Public API for integration

• The public API is exposed as part of the BusinessGPT Firewall.

Getting API KEY

The API allows sending requests to AI service through HTTP requests.

Each user has a unique API key to authenticate the API. The API key is viewed on the User Settings page in the dashboard. You need to copy it and send in the request.

Open

Chat API service - POST request

POST: https://[firewall API address]/firewallApi/v1/chat

Sample URL for BGD15 environment:
https://bgd15-firewall.agatdemo.com/firewallApi/v1/chat

Allows to send a prompt to the AI and receive a response based on some particular content or all company data

• APIKey

• Prompt

• DataSource - Possible values: PrivateAndPublic, Public, Private.
  When the DataSource is set to public, the chat will use the pre-trained LLM knowledge, while the private value will use the company data uploaded.

• PrivateDataSource- Possible values - Content, Collection, All
  The PrivateDataSource values are not needed for public-only data

• PrivateDataID - The ID of the content or the collection
  The PrivateDataID is not needed when privateDataSource =All.

• AIModel (optional. Default will be as for the user. Available values: GPT3_5, GPT4, WizardLM, GPT4o, GPT_4o_Mini)

• ChatId (optional): If provided, the question will be added to the existing chat with an external chat ID that equals the provided value. If no chat exists, a new one will be created.

• MaxWordsInAnswer (optional) - If provided it should limit the number of words in the answer. The min word limit is 5.

• User (optional) - the user that has asked the question

• ChatAIService (optional. Default will be BusinessGPTDashboard . Available values: ChatGPT, Gemini, BusinessGPTDashboard , MicrosoftCopilot , Cohere, Claude, SlackBot)

• Context (Optional) - the context of the chat. For example, the name of the Slack channel or Word document that the prompt was used from.

• ChatName (optional) - the name of the chat in the auditing

Output - for HTTP status OK (200):

• PromptId

• Response

In case of an error, it will return an error message.

Open

How do you find the ID of the collection or content item for the “PromptScopeId” parameter?

To find the ID triple-click the line to get some system info:

ProjectID is the collection ID:

For a document it is the contentID as in the image below

Create Collection API service - POST request

POST: https://[firewall API address]/firewallApi/v1/createcollection

Creates a collection

Input parameters

• APIKey

• Collection name

• Collection id (optional id)

• AllowedGroups (optional)

• AllowedEmails (optional)

• Action (string, optional, default: "Add")
  The action to be performed on the collection. Possible values include:

  • Add: Upload a new file (default action).

  • UpdatePermissions: Modify permissions for an existing file.

  • Rename: Change the name of an existing file.

  • Delete: Remove an existing file.

• Output - for HTTP status OK (200):

  • CollectionID

Upload API service - POST request

POST: https://[firewall API address]/firewallApi/v1/upload

Sample URL for BGD15 environment:
https://https://bgd15-firewall.agatdemo.com/firewallApi/v1/upload

Allows to send file to the AI to be saved in BusinessGPT and receive its ID.

Input parameters - should be sent as form-data:

• APIKey

• FileName

• FileContent - binary

• ContentSourceName (optional)- The name of the client using the API (for example, File loader)

• ContentSourceIP (optional)- The IP of the client using the API (for example the host of the File loader)

• AllowedGroups (optional)

• AllowedEmails (optional)

• FilePath (optional)

• Action (string, optional, default: "Add")
  The action to be performed on the file. Possible values include:

  • Add: Upload a new file (default action).

  • UpdatePermissions: Modify permissions for an existing file.

  • Rename: Change the name of an existing file.

  • Delete: Remove an existing file.

• ContentId (string, required for UpdatePermissions, Rename, or Delete)

• CollectionID (Optional)

Output - for HTTP status OK (200):

• ContentId

In case of an error, it will return an error message.

Get classifications service - GET request

GET: https://[firewall API address]/firewallApi/v1/getClassifications

Sample URL for BGD10 environment:
https://bgd15-firewall.agatdemo.com/firewallApi/v1/getClassifications

Allows to get status and classifications of content.

Input parameters - should be sent as JSON:

• APIKey

• ContentId

Output - for HTTP status OK (200):

• EmbeddingStatus- of the content (document) - New/SentToQueue/Processing/Done/Failed

• Classifications(only if embedding status is Done) - list of classifications found for the content, by rule type (AI/Regular). Each classification contains the following fields:

  • RuleType - AI/Regular

  • Status - New/Processing/Done/Error/Skip

  • ClassificationRules (only if status is Done) - list of rules of the specified type that were matched for the content. Each rule contains the following fields:

    • RuleName

    • RuleDescription

    • RulePurpose

    • RuleType

    • SensitivityLevel

    • RuleValue

In case of an error, it will return an error message.

Healthcheck service - GET request

GET: https://[firewall API address]/firewallApi/v1/alive

Sample URL for BGD10 environment:
https://bgd15-firewall.agatdemo.com/firewallApi/v1/alive

Postman Samples for all APIs

Attached is the Postman collection with example requests.

Open