OpenAI Integrations

Integrations

OpenAI

Build AI apps with OpenAI

Natural language queries powered by OpenAI

Build an app with Jet

See docs

Overview

The Jet Admin OpenAI integration lets your app send prompts, generate completions, summaries and images, and read the results back into your own records, driven by the same tables, forms and record actions you already build in Jet. Whether a ticket needs summarizing, a lead needs classifying, or a document needs its fields extracted, the whole workflow runs inside Jet, and every call is scoped by role and written to the audit log.

That covers what teams build on OpenAI first: AI-assisted support consoles that draft replies from a ticket thread, data enrichment workflows that tag and classify records as they arrive, and document processing flows that extract structured fields from an upload. Because Jet reads your own database alongside OpenAI, every prompt can pull in the exact record it's working on, and every response writes straight back to it.

What you can do

Generate text completion

Send a prompt built from your own record data to OpenAI and write the response back to the record, for example drafting a reply or a summary.

Summarize text

Send a document, ticket thread or note to OpenAI and store a short summary next to the record.

Classify or tag content

Send text to OpenAI and use the response to set a category, priority or sentiment field on a record automatically.

Generate embeddings

Create embeddings for a record's text so it can be matched or searched by meaning elsewhere in your app.

Moderate content

Check user-submitted text against OpenAI's moderation endpoint before it's stored or shown, and flag or block what fails.

Generate image

Create an image from a prompt built inside a Jet workflow, for example a placeholder or a generated asset for a record.

Run assistant thread

Send a message to an OpenAI Assistant and read back its response as part of a multi-step workflow.

Transcribe audio

Send an audio file to OpenAI and write the transcript back to the record it belongs to.

Extract structured data

Send unstructured text (an email, a form response) to OpenAI and parse the structured fields it returns into your own table.

Translate text

Send a field's content to OpenAI for translation and store the result alongside the original.

Add upload part

Add a chunk of data to an OpenAI multipart file upload.

Analyze sentiment

Detect whether a piece of text is positive, negative or neutral with an OpenAI model.

Answer question

Answer a question with an OpenAI model.

Cancel eval run

Cancel an OpenAI eval run in progress.

Cancel fine tuning

Cancel an OpenAI fine-tuning job.

Cancel response

Cancel an OpenAI response that is running in the background.

Cancel upload

Cancel an OpenAI multipart file upload.

Cancel vector store file batch

Cancel a batch of files being added to an OpenAI vector store.

Complete upload

Finish an OpenAI multipart upload and turn it into a file.

Correct grammar

Fix grammar and spelling in text with an OpenAI model.

Create checkpoint permissions

Share a fine-tuned OpenAI model checkpoint with other projects.

Create conversation

Start an OpenAI conversation with a model, voice and instructions.

Create image edit

Edit an image with a text prompt and optional mask using OpenAI.

Create image variation

Generate variations of an image with OpenAI.

Create items

Add messages or other items to an OpenAI conversation.

Create response

Generate a model response with the OpenAI Responses API.

Create speech

Turn text into lifelike speech with an OpenAI voice.

Create thread

Create an OpenAI Assistants thread with starting messages.

Create translation

Translate an audio file into English text with OpenAI.

Create upload

Start a multipart upload for a large file to OpenAI.

Create vector store file batch

Add a batch of files to an OpenAI vector store.

Delete an item

Delete an item from an OpenAI conversation.

Delete checkpoint permission

Stop sharing a fine-tuned OpenAI model checkpoint with a project.

Delete conversation

Delete an OpenAI conversation.

Delete response

Delete a stored OpenAI response.

Delete thread

Delete an OpenAI Assistants thread.

Extract keywords

Pull the key terms out of a piece of text with an OpenAI model.

Get chat messages

Get the messages from a stored OpenAI chat completion.

Get conversation

Get an OpenAI conversation and its details.

Get input token counts

Count the input tokens a request will use with an OpenAI model.

Get response

Get a stored OpenAI response by its ID.

Get thread

Get an OpenAI Assistants thread.

Get vector store file batch

Check the status of a file batch in an OpenAI vector store.

List checkpoint permissions

List the projects a fine-tuned OpenAI model checkpoint is shared with.

List fine tuning checkpoints

List the checkpoints saved during an OpenAI fine-tuning job.

List fine tuning events

List status events for an OpenAI fine-tuning job.

List input items

List the input items used to generate an OpenAI response.

List vector store files in a batch

List the files in an OpenAI vector store batch.

Pause fine tuning

Pause an OpenAI fine-tuning job.

Remix video

Create a new version of an OpenAI Sora video from an existing one.

Resume fine tuning

Resume a paused OpenAI fine-tuning job.

Retrieve an item

Get a single item from an OpenAI conversation.

Retrieve file content

Download the contents of a file stored in OpenAI.

Retrieve vector store file content

Get the parsed content of a file in an OpenAI vector store.

Retrieve video content

Download a video generated with OpenAI Sora.

Search vector store

Search an OpenAI vector store for the most relevant chunks.

Suggest color

Suggest a color that matches a description with an OpenAI model.

Suggest emoji

Suggest emoji that fit a piece of text with an OpenAI model.

Translate audio to English

Translate spoken audio into English text with OpenAI.

Update conversation

Update the metadata of an OpenAI conversation.

Update thread

Update the metadata of an OpenAI Assistants thread.

Update vector store file attributes

Update the attributes of a file in an OpenAI vector store.

Use Cases

Scenario

What it looks like

AI-assisted support console

Draft a reply or summarize a long ticket thread from inside your support screen, with the agent reviewing before it sends.

Automated data enrichment

Classify, tag or summarize incoming records like leads, tickets or submissions the moment they're created, so your team works from data that's already organized.

Content moderation queue

Screen user-submitted text automatically and route anything flagged to a review queue instead of publishing it directly.

Natural-language search

Let your team search records by meaning, not just keyword, using embeddings generated from your own data.

Internal knowledge assistant

Let staff ask questions against your own records or documents and get an AI-drafted answer with the source record attached.

Automated document processing

Extract structured fields from uploaded documents or forms and write them directly into your database, cutting out manual entry.

Key benefits

AI without a separate app. Generate text, summaries and classifications from inside the same screens your team already works in.
Prompts built from your own data. Pull fields from a record straight into a prompt, instead of copying and pasting between tools.
Results written back automatically. Store a completion, summary or extracted field directly on the record it came from.
Actions with a record. Every OpenAI call runs inside your app, scoped by role, and written to the audit log.
Complete workflows. Tie a generated result to everything that follows it: update a record, trigger a notification, route for review.
Human review where it matters. Draft with AI, then have a person approve before anything sends or publishes.

How to connect Jet Admin with OpenAI

In OpenAI, open platform.openai.com/api-keys and create a Secret key.
In Jet Admin, open your project and add a new resource, or pick OpenAI while creating a project.
Choose OpenAI and paste the Secret key.
Jet loads the OpenAI actions available: completions, embeddings, moderation and image generation.
Add the data sources you want to feed into prompts, for example the record fields you want summarized or classified.
Generate the screens you need, then set role permissions on who can trigger AI actions.
Add actions and workflows on top: auto-tagging on record creation, ticket summaries, and a review step before AI output is saved.