Knowledge bases
A knowledge base (KB) is a named collection of datasources — documents or web pages — that
a flow can query for answers, either via a Simple project’s FAQ topic or an Advanced project’s
knowledge node / pre-hook knowledge_query integration lookup.
Creating a knowledge base
Section titled “Creating a knowledge base”From a project’s Knowledge Bases page, create a KB and add datasources to it. A datasource is either:
- A file upload — PDF, DOC/DOCX, Markdown, JSON, CSV, or XML.
- A website URL — crawled and re-crawlable on demand.
Ingestion
Section titled “Ingestion”Adding a datasource kicks off ingestion: the content is chunked, embedded, and indexed, with the
datasource’s status moving through indexing → active (or flagged if it fails). Ingestion is
asynchronous — the UI shows per-datasource progress, and you can re-index a datasource (e.g. after
a source document changes) or the whole KB at once.
Retrieval at call time searches your indexed content for the passages most relevant to the caller’s query, returning the top matches for the agent to answer from.
Using a KB in a flow
Section titled “Using a KB in a flow”- Simple project: attach a KB to an FAQ topic; the agent answers from that KB’s content when the topic is matched.
- Advanced project: reference a KB from a knowledge-query pre-hook lookup, or from a dedicated knowledge node in the conversation graph, storing the retrieved passages into a variable for the agent to use.
Best practices
Section titled “Best practices”- Keep datasources focused and current — stale documents produce stale (or contradictory) answers.
- Prefer several smaller, topic-scoped datasources over one enormous document; retrieval quality degrades with very large, unstructured single sources.
- Re-index after editing a source document — Nairon does not detect external edits automatically for uploaded files.