A technical-books catalogue with context built in.

Flat chunk search loses the catalogue around the answer.

A useful book explorer should answer a question and show where to read next. Chunk-only retrieval can match a BOOK_CHUNK like "bound queues keep downstream failure visible" while dropping the CHAPTER title, BOOK title, AUTHOR name, and TOPIC that would make the recommendation trustworthy enough to act on, forcing a manual join back to the catalogue metadata.

Graph intelligence on ingest

Incoming data becomes queryable graph context.

A BOOK payload nests AUTHOR, TOPIC, CHAPTER, and BOOK_CHUNK records in one import. RushDB links each BOOK_CHUNK to its parent CHAPTER, BOOK, AUTHOR, and TOPIC automatically, so once a managed index is created on BOOK_CHUNK.text, a semantic match carries its full provenance path instead of returning an orphaned excerpt.

Suggested relationship analysis requires an LLM configured for the project. Suggestions stay in draft form until you approve them, so inferred domain meaning never mutates the graph silently. You can also add explicit relationships through the SDK or API.

Data model

One flexible graph for the workflow.

Start with the payload shape your product already produces. RushDB stores it as Records, infers typed properties, and keeps nested or approved domain relationships queryable.

{
  "isbn": "978-1-0000-0042-1",
  "title": "Reliable Services in Practice",
  "AUTHOR": [{ "name": "Mina Patel" }],
  "TOPIC": [{ "name": "distributed systems" }, { "name": "backpressure" }],
  "CHAPTER": [{
    "title": "Backpressure and recovery",
    "chapterNumber": 7,
    "BOOK_CHUNK": [
      { "chunkId": "chunk-7-03", "text": "Bound queues keep downstream failure visible..." }
    ]
  }]
}

Working example

Recommend a book and cite the chapter.

Search indexed chapter excerpts for a practical distributed-systems question, then return the matching book, chapter, author, and topic context.

BOOK "Reliable Services in Practice"
  AUTHOR "Mina Patel"
  TOPIC "distributed systems"
  CHAPTER "Backpressure and recovery"
    BOOK_CHUNK.text "Bound queues keep downstream failure visible..."

{
  "labels": ["BOOK_CHUNK"],
  "propertyName": "text",
  "query": "practical tracing, backpressure, and recovery patterns"
}

{
  "book": "Reliable Services in Practice",
  "author": "Mina Patel",
  "chapter": "Backpressure and recovery",
  "topic": "distributed systems"
}

TypeScript SDK

A complete starting point.

The example includes the one-time index setup so the retrieval path is explicit.

from rushdb import RushDB

db = RushDB('RUSHDB_API_KEY')

db.records.import_json({
    'label': 'BOOK',
    'data': [{
        'title': 'Reliable Services in Practice',
        'AUTHOR': [{'name': 'Mina Patel'}],
        'TOPIC': [{'name': 'distributed systems'}],
        'CHAPTER': [{'title': 'Backpressure and recovery', 'BOOK_CHUNK': [{'text': 'Bound queues keep downstream failure visible...'}]}],
    }],
})
db.ai.indexes.create({'label': 'BOOK_CHUNK', 'propertyName': 'text'})
matches = db.ai.search({'labels': ['BOOK_CHUNK'], 'propertyName': 'text', 'query': 'practical tracing and recovery patterns'})

Implementation blueprint

Build the books GraphRAG path.

Use this sequence to keep catalogue browsing, semantic retrieval, and citation provenance on the same graph.

Relevant docs

Read the exact primitives behind this pattern.

These links point to the RushDB docs pages that map directly to this blueprint: ingestion, labels, properties, values, SearchQuery, relationships, semantic search, MCP, or deployment.

How it works

Build the smallest useful workflow first.

Know where it fits.

Questions developers ask.