Guide to DocsGPT API Keys

DocsGPT API keys are essential for developers and users who wish to integrate the DocsGPT models into external applications, such as our widget. This guide will walk you through the steps of obtaining an API key, starting from uploading your document to understanding the key variables associated with API keys.

Obtaining Your API Key

After uploading your document, you can obtain an API key either through the graphical user interface or via an API call:

• Graphical User Interface: Navigate to the Settings section of the DocsGPT web app, find the Agents option, and press ‘Create New’ to generate a new agent (which includes an API key).
• API Call: Alternatively, you can use the /api/create_agent endpoint to create a new agent. An API key is automatically generated for each agent. For detailed instructions, visit DocsGPT API Documentation .

Understanding Key Variables

Upon creating your agent, you will encounter several key variables. Each serves a specific purpose:

• Name: Assign a name to your agent for easy identification.
• Source: Indicates the source document(s) linked to your agent, which DocsGPT will use to generate responses.
• ID: A unique identifier for your agent. You can view this by making a call to /api/get_agents.
• Key: The API key for the agent, which will be used in your application to authenticate API requests.

With your API key ready, you can now integrate DocsGPT into your application, such as the DocsGPT Widget or any other software, via /api/answer or /stream endpoints. The source document is preset with the agent, allowing you to bypass fields like selectDocs and active_docs during implementation.

Congratulations on taking the first step towards enhancing your applications with DocsGPT!