is auto.

`functions`

Type: array
SubType: ChatCompletion-PluginChatFunction
Dynamic: ❓
Required: ❌

The function call(s) the API can use when generating completions.

`logitBias`

Type: object
SubType: integer
Dynamic: ❌
Required: ❌

Modify the likelihood of specified tokens appearing in the completion. Defaults to null.

`maxTokens`

Type: integer
Dynamic: ❌
Required: ❌

The maximum number of tokens to generate in the chat completion. No limits are set by default.

`messages`

Type: array
SubType: ChatMessage
Dynamic: ❌
Required: ❌

A list of messages comprising the conversation so far.

Required if prompt is not set.

`n`

Type: integer
Dynamic: ❓
Required: ❌

How many chat completion choices to generate for each input message. Defaults to 1.

`presencePenalty`

Type: number
Dynamic: ❌
Required: ❌

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far. Defaults to 0.

`prompt`

Type: string
Dynamic: ❌
Required: ❌

The prompt(s) to generate completions for. By default, this prompt will be sent as a user role.

If not provided, make sure to set the messages property.

`stop`

Type: array
SubType: string
Dynamic: ❌
Required: ❌

Up to 4 sequences where the API will stop generating further tokens. Defaults to null.

`temperature`

Type: number
Dynamic: ❌
Required: ❌

What sampling temperature to use, between 0 and 2. Defaults to 1.

`topP`

Type: number
Dynamic: ❌
Required: ❌

An alternative to sampling with temperature, where the model considers the results of the tokens with top_p probability mass. Defaults to 1.

`user`

Type: string
Dynamic: ✔️
Required: ❌

A unique identifier representing your end-user.

Outputs

`choices`

Type: array
SubType: ChatCompletionChoice
Dynamic: ❓
Required: ❌

A list of all generated completions.

`id`

Type: string
Dynamic: ❓
Required: ❌

Unique ID assigned to this Chat Completion.

`model`

Type: string
Dynamic: ❓
Required: ❌

The GPT model used.

`object`

Type: string
Dynamic: ❓
Required: ❌

The type of object returned, should be "chat.completion".

`usage`

Type: Usage
Dynamic: ❓
Required: ❌

The API usage for this request.

`arguments`

Type: JsonNode
Dynamic: ❓
Required: ❓

`name`

Type: string
Dynamic: ❓
Required: ❓

`io.kestra.plugin.openai.ChatCompletion-PluginChatFunctionParameter`

Properties

`description`

Type: string
Dynamic: ✔️
Required: ✔️

A description of the function parameter.

Provide as many details as possible to ensure the model returns an accurate parameter.

`name`

Type: string
Dynamic: ✔️
Required: ✔️

The name of the function parameter.

`enumValues`

Type: array
SubType: string
Dynamic: ✔️
Required: ❌

A list of values that the model must choose from when setting this parameter.

Optional, but useful when for classification problems.

`required`

Type: boolean
Dynamic: ❓
Required: ❌
Default: false

Whether or not the model is required to provide this parameter.

Defaults to false.

`description`

Type: string
Dynamic: ✔️
Required: ❌

A description of what the function does.

`name`

Type: string
Dynamic: ✔️
Required: ❌

The name of the function.

`parameters`

Type: array
SubType: ChatCompletion-PluginChatFunctionParameter
Dynamic: ❓
Required: ❌

The function's parameters.

`com.theokanning.openai.completion.chat.ChatCompletionChoice`

Properties

`finish_reason`

Type: string
Dynamic: ❓
Required: ❓

`index`

Type: integer
Dynamic: ❓
Required: ❓

`message`

Type: ChatMessage
Dynamic: ❓
Required: ❓

`com.theokanning.openai.Usage`

Properties

`completion_tokens`

Type: integer
Dynamic: ❓
Required: ❓

`prompt_tokens`

Type: integer
Dynamic: ❓
Required: ❓

`total_tokens`

Type: integer
Dynamic: ❓
Required: ❓

`com.theokanning.openai.completion.chat.ChatMessage`

Properties

`content`

Type: string
Dynamic: ❓
Required: ❓

`function_call`

Type: ChatFunctionCall
Dynamic: ❓
Required: ❓

`name`

Type: string
Dynamic: ❓
Required: ❓

`role`

Type: string
Dynamic: ❓
Required: ❓

​Chat​Completion

ChatCompletion

arguments

name

description

name

enumValues

required

description

name

parameters

finish_reason

index

message

completion_tokens

prompt_tokens

total_tokens

content

function_call

name

role

ChatCompletion

`arguments`

`name`

`description`

`name`

`enumValues`

`required`

`description`

`name`

`parameters`

`finish_reason`

`index`

`message`

`completion_tokens`

`prompt_tokens`

`total_tokens`

`content`

`function_call`

`name`

`role`