Projects & Sources

A source is a collection of content, often deliminated by sitemaps, url paths, or other logical units. For example, a GitHub repository is “1” source. A marketing site is another. A documentation site can be one or split into multiple. We consider a source seperate if it’s crawled independently of others.

Projects are often used to represent different core scenarios or sets of sources. For example, teams sometimes create different projects for different product lines or to separate out internal (employee) facing scenarios that use private content sources compared to a customer-facing project with public sources.

Integrations represent different “instances” or locations of a chatbot for your project. For example, you may register one integration for your marketing site, one for your documentation site, and another for your help desk. Our analytics views are filterable by integration - allowing you to segment usage patterns. Each integration gets its own API key. All project settings and sources assigned to that project apply to an integration.

While it is up to your company’s own policies and best practices, chat and search API keys are generally ok to be included in client-side (browser) code if the search and chat service is intended for public, unauthenticated use. This is typical of public-facing documentation sites or marketing pages. We implement various protection mechanisms to prevent against abusive usage and in general the chat service is scoped to answering questions about your product so is not a general use API key like an OpenAI or general LLM provider API key would be. If you would like to implement your own protection mechanisms, it is possible to have traffic routed through a private proxy, implement CAPTCHA, and/or add user authentication.

Teams typically create an Integration within a project they use for staging environments. This can help separate out usage from your production usage. If you need truly independent staging or testing environments, you can set up two projects that mirror each other instead.

Separately, if using our UI components, you can set baseSettings.env to DEVELOPMENT so that questions asked in that mode are not shown in the analytics dashboard.