Knowledge Base
About Knowledge Base
Choose an entry point
| Task | Entry |
|---|---|
| Store and preview original files | Library |
| Maintain searchable text and metadata | Knowledge Base content page |
| Parse files into knowledge | Library parsing configuration |
| Compare retrieval results | Knowledge retrieval test |
| Use knowledge in a process | Workflow knowledge retrieval node |
Current knowledge base types
The current creation form is fixed to Pro. Open existing FAQ or Chunk knowledge bases from the list.
Content and indexes
Pro content includes a vector index, a tokenized index, and Metadata. Vector retrieval matches meaning; tokenized retrieval matches keywords. Metadata holds information such as source and category and can be used for filtering. Both indexes may use the same text.
Before you start
Define the content scope, embedding model, metadata schema, and readers and maintainers. The model and schema cannot be freely changed after creation. Validate the design with a small mock sample. Continue with Create and manage knowledge bases.