OpenAI | Documentation

The OpenAI AI connector enables you to connect the AI models served on the OpenAI Platform for the following tasks:

Text Generation
Text Embeddings
Speech Recognition
Text to Image

#Release Stage

Alpha

#Resource Configuration

The up-to-date configuration is maintained here.

Field	Type	Note
api_key*	string	Enter your OpenAI API key. To find your keys, go to your OpenAI's Account page.

#No-code Setup

PREREQUISITES

To create a OpenAI AI connector, you'll first need to create a OpenAI account by visiting openai.com. Access to your API keys can then be managed through OpenAI's Account page.

To create a OpenAI AI connector:

Go to the Resource page and click Add Resource
Select OpenAI
Fill in a unique ID for the resource. Optionally, give a short description in the Description field
Fill in the required fields.
- Fill API Key. Follow the OpenAI documentation to find your API key
- Optionally, fill Orgnization ID that specify which organization is used for the requests. Usage will count against the specified organization's subscription quota.

#Low-code Setup

cURL(Instill-Cloud)

cURL(Instill-Core)

curl -X POST https://api.instill.tech/vdp/v1alpha/users/<user-id>/connectors \
--header 'Authorization: Bearer <Instill-Cloud-API-Token>' \
--data '{
  "id": "my-openai",
  "connector_definition_name": "connector-definitions/ai-openai",
  "configuration": {
    "api_key": "<open-ai-api-key>"
  }
}'

For other operations, please refer to the VDP Protobufs.

#Connector Configuration

When using the OpenAI AI connector in your pipeline, certain fields of the input data need to be filled to trigger the pipeline effectively. Here are the expected input and output data fields for the OpenAI AI connector.

#Text Generation

If task is set to TASK_TEXT_GENERATION

Input	Type	Description
task	string	`TASK_TEXT_GENERATION`
prompt	string	Text prompt
model	string	The model that you want to use. eg., `gpt-4` and `gpt-3.5-turbo` .
system_message	string	The 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."
temperature	float	The 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.
n	int	How many chat completion choices to generate for each input message.
max_tokens	int	The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.
top_p	float	An 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_penalty	float	Number 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. See more information about frequency and presence penalties.
frequency_penalty	float	Number 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. See more information about frequency and presence penalties.
response_format.type	string	Setting to `json_object` enables JSON mode.

Output	Type	Description
texts	array[string]	Generated text array

#Text Embeddings

Input	Type	Description
task	string	`TASK_TEXT_EMBEDDINGS`
text	string	Text to be converted to dense vector
model	string	The model that you want to use. eg. `text-embedding-ada-002`

Output	Type	Description
embedding	array[float]	A vector embeddings

#Speech Recognition

Input	Type	Description
task	string	`TASK_SPEECH_RECOGNITION`
model	string	The model that you want to use, e.g., `whisper-1`.
audio	string	Base64 encoded audio recording to transcribe
temperature	float	The 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.
language	string	The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
prompt	string	An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

Output	Type	Description
text	string	Transcribed text

#Text to Image

Input	Type	Description
task	string	`TASK_TEXT_TO_IMAGE`
model	string	ID of the model to use
prompt	string	A text description of the desired image(s).
n	float	The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.
size	string	The size of the generated images.
style	string	The style of the generated images.

Output	Type	Description
results	array[object]	Generated images

#Example

Example input and output data for each task:

TASK_TEXT_GENERATION

TASK_TEXT_EMBEDDINGS

TASK_SPEECH_RECOGNITION

TASK_TEXT_TO_IMAGE

// Input
{
  "task": "TASK_TEXT_GENERATION",
  "model": "gpt-3.5-turbo",
  "prompt": "Write me a story about London"
}
// Output
{
  "texts": [
    "Once upon a time, in the heart of England, there stood a vibrant city named London. It was a place of rich history, diverse culture, and endless possibilities. From its iconic landmarks to its bustling streets, the city had a unique charm that drew people from all walks of life..."
  ]
}