Getting Started
kapa is a retrieval augmentented generation system (RAG). To set up an instance of kapa you have to ingest all relevant technical knowledge which is required to answer the questions of the intended audience. To answer questions kapa first performs search over an index created from the ingested knowledge sources and then uses LLMs to generate the final output. Users can manage their data sources in the kapa dashboard.
What knowledge sources does kapa.ai support? 📚
kapa supports a wide range of data sources to ingest knowledge from. The following table provides an overview of the supported data sources and their corresponding integrations:
| Type | Supported Data Sources |
|---|---|
| 🌐 Websites | Web Crawling all webpages and documentation sits (e.g., Docusaurus, Readme, ReadTheDocs, MkDocs, Mintlify, GitBook, Gatsby) |
| 🛠️ GitHub | Issues, Discussions, Files, Pull Requests, Codebase |
| 💬 Community Discussion | Slack, Discord, Discourse Forum, StackOverflow |
| 🧠 Knowledge Bases | Zendesk Help Center, Zendesk Support Tickets, Confluence, Jira, Notion |
| 📦 API Specs | OpenAPI, GraphQL |
| 📚 Files & Others | Custom QA, YouTube, S3 Storage, File Upload |
We're constantly adding new data sources to kapa. If you have a suggestion or need for a data source not listed above, please don't hesitate to reach out with your request. While the above are our official sources, we always work with our users to ingest other data types via custom integrations and solutions.
How do I ingest sources? 📥
Currently, the kapa.ai team will help you onboard onto the platform and ingest sources for you. Once you sign up to the kapa.ai beta, there's usually a 12-24hr turnaround time for this process. After the kapa team initially gets you onboarded, you can manage their data sources in the kapa dashboard (access granted after sign-up).
Want access within 12-24 hrs? Head to kapa.ai to sign up and the team will be in touch within a few hours to get you set up with a demo instance.