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

#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 AI page and click Set up new AI
In the Set Up New AI Connector page, fill an ID for your model, this will be the unique identifier of this connector
[Optional] Give a short description of your connector in the Description field
Click the AI Connector Type ▾ drop-down and choose OpenAI
Fill the following information and click Set up
- Fill API Key. Follow the OpenAI documentation to find your API key
By default, the connector is disconnected. To connect and use AI connector, go to the connector page and click Connect.

#Low-code Setup

cURL(Instill-Cloud)

cURL(Instill-Core)

curl -X POST https://api.instill.tech/vdp/v1alpha/users/<user-id>/connector-resources \
--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.

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

#Example

Example input and output data for each task:

TASK_TEXT_GENERATION

TASK_TEXT_EMBEDDINGS

TASK_SPEECH_RECOGNITION

// 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..."
  ]
}