OpenAI Component

Interact with OpenAI models, including Chat GPT and DALL·E

Component key: openai

Description

OpenAI is an artifical intelligence research laboratory that conducts AI research. It has notably produced the chat AI ChatGPT and the image generator DALL·E.

This component wraps some of OpenAI's REST API endpoints. Additional endpoints can be referenced in their API documentation. You can use the Raw Request action to interact with endpoints that are not convered by other actions.

OpenAI Connections

OpenAI API Key

Integrations can authenticate with OpenAI using API keys. Generate an API key at platform.openai.com/account/api-keys.

If your user is associate with one organization, you can leave the connection's organization field blank. Otherwise, specify your organization's ID.

Input	Notes	Example
Input API Key password / Required apiKey	Notes Generate an API key at https://platform.openai.com/account/api-keys	Example
Input Organization string organization	Notes Your organization ID. If you have just one organization, this value is optional.	Example org-9AeeV8Yj8WK9tW6QEZNHDI8Z

Actions

Create Chat Completion

Create a completion for the chat message | key: createChatCompletion

Input	Default	Notes	Example
Input Connection connection / Required connection	Default	Notes	Example
Input Messages code / Required messages	Default [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Who won the world series in 2020?" }, { "role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020." }, { "role": "user", "content": "Where was it played?" }]	Notes	Example
Input Model string / Required model	Default gpt-3.5-turbo	Notes	Example text-davinci-003
Input Number of choices string numChoices	Default 1	Notes How many chat completion choices to generate for each input message.	Example
Input Temperature string temperature	Default 1	Notes What 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.	Example
Input top_p string topP	Default 1	Notes 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.	Example

Output Example Payload

{  "data": {    "id": "chatcmpl-6vf993Onyn1Bwq67AYDTR6fIjzvBu",    "object": "chat.completion",    "created": 1679200883,    "model": "gpt-3.5-turbo-0301",    "usage": {      "prompt_tokens": 56,      "completion_tokens": 21,      "total_tokens": 77    },    "choices": [      {        "message": {          "role": "assistant",          "content": "The 2020 World Series was played at the Globe Life Field in Arlington, Texas, USA."        },        "finish_reason": "stop",        "index": 0      }    ]  }}

---

Create Image

Create image(s) given a prompt | key: createImage

Input	Default	Notes	Example
Input Connection connection / Required connection	Default	Notes	Example
Input Image Size string imageSize	Default 1024x1024	Notes The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.	Example
Input Number of Images string / Required numImages	Default 1	Notes The number of images to generate. Must be between 1 and 10.	Example
Input Prompt string / Required prompt	Default	Notes A text description of the desired image(s). The maximum length is 1000 characters.	Example A cute baby sea otter

Output Example Payload

{  "data": {    "created": 1589478378,    "data": [      {        "url": "https://..."      },      {        "url": "https://..."      }    ]  }}

---

Get Model by ID

Get model by ID | key: getModelById

Input	Notes	Example
Input Connection connection / Required connection	Notes	Example
Input Model string / Required model	Notes	Example text-davinci-003

Output Example Payload

{  "data": {    "id": "davinci",    "object": "model",    "created": 1649359874,    "owned_by": "openai",    "permission": [      {        "id": "modelperm-U6ZwlyAd0LyMk4rcMdz33Yc3",        "object": "model_permission",        "created": 1669066355,        "allow_create_engine": false,        "allow_sampling": true,        "allow_logprobs": true,        "allow_search_indices": false,        "allow_view": true,        "allow_fine_tuning": false,        "organization": "*",        "group": null,        "is_blocking": false      }    ],    "root": "davinci",    "parent": null  }}

---

List Models

List all available models | key: listModels

Input	Notes
Input Connection connection / Required connection	Notes

Output Example Payload

{  "data": {    "object": "list",    "data": [      {        "id": "davinci",        "object": "model",        "created": 1649359874,        "owned_by": "openai",        "permission": [          {            "id": "modelperm-U6ZwlyAd0LyMk4rcMdz33Yc3",            "object": "model_permission",            "created": 1669066355,            "allow_create_engine": false,            "allow_sampling": true,            "allow_logprobs": true,            "allow_search_indices": false,            "allow_view": true,            "allow_fine_tuning": false,            "organization": "*",            "group": null,            "is_blocking": false          }        ],        "root": "davinci",        "parent": null      }    ]  }}

---

Raw Request

Send Raw Request to OpenAI | key: rawRequest

Input	Default	Notes	Example
Input Connection connection / Required connection	Default	Notes	Example
Input Data string data	Default	Notes The HTTP body payload to send to the URL.	Example {"exampleKey": "Example Data"}
Input Debug Request boolean debugRequest	Default false	Notes Enabling this flag will log out the current request.	Example
Input File Data string Key Value List fileData	Default	Notes File Data to be sent as a multipart form upload.	Example [{key: "example.txt", value: "My File Contents"}]
Input Form Data string Key Value List formData	Default	Notes The Form Data to be sent as a multipart form upload.	Example [{"key": "Example Key", "value": new Buffer("Hello World")}]
Input Header string Key Value List headers	Default	Notes A list of headers to send with the request.	Example User-Agent: curl/7.64.1
Input Max Retry Count string maxRetries	Default 0	Notes The maximum number of retries to attempt.	Example
Input Method string / Required method	Default	Notes The HTTP method to use.	Example
Input Query Parameter string Key Value List queryParams	Default	Notes A list of query parameters to send with the request. This is the portion at the end of the URL similar to ?key1=value1&key2=value2.	Example
Input Response Type string / Required responseType	Default json	Notes The type of data you expect in the response. You can request json, text, or binary data.	Example
Input Retry On All Errors boolean retryAllErrors	Default false	Notes If true, retries on all erroneous responses regardless of type.	Example
Input Retry Delay (ms) string retryDelayMS	Default 0	Notes The delay in milliseconds between retries.	Example
Input Timeout string timeout	Default	Notes The maximum time that a client will await a response to its request	Example 2000
Input URL string / Required url	Default /v1/models	Notes This is the URL to call.	Example /v1/images/generations
Input Use Exponential Backoff boolean useExponentialBackoff	Default false	Notes Specifies whether to use a pre-defined exponential backoff strategy for retries.	Example

---