ChatGPT Compliance Source (Beta)

Beta

OpenAI provides advanced AI solutions for enterprises, offering secure, compliant, and customizable conversational AI capabilities to improve the productivity while meeting organizational governance and regulatory needs.

The ChatGPT Compliance API enables enterprise customers to access structured conversation logs and metadata, integrating with eDiscovery, DLP, or SIEM systems to support auditing, compliance, and security requirements.

Data collected

Source	Description	Polling interval
Conversations	Log of user interactions with ChatGPT, including exchanged messages and metadata, used for compliance review and auditing.	1 hour

Setup

Vendor configuration

You are required to provide the Workspace ID and API Key to configure the ChatGPT Compliance source.

• Follow the below steps to collect the Workspace ID:

  1. In the OpenAI platform sidebar, go to Settings - Workspace Settings (or General Settings).
  2. Your Workspace ID can be found in the About / Workspace Info section.

• Follow the below steps to collect the API Key:

  1. Sign in to the OpenAI API Platform Portal.
     note

     Be sure to create the API key within the same organization as your ChatGPT Enterprise workspace.

  2. Navigate to API Keys > + Create new secret key.
  3. On the pop-up window, enter the following details:
     • Under Owned by, select You.
     • Enter the name of the API key.
     • Select the default project.
     • Under Permissions, select All.
  4. Click Create secret key.
  5. Copy and save the key.
     note

     The API key is only visible once, so be sure to copy it securely. This API key will be required when you set up the ChatGPT Enterprise instance on the Sumo Logic platform.

  6. Send an email to support@openai.com requesting access to the Compliance API. Include the last 4 characters of the API key, the name of the key, who created it, and the requested scope (read).
  7. OpenAI team will verify the key and grant the requested Compliance API scopes.

Source configuration

When you create a ChatGPT Compliance Source, you add it to a Hosted Collector. Before creating the source, identify the Hosted Collector you want to use or create a new Hosted Collector. For instructions, see Configure a Hosted Collector and Source.

To configure a ChatGPT Compliance Source, follow the steps below:

1. New UI. In the Sumo Logic main menu select Data Management, and then under Data Collection select Collection. You can also click the Go To... menu at the top of the screen and select Collection.
   Classic UI. In the main Sumo Logic menu, select Manage Data > Collection > Collection.
2. On the Collection page, click Add Source next to a Hosted Collector.
3. Search for and select ChatGPT Compliance.
4. Enter a Name for the Source. The description is optional.
5. (Optional) For Source Category, enter any string to tag the output collected from the Source. Category metadata is stored in a searchable field called _sourceCategory.
6. (Optional) Fields. Click the +Add button to define the fields you want to associate. Each field needs a name (key) and value.
   •  A green circle with a check mark is shown when the field exists and is enabled in the Fields table schema.
   •  An orange triangle with an exclamation point is shown when the field doesn't exist in the Fields table schema. In this case, you'll see an option to automatically add or enable the nonexistent fields to the Fields table schema. If a field is sent to Sumo Logic that does not exist in the Fields schema it is ignored, known as dropped.
7. Workspace ID. Name of the workspace ID collected from the ChatGPT platform.
8. API Key. Enter the API Key generated from the ChatGPT platform.
9. Polling Interval. The polling interval is set for 1 hour by default and can be configured to a maximum of 24 hours. You can adjust it based on your needs. This sets how often the source checks for new data.
10. When you are finished configuring the Source, click Save.

JSON schema

Sources can be configured using UTF-8 encoded JSON files with the Collector Management API. See Use JSON to Configure Sources for details.

Parameter	Type	Value	Required	Description
schemaRef	JSON Object	{"type":"ChatGPT Compliance"}	Yes	Define the specific schema type.
sourceType	String	"Universal"	Yes	Type of source.
config	JSON Object	Configuration object	Yes	Source type specific values.

Configuration Object

Parameter	Type	Required	Default	Description	Example
name	String	Yes	null	Type a desired name of the source. The name must be unique per Collector. This value is assigned to the metadata field _source.	"mySource"
description	String	No	null	Type a description of the source.	"Testing source"
category	String	No	null	Type a category of the source. This value is assigned to the metadata field _sourceCategory. See best practices for details.	"mySource/test"
fields	JSON Object	No	null	JSON map of key-value fields (metadata) to apply to the Collector or Source. Use the boolean field _siemForward to enable forwarding to SIEM.	{"_siemForward": false, "fieldA": "valueA"}
workspaceId	String	Yes	null	Name of your workspace ID.	ABCD-SAMPLE-WORKSPACE-ID
apiKey	String	Yes	null	API Key of the account.	sk-proj-XXXXXXXXXXXXXXX
pollingInterval	Integer	Yes	1 hour	Time interval (in hours) after which the source will check for new data.	1h

JSON example

static/files/c2c/chatgpt-compliance/example.json

loading...

See full example on GitHub

Terraform example

static/files/c2c/chatgpt-compliance/example.tf

loading...

See full example on GitHub

Limitations

• Updates to conversations after a prolonged gap may cause re-ingestion and potential duplication.
• As ChatGPT continues to evolve, updates may alter conversation data or API behavior, potentially impacting integration consistency.

FAQ

info

Click here for more information about Cloud-to-Cloud sources.