AI runtimepackages/ai/document-pipeline
document-pipeline package
Ingestion for PDF / docx / markdown — chunk, table-aware extract, embed, route to @nebutra/knowledge-base. OCR fallback for image-only pages.
- Stability
- Stable
- Scope
- Global
- Boundary
- packages/ai/document-pipeline
document-pipeline
packages/ai/document-pipelineAI runtime · tool registry · MCP boundary
Ready
Capability graph
ai/document-pipelinedocument-pipeline
Tool policy
Stream UI
Output
Run ledger
- 1Inputpackages/ai/document-pipeline/request
- 2Planmessage reducer -> model turn
- 3Tool policytool schema · auth scope · rate limit
- 4Stream UIevents -> UI state machine
- 5Output@nebutra/agents response envelope
p50 latency
56 ms
events/sec
495/s
providers
3
eval score
91
Usagedocument-pipeline.ts
typescriptdocument-pipeline.ts
1import { documentPipeline } from "@nebutra/document-pipeline";
2
3const result = await documentPipeline.run({
4 tenantId: org.id,
5 // document-pipeline is part of the AI runtime — composable with other AI primitives.
6 input: payload,
7});