Djinious
Document intelligenceEnterprise operations

Making a document archive answerable

A shared drive nobody can query becomes a searchable, cited corpus without a migration project.

Contracts, reports, specifications and the spreadsheets that accompany them are ingested from the document store — PDF and DOCX parsed in-process, tabular files one object per row. Each object is enriched offline for entities, keywords and topics, embedded, and indexed for both full-text and vector search.

A hybrid query returns the passage and the file it came from, so an answer is always traceable to a page.

How it runs

  1. Upload

    Upload into folders and select what to ingest; status and record count land on the document itself.

    Document folders
  2. Enrich

    The deterministic enricher extracts entities, keywords, topics and language with no model required.

    Offline enrichment
  3. Search

    Search in keyword, semantic or hybrid mode across everything ingested.

    Hybrid search
  4. Investigate

    Collect results into an investigation case, where they keep their references back to the source.

    Provenance