Extract structured data from construction drawings. Detect annotations, build knowledge graphs, and search across entire drawing sets. Built for: AEC firms, software integrators, document management platforms, and AEC startups building on top of drawing intelligence.

Use Cases

Cross-Reference Indexing

Automatically link section tags, detail callouts, and sheet references across a drawing set

QA/QC Automation

Validate drawing consistency, detect missing references, flag revision conflicts

Quantity Takeoffs

Extract and count components, connections, and annotations

Analytical Model Generation

Build structured data for BIM/analysis workflows

Pricing

Capability	Endpoint	Price
Raw Detection	`POST /v1/drawings`	$0.02/page
Graph Ingestion	`POST /v1/projects/{id}/sheets`	$0.15/page
Search	`POST /v1/projects/{id}/search`	$0.005/query
Query (NL answers)	`POST /v1/projects/{id}/query`	$0.03/query

When to Use What

Need	Use	Cost Example
Fast annotation detection, no storage	Raw Detection	100 pages = $2
Searchable knowledge graph across sheets	Graph Ingestion	100 pages = $15
Find specific entities or components	Search	200 queries = $1
Ask questions in plain English	Query	50 questions = $1.50

Pricing Example

A 96-page structural set with Graph Ingestion + 100 searches + 20 queries = $15.10

Quickstart

Get your API key

Detect annotations (Tier 1)

Fast detection with instant results:

curl -X POST https://api.stru.ai/v1/drawings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  -F "page=1"

Or ingest into knowledge graph (Tier 2)

Create a project and ingest pages for searchable graphs:

# Create project
curl -X POST https://api.stru.ai/v1/projects \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Project"}'

# Ingest a page
curl -X POST https://api.stru.ai/v1/projects/proj_xxx/sheets \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  -F "page=1"

Authentication

All requests require a Bearer token:

Authorization: Bearer <your-api-key>

Tier 1: Raw Detection

Fast geometric detection. No LLM, no graph storage. Returns annotations in ~1-2 seconds. Detects: Leaders, Section Tags, Detail Tags, Revision Triangles, Revision Clouds, Title Block bounds.

POST /v1/drawings

Submit a PDF page for annotation detection. Request (multipart/form-data):

Field	Type	Required	Description
`file`	file	Yes	PDF file (max 50MB)
`page`	integer	Yes	Page number (1-indexed)

curl -X POST https://api.stru.ai/v1/drawings \
  -H "Authorization: Bearer sk-xxx" \
  -F "[email protected]" \
  -F "page=4"

Response (200 OK)

{
  "id": "drw_7f8a9b2c",
  "page": 4,
  "dimensions": {"width": 2592, "height": 1728},
  "processing_ms": 1250,
  "annotations": {
    "leaders": [
      {
        "id": "ldr_001",
        "bbox": [1200, 450, 1400, 520],
        "arrow_tip": [1200, 485],
        "text_bbox": [1280, 450, 1400, 520],
        "texts_inside": [{"id": 45, "text": "W12x26"}]
      }
    ],
    "section_tags": [
      {
        "id": "sec_001",
        "bbox": [800, 600, 850, 650],
        "circle": {"center": [825, 625], "radius": 22},
        "direction": "right",
        "texts_inside": [{"id": 12, "text": "A"}, {"id": 13, "text": "S1.5"}],
        "section_line": {"start": [200, 625], "end": [800, 625]}
      }
    ],
    "detail_tags": [
      {
        "id": "det_001",
        "bbox": [1500, 900, 1550, 950],
        "circle": {"center": [1525, 925], "radius": 22},
        "texts_inside": [{"id": 78, "text": "3"}, {"id": 79, "text": "S1.6"}],
        "has_dashed_bbox": true
      }
    ],
    "revision_triangles": [
      {
        "id": "tri_001",
        "bbox": [600, 300, 620, 330],
        "vertices": [[610, 300], [600, 330], [620, 330]],
        "text": "B"
      }
    ],
    "revision_clouds": [
      {
        "id": "cld_001",
        "bbox": [400, 200, 700, 450]
      }
    ]
  },
  "titleblock": {
    "bounds": [2100, 50, 2550, 1700],
    "viewport": [50, 50, 2100, 1700]
  }
}

GET /v1/drawings/

Retrieve a previously processed drawing.

DELETE /v1/drawings/

Delete a drawing result.

Tier 2: Graph + Search

Full pipeline: detection → LLM enrichment → Neo4j graph → semantic search. What you get:

Entities with semantic descriptions
Relationships between entities
Cross-sheet reference linking
Natural language search and query

Projects

POST /v1/projects

Create a project to group related sheets.

{
  "name": "Building A Structural",
  "description": "96-page structural drawing set"
}

Response

{
  "id": "proj_abc123",
  "name": "Building A Structural",
  "created_at": "2026-01-29T10:00:00Z"
}

GET /v1/projects

List all projects.

GET /v1/projects/

Get project details and stats.

DELETE /v1/projects/

Delete project and all sheets/entities.

Sheets

POST /v1/projects//sheets

Ingest a PDF page into the knowledge graph. Request (multipart/form-data):

Field	Type	Required	Description
`file`	file	Yes	PDF file
`page`	integer	Yes	Page number (1-indexed)
`webhook_url`	string	No	Callback when complete

Response (202 Accepted)

{
  "job_id": "job_xyz789",
  "status": "processing",
  "steps": {
    "detection": "pending",
    "enrichment": "pending",
    "synthesis": "pending",
    "graph": "pending"
  }
}

GET /v1/projects//jobs/

Check ingestion progress.

Response

{
  "job_id": "job_xyz789",
  "status": "complete",
  "steps": {
    "detection": {"status": "complete", "duration_ms": 1200},
    "enrichment": {"status": "complete", "duration_ms": 8500, "tokens": 12400},
    "synthesis": {"status": "complete", "duration_ms": 15000, "tokens": 45000},
    "graph": {"status": "complete", "duration_ms": 800}
  },
  "result": {
    "sheet_id": "S1.4",
    "entities_created": 87,
    "relationships_created": 42
  }
}

GET /v1/projects//sheets

List all sheets in project.

GET /v1/projects//sheets/

Get sheet with all entities.

DELETE /v1/projects//sheets/

Remove sheet from graph.

Search

POST /v1/projects//search

Hybrid semantic search (vector + fulltext + graph traversal).

Price: $0.005 per query

Request:

{
  "query": "W12x26 beam connections at grid A",
  "limit": 10,
  "filters": {
    "sheet_id": "S1.4",
    "entity_type": ["Component", "Connection"]
  },
  "include_graph_context": true
}

Response

{
  "results": [
    {
      "entity": {
        "id": "ent_abc123",
        "type": "Component",
        "label": "W12x26 Steel Beam",
        "description": "Wide flange beam spanning grid A to C",
        "sheet_id": "S1.4",
        "bbox": [450, 320, 1200, 380]
      },
      "score": 0.94,
      "graph_context": {
        "connected_entities": [
          {"id": "ent_def456", "type": "Connection", "label": "Bolted Connection"},
          {"id": "ent_ghi789", "type": "Datum", "label": "Grid A"}
        ],
        "relationships": [
          {"type": "CONNECTS_TO", "fact": "W12x26 beam connects to column at grid A"}
        ]
      }
    }
  ],
  "search_ms": 245
}

Query

POST /v1/projects//query

Ask questions in natural language.

Price: $0.03 per query

Request:

{
  "question": "What beams connect to column C3 on the second floor?"
}

Response

{
  "answer": "Three beams connect to column C3: a W16x31 running east to D3, a W12x26 north to C4, and a W12x26 south to C2.",
  "sources": [
    {"entity_id": "ent_abc", "sheet_id": "S1.4", "label": "W16x31 Beam", "bbox": [800, 400, 1400, 450]}
  ],
  "confidence": 0.92
}

Entities & Relationships

GET /v1/projects//entities

List entities. Filter by sheet_id, type.

GET /v1/projects//entities/

Get entity with all relationships.

GET /v1/projects//relationships

List relationships. Filter by source_id, target_id, type.

Reference

Entity Types
Relationship Types
Rate Limits

Type	Examples
`Sheet`	S1.1, A2.3
`View`	Plan, Section, Detail, Elevation
`Zone`	Title Block, General Notes, Legend
`Component`	Beam, Column, Duct, Pipe
`Connection`	Weld, Bolt
`Datum`	Grid Line, Level
`Annotation`	Leader Note, Dimension
`Callout`	Section Tag, Detail Tag
`Symbol`	North Arrow, Revision Triangle

Type	Description
`CONNECTS_TO`	Physical interface
`SUPPORTS`	Structural load path
`PART_OF`	Assembly hierarchy
`LOCATED_AT_GRID`	At grid intersection
`REFERENCES`	Points to sheet/detail
`DESCRIBES`	Annotates
`REVISES`	Marks revision

Plan	Detection	Graph Ingestion	Search	Query
Free	50/month	10/month	100/month	20/month
Pro	1000/month	500/month	5000/month	500/month
Enterprise	Unlimited	Unlimited	Unlimited	Unlimited

Errors

{"error": {"code": "invalid_page", "message": "Page 15 does not exist (total: 10)"}}
{"error": {"code": "rate_limited", "message": "Too many requests", "retry_after": 30}}

Webhooks

When you provide a webhook_url during sheet ingestion, we’ll POST to it when processing completes:

{
  "event": "sheet.complete",
  "project_id": "proj_abc123",
  "sheet_id": "S1.4",
  "entities_created": 87
}

Header: X-Signature: sha256=<hmac>

Agent Guides

API Reference

Drawing Analysis API

Use Cases

Cross-Reference Indexing

QA/QC Automation

Quantity Takeoffs

Analytical Model Generation

Pricing

Quickstart

Authentication

Tier 1: Raw Detection

POST /v1/drawings

GET /v1/drawings/

DELETE /v1/drawings/

Tier 2: Graph + Search

Projects

POST /v1/projects

GET /v1/projects

GET /v1/projects/

DELETE /v1/projects/

Sheets

POST /v1/projects//sheets

GET /v1/projects//jobs/

GET /v1/projects//sheets

GET /v1/projects//sheets/

DELETE /v1/projects//sheets/

Search

POST /v1/projects//search

Query

POST /v1/projects//query

Entities & Relationships

GET /v1/projects//entities

GET /v1/projects//entities/

GET /v1/projects//relationships

Reference

Errors

Webhooks

Agent Guides

API Reference

​Use Cases

Cross-Reference Indexing

QA/QC Automation

Quantity Takeoffs

Analytical Model Generation

​Pricing

​Quickstart

​Authentication

​Tier 1: Raw Detection

​POST /v1/drawings

​GET /v1/drawings/

​DELETE /v1/drawings/

​Tier 2: Graph + Search

​Projects

​POST /v1/projects

​GET /v1/projects

​GET /v1/projects/

​DELETE /v1/projects/

​Sheets

​POST /v1/projects//sheets

​GET /v1/projects//jobs/

​GET /v1/projects//sheets

​GET /v1/projects//sheets/

​DELETE /v1/projects//sheets/

​Search

​POST /v1/projects//search

​Query

​POST /v1/projects//query

​Entities & Relationships

​GET /v1/projects//entities

​GET /v1/projects//entities/

​GET /v1/projects//relationships

​Reference

​Errors

​Webhooks

Use Cases

Pricing

Quickstart

Authentication

Tier 1: Raw Detection

POST /v1/drawings

GET /v1/drawings/

DELETE /v1/drawings/

Tier 2: Graph + Search

Projects

POST /v1/projects

GET /v1/projects

GET /v1/projects/

DELETE /v1/projects/

Sheets

POST /v1/projects//sheets

GET /v1/projects//jobs/

GET /v1/projects//sheets

GET /v1/projects//sheets/

DELETE /v1/projects//sheets/

Search

POST /v1/projects//search

Query

POST /v1/projects//query

Entities & Relationships

GET /v1/projects//entities

GET /v1/projects//entities/

GET /v1/projects//relationships

Reference

Errors

Webhooks