Tool

Query Confluence Knowledge Base with ChatGPT

Connect a Custom GPT to Confluence via OAuth so it can answer questions from your organization's spaces and pages.

Works with confluenceatlassian

Maintainer of this project? Claim this page to edit the listing.


93
Spark score
out of 100
Updated 21 days ago
Version 1.0.0
Models

Add to Favorites

Why it matters

Leverage ChatGPT's natural language capabilities to seamlessly query your organization's Confluence knowledge base. Retrieve information and get answers to your questions without manual searching.

Outcomes

What it gets done

01

Connect ChatGPT to your Confluence instance.

02

Scan Confluence spaces and pages for relevant information.

03

Formulate natural language responses based on Confluence content.

04

Provide quick access to project documentation and company policies.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/oai-gptactionconfluence | bash

Overview

GPT Action Library: Confluence

A GPT Action connecting a Custom GPT to Confluence via OAuth 2.0, letting it search spaces and pages to answer user questions from an organization's knowledge base. Use it to give a Custom GPT read-only access to Confluence content. Requires Atlassian Developer Portal admin access to create the OAuth app and configure scopes.

What it does

This GPT Action connects a Custom GPT to Confluence, Atlassian's team collaboration and documentation platform: it takes a user's question, scans relevant Confluence spaces and pages, and formulates an answer grounded in that content. It's read-only as documented - updating Confluence content directly from ChatGPT isn't covered here, though the cookbook notes it's technically feasible with additional Actions and scopes.

When to use - and when NOT to

Use this to give knowledge workers, project managers, customer support teams, or anyone in an organization natural-language access to Confluence's knowledge base - retrieving documentation, project updates, or policy details without manually searching pages. It requires permission to create an app in the Atlassian Developer Portal, so it's not something an individual user can set up without admin-level access to that portal.

Inputs and outputs

Setup starts in the Atlassian Developer Portal: create an OAuth 2.0 integration, switch its distribution to "Sharing," add the scopes needed (User identity API and Confluence API, so the app knows what the user can access and can fetch from Confluence), then configure OAuth 2.0 authorization with a callback URL from the GPT Action, and finally copy the resulting Client ID and Client Secret values. In ChatGPT's Authentication panel, select OAuth and enter the Client ID, Client Secret, Authorization URL (https://auth.atlassian.com/authorize), Token URL (https://auth.atlassian.com/oauth/token), and scope read:confluence-content.all search:confluence, with Token set to default POST.

Integrations

After configuring authentication in ChatGPT, copy the callback URL it generates back into the Confluence app's Authorized redirect URIs to finalize the connection. Common issues: a callback URL error usually means the redirect URI wasn't added correctly on the Confluence side; the GPT querying the wrong project or dataset usually means the Custom GPT instructions need to be made more explicit about which one to use, or should instead require the user to specify it directly; and looping Actions usually indicate the app is missing a required scope or permission for whatever it's actually trying to do.

Who it's for

Developers setting up a Custom GPT that needs to answer questions from an organization's Confluence knowledge base, handling the full OAuth setup on both the Atlassian and ChatGPT sides. Before starting, it's worth reviewing OpenAI's general introductions to GPT Actions and the Actions Library, plus the from-scratch getting-started walkthrough, since this Confluence-specific guide builds directly on those foundational concepts rather than re-explaining them here.

Source README

GPT Action Library: Confluence

Introduction

This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you proceed, make sure to first familiarize yourself with the following information:

This particular GPT Action provides an overview of how to connect to Confluence, Atlassian's collaboration and documentation platform. This Action takes a user’s question, scans the relevant Confluence spaces and pages to gather the necessary information, then formulates a response to answer the user’s question. This cookbook does not address updating content in Confluence directly from ChatGPT, but it is technically feasible to accomplish with additional Actions and scopes.

Value + Example Business Use Cases

Value

Users can now leverage ChatGPT's natural language capability to connect directly to Confluence, enabling seamless interaction with their organization's knowledge base.

Example Use Cases

  • Knowledge Workers: Easily retrieve information from Confluence pages and spaces to answer questions or gather details for reports and presentations.
  • Project Managers: Quickly access project documentation and updates stored in Confluence without manually searching through pages.
  • Customer Support Teams: Provide accurate and timely responses to customer inquiries by pulling relevant information from the Confluence knowledge base.
  • All Users: Gain more visibility into company-wide documentation, policies, and procedures, enhancing collaboration and knowledge sharing.

Application Information

Application Key Links

Check out these links from the application before you get started:

Application Prerequisites

Before you get started, make sure you go through the following steps in your application environment:

  • Ensure you have permissions to create an App in the Atlassian Developer Portal
  • Determine what interactions you would like your GPT to take (search, read, edit, etc.)

ChatGPT Steps

Custom GPT Instructions

Once you've created a Custom GPT, copy the text below in the Instructions panel. Have questions? Check out Getting Started Example to see how this step works in more detail.

OpenAPI Schema

Once you've created a Custom GPT, copy the text below in the Actions panel. Have questions? Check out Getting Started Example to see how this step works in more detail.

Authentication Instructions

Below are instructions on setting up authentication with this 3rd party application. Have questions? Check out Getting Started Example to see how this step works in more detail.

Pre-Action Steps

Before you set up authentication in ChatGPT, make sure you go through the following steps within the Atlassian Developer portal to create your Confluence app:

  1. Select the Create drop-down
  2. Choose OAuth 2.0 integration
  3. Give a name, agree to terms, and click Create
  4. Select "Distribution" on the left-hand menu and click “Edit”
  5. Change radio button to "Sharing"
  6. Fill out required fields and Save Changes
  7. Select "Permissions" on the left-hand menu
  8. Add in the scopes you would like to include (e.g., User identity API and Confluence API so that the app can know what a user has access to and fetch from Confluence)
  9. Select "Authorization" on the left-hand menu
  10. Click "Add" under Action in the row for OAuth 2.0
  11. Enter the callback URL from your GPT (note: you may need to add a placeholder for now and revisit this once you have created the Action and OAuth in your GPT so that you have the final callback URL)
  12. Select "Settings" under the left-hand menu
  13. Copy your Client ID and Secret for us in OAuth setup in GPT

In ChatGPT

In ChatGPT, click on "Authentication" and choose "OAuth". Enter in the information below.

Post-Action Steps

Once you've set up authentication in ChatGPT, follow the steps below in the application to finalize the Action.

  • Copy the callback URL from the GPT Action
  • In the “Authorized redirect URIs” (see screenshot above), add your callback URL

FAQ & Troubleshooting

  • Callback URL Error: If you get a callback URL error in ChatGPT, pay close attention to the screenshot above. You need to add the callback URL directly into your Confluence app for the action to authenticate correctly
  • Schema calls the wrong project or dataset: If ChatGPT calls the wrong project or dataset, consider updating your instructions to make it more explicit either (a) which project / dataset should be called or (b) to require the user provide those exact details before it runs the query
  • Looping Actions: You may not have given the necessary scopes/permissions to your app to accomplish its intended purpose

Are there integrations that you’d like us to prioritize? Are there errors in our integrations? File a PR or issue in our github, and we’ll take a look.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.