Document Intelligence

Document search and question-answering system with RAG pipeline, HTTP service, file storage, database, and deployment.

Name	`document-intelligence`
Version	`0.1.0`
Tags	ai, rag, documents, search, typescript
Source	`composites/document-intelligence.yaml`

Render it

# CLI
npx @nanohype/sdk render-composite document-intelligence --out ./my-app

# SDK
import { LocalSource, renderComposite } from "@nanohype/sdk";
const result = await renderComposite(source, "document-intelligence", variables);

# MCP — from an agent
get_composite({ name: "document-intelligence" })

What it draws together

Template	Rendered at	Notes
`monorepo`	root	the root project
`rag-pipeline`	`packages/rag`
`ts-service`	`apps/api`
`module-auth-ts`	`packages/auth`
`module-database-ts`	`packages/db`
`module-storage-ts`	`packages/storage`
`eval-harness`	`packages/evals`	only when `IncludeEvals`
`k8s-deploy`	`infra`

Variables

Required

ProjectName string: Project name used across all templates Must be lowercase kebab-case.

Optional

LlmProvider string — defaults to anthropic: LLM provider for generation
VectorStore string — defaults to pgvector: Vector database backend
IncludeEvals bool — defaults to true: Include evaluation harness