Skip to content
← All workDeployed

Multi-Tenant Document Q&A API

Built a reusable multi-tenant RAG backend in Node.js: layout-aware OCR ingestion, table-safe chunking, token-budgeted embeddings and HNSW vector indexing, serving cited conversational answers to several client front ends.

Role
Lead backend engineer · ingestion, retrieval & API
Year
2023–2024
Type
RAG & search
Stack
Azure OpenAI · Azure AI Search · Node.js · Express · LangChain JS · Document Intelligence · Redis vector store · Azure Blob Storage · Cosmos DB · Azure App Service

The problem

Teams kept policies, brochures, spreadsheets and scanned PDFs scattered across storage, and finding an answer meant opening files one by one. One backend had to serve multiple client deployments, each seeing only its own documents, with cited answers and follow-up suggestions.

Architecture

  1. 01

    Upload

    Files land in tenant-scoped Blob Storage with progress tracking and no-overwrite protection; Markdown and text converted to citable PDF.

  2. 02

    Parse

    Document Intelligence layout output rebuilt into reading-order page text with tables rendered inline as HTML.

  3. 03

    Chunk & embed

    Sentence-aware, table-safe chunks embedded in batches capped by item count and tiktoken budget, with retry and back-off.

  4. 04

    Index

    Chunks upserted into an HNSW cosine vector index with semantic configuration, tagged with page-level source references.

  5. 05

    Answer

    History-aware question rewriting, retrieval and grounded generation with filename citations, follow-up questions and fresh SAS links.

Engineering highlights

  • 01

    Layout-aware page reconstruction

    Built a character map of each page's spans to locate table regions, replacing them in reading order with HTML tables preserving row and column spans, so tabular data survives into retrieval intact.

  • 02

    Table-safe chunking

    Roughly 1,000-character chunks with overlap snap to sentence boundaries; if a chunk ends inside an unclosed table, the next starts at the table's beginning, so tables are never split mid-row.

  • 03

    Origin-based tenant routing

    A per-environment map binds each allowed front-end origin to its own storage account and container; upload, listing, SAS generation and citation lookup all resolve through it, isolating tenants on one backend.

  • 04

    Idempotent vector writes

    Chunk keys are SHA-1 hashes of source URL and chunk index, so re-uploads overwrite rather than duplicate. Removal pages through chunks by source filter until none remain.

  • 05

    Rate-limit-aware embedding

    Embedding requests are grouped by item count and tiktoken budget, with configurable retries and long back-off windows, and index uploads are batched to keep large ingestions within service quotas.

Next projectAI Property Brochure Generator