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 Flow’s FAQ topic or a Graph Flow’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 written into
Nairon’s vector store, 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 embeds the caller’s query and performs a hybrid similarity search over the KB’s chunks, returning the top matching passages for the agent to answer from.
Using a KB in a flow
Section titled “Using a KB in a flow”- Simple Flow: attach a KB to an FAQ topic; the agent answers from that KB’s content when the topic is matched.
- Graph Flow: 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.