For the complete documentation index, see llms.txt. Every documentation page is also served as markdown: append .md to its URL or request it with Accept: text/markdown. A single-file snapshot of all docs is at llms-full.txt.

Alloovium

Projets

Document Types

Alloovium classe automatiquement les documents pour optimiser l'analyse. Découvrez les types pris en charge et comment fonctionne le pipeline de traitement.

Document Types

Alloovium automatically classifies uploaded documents into categories to help with organisation and to optimise analysis. Common types include contracts, specifications, drawings, reports, and correspondence. You can also assign a custom type to any document.

TypeDescriptionIdéal pour
ContractLegal agreements and subcontractsPayment terms, obligations, liquidated damages
SpecificationTechnical and performance specsScope verification, compliance checking
DrawingEngineering and architectural drawingsDiscipline and revision tracking
RFI / RFI ResponseRequests for information and their answersOpen-item tracking, notice history
SubmittalShop drawings, samples, product dataApproval status, review turnaround
ITPInspection & test plansHold points, quality verification
SWMS / JSASafe work method statements, job safety analysesSafety compliance, high-risk work
Register / LogSchedules, registers, and logsVariation, defect, and notice tracking
ReportSite and inspection reportsIssue tracking, defect management
CorrespondenceEmails, letters, instructionsNotice tracking, variation history
Meeting MinutesRecords of site and project meetingsActions, decisions, attendance
Permit / TransmittalPermits and document transmittalsApprovals, issue records
Environmental (EMP / CEMP)Environmental management plansCompliance obligations, conditions

Around twenty categories are recognised in total, plus a general fallback. You can override the type on any document.

Processing Pipeline

Understanding how Alloovium processes your documents helps you get the most out of the platform. Each document goes through the following stages:

  1. Text extractionAlloovium reads the raw text from each page. For scanned PDFs and images, GPU-accelerated OCR is applied automatically.
  2. Layout analysisThe document structure is analysed: headings, tables, figures, and paragraph blocks are identified and tagged.
  3. ChunkingThe document is split into semantically meaningful segments (typically 200–500 tokens each) that are small enough for precise retrieval.
  4. EmbeddingEach chunk is converted into a vector embedding using a high-dimensional model trained on technical and legal language.
  5. IndexingEmbeddings are stored in a vector index for fast similarity search, enabling sub-second retrieval during AI queries.

GPU extraction

Alloovium uses GPU-accelerated document extraction for complex PDFs and engineering drawings. This means higher accuracy on scanned documents, tables with merged cells, and multi-column layouts.