{{snippet.Integrations_Requirements}}

{{variable.FAQarticles}}

You need a few published {{variable.FAQarticles}} {{variable.OnTheAdminPanel}}.

Unpublished {{variable.FAQarticles}} are always ignored by {{variable.OpenAI}}.

Make sure all the {{variable.FAQarticles}} you want {{variable.OpenAI}} to use are tagged as Published {{variable.OnTheAdminPanel}}.

FAQArticles_PublishedList

{{variable.FAQarticles}} must be published to let {{variable.OpenAI}} redirect customers to them for more information.

Keep the following points in mind when drafting and editing your {{variable.FAQarticles}} for optimal results:

Keep sentences short and simple — the clearer you are, the better the answers will be.
Create one {{variable.FAQarticles}} per topic you want to cover — to solve common IT issues, split Wi-Fi, printing, and hardware issues into separate {{variable.FAQarticles}}.
Write using a conversational tone and consistent wording — write your {{variable.FAQarticles}} with common {{variable.customer}} questions in mind and use the same wording consistently.

A paying {{variable.OpenAI}} account

You need a paying {{variable.OpenAI}} account. If you don't have an account yet, you can create one at auth0.openai.com/u/signup. Your account must have a payment method enabled to answer customer help-desk requests.

{{variable.OpenAI}}
charges you per token. Each message a {{variable.customer}} sends through your {{variable.helpdesk}} uses multiple tokens. The number of tokens used per request varies based on the length of the questions asked.

How much {{variable.OpenAI}} charges you varies based on the number of requests your {{variable.customers}} send and how long each request is. More information on pricing for Davinci (text-davinci-003) is available at openai.com/pricing.

Want more control over {{variable.OpenAI}} charges?

You can cap the amount {{variable.OpenAI}} can charge you every month at platform.openai.com/account/billing/limits. Once your {{variable.OpenAI}} account reaches the cap, we'll stop answering help-desk messages automatically to prevent any additional charges.

Intregrating {{variable.OpenAI}}

You can integrate {{variable.OpenAI}} in three steps:

Create an API key in {{variable.OpenAI}}
Enable {{variable.OpenAI}} {{variable.OnTheAdminPanel}}
Test {{variable.OpenAI}}'s answers based on your {{variable.FAQarticles}}

OpenAI_IntegrationProcess

Step 1. Create an API key in {{variable.OpenAI}}

The first step is to create an API key dedicated to Nexudus in your {{variable.OpenAI}} account.

OpenAI Key Generation

You won't be able to see or copy your API key again.

Treat your API key as a password and save it somewhere safe. You'll need it to complete the integration process.

Click Done.

Once you have your {{variable.OpenAI}} API key, you're ready to move to Step 2.

Step 2. Enable {{variable.OpenAI}} {{variable.OnTheAdminPanel}}

The second step is to enable the {{variable.OpenAI}} integration {{variable.OnTheAdminPanel}}.
OpenAI_EnablingIntegration

{{snippet.FirstStepProcedure}}
{{snippet.OpenAI_Path}}
Enable the {{variable.OpenAI}} integration toggle.
Add your {{variable.OpenAI}} API key.
{{snippet.Save_Changes}}

Once the {{variable.OpenAI}} integration is enabled in {{variable.Nexudus}}, you're ready to move to Step 3.

Step 3. Test {{variable.OpenAI}}'s answers based on your {{variable.FAQarticles}}

The last step to integrate {{variable.OpenAI}} is to test the answers generated based on customer questions and queries, also known as training the {{variable.OpenAI}} model. We recommend testing the integration using closed help-desk requests.

{{variable.MoreInformation}} Testing OpenAI.

Supercharge your help-desk using OpenAI x Nexudus ⚡