OpenAI

The OpenAI component is an AI component that allows users to connect the AI models served on the OpenAI Platform. It can carry out the following tasks:

#Release Stage

Alpha

#Configuration

The component definition and tasks are defined in the definition.json and tasks.json files respectively.

#Setup

In order to communicate with OpenAI, the following connection details need to be provided. You may specify them directly in a pipeline recipe as key-value pairs within the component's setup block, or you can create a Connection from the Integration Settings page and reference the whole setup as setup: ${connection.<my-connection-id>}.

FieldField IDTypeNote
API Keyapi-keystringFill in your OpenAI API key. To find your keys, visit your OpenAI's API Keys page.
Organization IDorganizationstringSpecify which organization is used for the requests. Usage will count against the specified organization's subscription quota.

#Supported Tasks

#Text Generation

OpenAI's text generation models (often called generative pre-trained transformers or large language models) have been trained to understand natural language, code, and images. The models provide text outputs in response to their inputs. The inputs to these models are also referred to as "prompts". Designing a prompt is essentially how you “program” a large language model model, usually by providing instructions or some examples of how to successfully complete a task.

InputIDTypeDescription
Task ID (required)taskstringTASK_TEXT_GENERATION
Model (required)modelstringID of the model to use.
Enum values
  • o1-preview
  • o1-mini
  • gpt-4o-mini
  • gpt-4o
  • gpt-4o-2024-05-13
  • gpt-4o-2024-08-06
  • gpt-4-turbo
  • gpt-4-turbo-2024-04-09
  • gpt-4-0125-preview
  • gpt-4-turbo-preview
  • gpt-4-1106-preview
  • gpt-4-vision-preview
  • gpt-4
  • gpt-4-0314
  • gpt-4-0613
  • gpt-4-32k
  • gpt-4-32k-0314
  • gpt-4-32k-0613
  • gpt-3.5-turbo
  • gpt-3.5-turbo-16k
  • gpt-3.5-turbo-0301
  • gpt-3.5-turbo-0613
  • gpt-3.5-turbo-1106
  • gpt-3.5-turbo-0125
  • gpt-3.5-turbo-16k-0613
Prompt (required)promptstringThe prompt text.
System Messagesystem-messagestringThe system message helps set the behavior of the assistant. For example, you can modify the personality of the assistant or provide specific instructions about how it should behave throughout the conversation. By default, the model’s behavior is using a generic message as "You are a helpful assistant.".
Imageimagesarray[string]The images.
Chat Historychat-historyarray[object]Incorporate external chat history, specifically previous messages within the conversation. Please note that System Message will be ignored and will not have any effect when this field is populated. Each message should adhere to the format {"role": "The message role, i.e. 'system', 'user' or 'assistant'", "content": "message content"}.
TemperaturetemperaturenumberWhat sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top-p but not both. .
NnintegerHow many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.
Max Tokensmax-tokensintegerThe maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
Response Formatresponse-formatobjectResponse format.
Top Ptop-pnumberAn alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. .
Presence Penaltypresence-penaltynumberNumber between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Frequency Penaltyfrequency-penaltynumberNumber between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
Input Objects in Text Generation

Chat History

Incorporate external chat history, specifically previous messages within the conversation. Please note that System Message will be ignored and will not have any effect when this field is populated. Each message should adhere to the format {"role": "The message role, i.e. 'system', 'user' or 'assistant'", "content": "message content"}.

FieldField IDTypeNote
ContentcontentarrayThe message content.
RolerolestringThe message role, i.e. 'system', 'user' or 'assistant'.

Content

The message content.

FieldField IDTypeNote
Image URLimage-urlobjectThe image URL
TexttextstringThe text content.
TypetypestringThe type of the content part.
Enum values
  • text
  • image-url

Image URL

The image URL

FieldField IDTypeNote
URLurlstringEither a URL of the image or the base64 encoded image data.
The response-format Object

Response Format

response-format must fulfill one of the following schemas:

Text
FieldField IDTypeNote
TypetypestringMust be "text"
JSON Object
FieldField IDTypeNote
TypetypestringMust be "json_object"
JSON Schema
FieldField IDTypeNote
JSON Schemajson-schemastringSet up the schema of the structured output.
TypetypestringMust be "json_schema"
OutputIDTypeDescription
Textstextsarray[string]Texts.
Usage (optional)usageobjectUsage statistics related to the query.
Output Objects in Text Generation

Usage

FieldField IDTypeNote
Completion tokenscompletion-tokensintegerTotal number of tokens used (completion).
Prompt tokensprompt-tokensintegerTotal number of tokens used (prompt).
Total tokenstotal-tokensintegerTotal number of tokens used (prompt + completion).

#Text Embeddings

Turn text into numbers, unlocking use cases like search.

InputIDTypeDescription
Task ID (required)taskstringTASK_TEXT_EMBEDDINGS
Model (required)modelstringID of the model to use.
Enum values
  • text-embedding-ada-002
  • text-embedding-3-small
  • text-embedding-3-large
Text (required)textstringThe text.
DimensionsdimensionsintegerThe number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
OutputIDTypeDescription
Embeddingembeddingarray[number]Embedding of the input text.

#Speech Recognition

Turn audio into text.

InputIDTypeDescription
Task ID (required)taskstringTASK_SPEECH_RECOGNITION
Model (required)modelstringID of the model to use. Only whisper-1 is currently available. .
Enum values
  • whisper-1
Audio (required)audiostringThe audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. .
PromptpromptstringAn optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. .
LanguagelanguagestringThe language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. .
TemperaturetemperaturenumberThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit. .
OutputIDTypeDescription
TexttextstringGenerated text.

#Text to Speech

Turn text into lifelike spoken audio

InputIDTypeDescription
Task ID (required)taskstringTASK_TEXT_TO_SPEECH
Model (required)modelstringOne of the available TTS models: tts-1 or tts-1-hd .
Enum values
  • tts-1
  • tts-1-hd
Text (required)textstringThe text to generate audio for. The maximum length is 4096 characters.
Voice (required)voicestringThe voice to use when generating the audio. Supported voices are alloy, echo, fable, onyx, nova, and shimmer.
Enum values
  • alloy
  • echo
  • fable
  • onyx
  • nova
  • shimmer
Response Formatresponse-formatstringThe format to audio in. Supported formats are mp3, opus, aac, and flac.
Enum values
  • mp3
  • opus
  • aac
  • flac
SpeedspeednumberThe speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.
OutputIDTypeDescription
Audio (optional)audiostringAI generated audio.

#Text to Image

Generate or manipulate images with DALL·E.

InputIDTypeDescription
Task ID (required)taskstringTASK_TEXT_TO_IMAGE
Model (required)modelstringThe model to use for image generation.
Enum values
  • dall-e-2
  • dall-e-3
Prompt (required)promptstringA text description of the desired image(s). The maximum length is 1000 characters for dall-e-2 and 4000 characters for dall-e-3.
NnintegerThe number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
QualityqualitystringThe quality of the image that will be generated. hd creates images with finer details and greater consistency across the image. This param is only supported for dall-e-3.
Enum values
  • standard
  • hd
SizesizestringThe size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.
Enum values
  • 256x256
  • 512x512
  • 1024x1024
  • 1792x1024
  • 1024x1792
NstylestringThe style of the generated images. Must be one of vivid or natural. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for dall-e-3.
Enum values
  • vivid
  • natural
OutputIDTypeDescription
Imagesresultsarray[object]Generated results.
Output Objects in Text to Image

Images

FieldField IDTypeNote
Generated ImageimagestringGenerated image.
Revised Promptrevised-promptstringRevised prompt.

#Example Recipes

Recipe for the PicassoAI: Cubist Creations at Your Command! pipeline.


version: v1beta
component:
mistral-0:
type: mistral-ai
task: TASK_TEXT_GENERATION_CHAT
input:
max-new-tokens: 100
model-name: open-mixtral-8x22b
prompt: |-
Generate a Picasso-inspired image based on the following user input:
${variable.prompt}
Using the specified Picasso period: ${variable.period}
Transform this input into a detailed text-to-image prompt by:
1. Identifying the key elements or subjects in the user's description
2. Adding artistic elements and techniques specific to the ${variable.period} period of Picasso's work
3. Including cubist or abstract features characteristic of the ${variable.period}
4. Suggesting a composition or scene layout typical of Picasso's work from this era
Enhance the prompt with vivid, descriptive language and specific Picasso-style elements from the ${variable.period}. The final prompt should begin with "Create an image in the style of Picasso's ${variable.period} period:" followed by the enhanced description.
safe: false
system-message: You are a helpful assistant.
temperature: 0.7
top-k: 10
top-p: 0.5
setup:
api-key: ${secret.INSTILL_SECRET}
openai-0:
type: openai
task: TASK_TEXT_TO_IMAGE
input:
model: dall-e-3
n: 1
prompt: |-
Using this primary color palette: ${variable.colour}
${mistral-0.output.text}
quality: standard
size: 1024x1024
style: vivid
setup:
api-key: ${secret.INSTILL_SECRET}
variable:
colour:
title: Colour
description: Describe the main colour to use i.e. blue, random
format: string
instill-ui-order: 1
period:
title: Period
description: |
Input different Picasso periods i.e. Blue, Rose, African, Synthetic Cubism, etc.
format: string
prompt:
title: Prompt
description: Input prompt here i.e. "A cute baby wombat"
format: string
output:
image:
title: Image
value: ${openai-0.output.results}

Recipe for the Explain this topic to me in another language pipeline.


version: v1beta
component:
openai:
type: openai
task: TASK_TEXT_GENERATION
input:
model: gpt-4o-mini
n: 1
prompt: |-
Talk about this topic in ${variable.language} in a concise and beginner-friendly way:
${variable.prompt}
response-format:
type: text
system-message: You are a helpful assistant.
temperature: 1
top-p: 1
setup:
api-key: ${secret.INSTILL_SECRET}
variable:
language:
title: Language
description: Input a language i.e. Chinese, Japanese, French, etc.
format: string
prompt:
title: Prompt
description: Write the topic you want to ask about here i.e. "Tell me about small LLMs"
format: string
output:
result:
title: Result
value: ${openai.output.texts}