defineKnowledgeCatalog
KIT · function · Runtime value
Compile a knowledge catalog from document declarations.
Reads are declarative: document returns the whole text, self returns exactly the named sections and subtree includes their nested sections. Section ids are validated up front, so a typo fails at read time instead of silently returning partial content.
Import
import { defineKnowledgeCatalog } from '@jangts/agent-core/kits/knowledge';import { defineKnowledgeCatalog } from '@jangts/agent-core/kits/knowledge';Other public entry points:@jangts/agent-core/types, @jangts/agent-core/kits/knowledge, @jangts/agent-core/kits.
Definition
Call
defineKnowledgeCatalog(documents: readonly KnowledgeDocument[], options?: KnowledgeCatalogOptions): KnowledgeCatalogCompile a knowledge catalog from document declarations.
Reads are declarative: document returns the whole text, self returns exactly the named sections and subtree includes their nested sections. Section ids are validated up front, so a typo fails at read time instead of silently returning partial content.
| Parameter | Type | Passing | Description |
|---|---|---|---|
documents | readonly KnowledgeDocument[] | Required | — |
options | KnowledgeCatalogOptions | Optional | — |
Fields of options
| Field | Type | Required | Description |
|---|---|---|---|
maxChars | number | undefined | Optional | Read-only. Maximum characters per read; exceeding it throws a RangeError. |
observe | ((snapshot: KnowledgeSnapshot) => void | Promise<void>) | undefined | Optional | Read-only. Observer invoked with every produced snapshot. |
Returns: KnowledgeCatalog.
Return value structure
| Field | Type | Required | Description |
|---|---|---|---|
sectionIds | (documentId: string) => readonly string[] | Required | Section ids of one document, in declaration order; throws for an unknown document. |
assertSelection | (read: KnowledgeRead) => void | Required | Validates a read without producing content; throws when the selection is invalid. |
read | (read: KnowledgeRead) => KnowledgeSnapshot | Required | Produces a snapshot for the read; throws for unknown documents, sections or budget excess. |
definitions | readonly Readonly<KnowledgeDocument>[] | Required | Read-only. Definitions in registration order; each entry is frozen by the implementation. |
ids | () => readonly string[] | Required | Ids in the same order as definitions. |
values | () => IterableIterator<Readonly<KnowledgeDocument>> | Required | See the type definition and usage context. |
entries | () => IterableIterator<readonly [string, Readonly<KnowledgeDocument>]> | Required | See the type definition and usage context. |
has | (id: string) => boolean | Required | See the type definition and usage context. |
get | (id: string) => Readonly<KnowledgeDocument> | undefined | Required | Returns the definition or undefined; the caller decides whether absence is an error. |
require | (id: string) => Readonly<KnowledgeDocument> | Required | Returns the definition or throws; use when the id is a required reference. |
Examples
- Knowledge: documents, sections, and evidence snapshots: One document contract supports plain objects and anchored text; a selection yields an evidence snapshot with an explicit version.
First read one plain-object document
Beginner · Node.js
import { Knowledge } from '@jangts/agent-core/kits/knowledge';
const catalog = Knowledge.defineKnowledgeCatalog([
{ id: 'manual', revision: '1', parts: ['Agent Core 支持普通 Workflow 节点。'] },
]);
const snapshot = catalog.read({ documentId: 'manual', selection: { mode: 'document' } });
console.log(snapshot.content, snapshot.revision);import { Knowledge } from '@jangts/agent-core/kits/knowledge';
const catalog = Knowledge.defineKnowledgeCatalog([
{ id: 'manual', revision: '1', parts: ['Agent Core 支持普通 Workflow 节点。'] },
]);
const snapshot = catalog.read({ documentId: 'manual', selection: { mode: 'document' } });
console.log(snapshot.content, snapshot.revision);Add sections and a budget to the same read
Configuration · Node.js
import { Knowledge } from '@jangts/agent-core/kits/knowledge';
const catalog = Knowledge.defineKnowledgeCatalog([
{ id: 'manual', revision: '2', parts: [
{ id: 'start', parts: ['先运行一个节点。', { id: 'advanced', parts: ['再增加模型和工具。'] }] },
] },
], { maxChars: 2000 });
console.log(catalog.sectionIds('manual'));
const snapshot = catalog.read({ documentId: 'manual', selection: { mode: 'subtree', sectionIds: ['start'] } });
console.log(snapshot.content, snapshot.id);import { Knowledge } from '@jangts/agent-core/kits/knowledge';
const catalog = Knowledge.defineKnowledgeCatalog([
{ id: 'manual', revision: '2', parts: [
{ id: 'start', parts: ['先运行一个节点。', { id: 'advanced', parts: ['再增加模型和工具。'] }] },
] },
], { maxChars: 2000 });
console.log(catalog.sectionIds('manual'));
const snapshot = catalog.read({ documentId: 'manual', selection: { mode: 'subtree', sectionIds: ['start'] } });
console.log(snapshot.content, snapshot.id);Switch to the text adapter; later catalog and read calls stay identical
Extension · Node.js
Paired anchors must match; markers are just one input for the text adapter, and Core does not require documents to be stored as Markdown.
import { Knowledge } from '@jangts/agent-core/kits/knowledge';
const document = Knowledge.parseKnowledgeDocument({
id: 'manual', revision: '3',
text: ['<!-- agent-section:start -->', '先运行一个节点。', '<!-- /agent-section:start -->'].join('\n'),
});
const catalog = Knowledge.defineKnowledgeCatalog([document], { maxChars: 2000 });
const read = { documentId: 'manual', selection: { mode: 'self' as const, sectionIds: ['start'] } };
catalog.assertSelection(read);
console.log(catalog.read(read).content);import { Knowledge } from '@jangts/agent-core/kits/knowledge';
const document = Knowledge.parseKnowledgeDocument({
id: 'manual', revision: '3',
text: ['<!-- agent-section:start -->', '先运行一个节点。', '<!-- /agent-section:start -->'].join('\n'),
});
const catalog = Knowledge.defineKnowledgeCatalog([document], { maxChars: 2000 });
const read = { documentId: 'manual', selection: { mode: 'self', sectionIds: ['start'] } };
catalog.assertSelection(read);
console.log(catalog.read(read).content);