AI runtimepackages/ai/knowledge-rag
knowledge-rag package
Retrieval-augmented generation pipeline — chunk, embed, store, retrieve, rerank — pluggable per vector store.
- Stability
- Stable
- Scope
- Global
- Boundary
- packages/ai/knowledge-rag
Retrieval pipeline
- Embed queryvector · dim 153612ms
- Search corpus5 / 12,401 chunks84ms
- Re-ranktop 3 surfaced22ms
Retrieved chunks3 of 5
To rotate keys, generate a new key, deploy, then revoke the previous secret.
docs/security/api-keys.md142 tokens
Relevance94%
Programmatic rotation can be scheduled via the /v1/keys/rotate endpoint.
docs/api/keys-endpoint.md96 tokens
Relevance88%
Audit logs capture every key create/revoke event for SOC 2 compliance.
docs/security/audit-log.md128 tokens
Relevance71%
12,401 chunks · 1,536-dim local embeddings · 118ms end-to-end
Usagerag.ts
typescriptrag.ts
1import { createKnowledgeBase } from "@nebutra/knowledge-rag";
2
3const kb = createKnowledgeBase({
4 tenantId: org.id,
5 chunkSize: 800,
6 overlap: 120,
7});
8
9await kb.ingest({ docs: await loadDocs() });
10
11const hits = await kb.search("How do I rotate API keys?", { topK: 5 });
12const context = hits.map((h) => h.text).join("\n---\n");