OpenAI

Note: This integration is available in the Business + Enterprise editions from v0.75.1 onwards

AI answers in Outline

AI answers in Outline

The OpenAI integration will allow for various AI functionality around the Outline workspace. Today, it enables “AI answers” to questions by semantically indexing your knowledge, retrieving related documents in realtime, and generating direct answers to questions using their content.

Setup

  • Ensure you have the outline-enterprise image installed and licensed

  • Sign up for an OpenAI account, create an API key and add it to the server environment under OPENAI_API_KEY.

  • Optionally configure OPENAI_URL to point to an alternative compatible API endpoint, but note that “compatible” providers have not been tested. By default the public OpenAI API will be used.

  • You will need a database with the pgvector extension installed to store the search index. This can be a new database, or the same database you use for other Outline data. If you’re using a separate database then an additional DATABASE_URL_VECTOR environment config should be provided to tell Outline where to find this database.

  • Restart the application server, Under Settings → Features → AI Answers you can now enable the integration which will automatically begin indexing content.

Limitations

  • AI answers are limited to information contained in documents that the logged in user has access to.

  • The initial indexing may take a few seconds or a few minutes depending on your OpenAI rate limit and the number of documents in your knowledgebase.

  • Content inside attachments will not be indexed.