Technical Drawing Extractor

Read the title block, drawing and revision number, scale, material, tolerances, dimensions, and bill of materials from an engineering drawing or blueprint PDF.

The full guide: Title block, tolerances, and GD&T from a drawing

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Technical Drawing Extractor.

What does the technical drawing extractor read from the title block?

The title block is where a drawing carries its identity, and the extractor reads it: the drawing (document) number, the title of the component or assembly, the revision number (A, B, 1, 2, Rev 01), the scale (1:100, 1:5), the unit of measurement, the drawing type (assembly, detail, schematic), the sheet number within a set, and the organization that released it.

Does it capture dimensions and tolerances?

Yes. The general tolerances field comes back, and a dimensions table returns each dimension's label, value, plus and minus tolerance, and unit, so nominal sizes and their allowances are structured rather than left as free text on the sheet.

Are the bill of materials and components extracted?

A bill of materials table returns each part number, part name, quantity, material, and supplier, and a components table lists subassemblies with their component part number, name, quantity, material, and weight, so BOM callouts on the drawing come across as rows.

What material, sign-off, and revision-history detail comes out?

The primary material and finish, the designer name and date, the approver name and date, the project name, part number, quantity, weight, effective and expiration dates, and reference standards, plus a specifications table and a revision history table listing each revision's number, date, description, designer, and approver.

What are the file limits and privacy terms?

One PDF up to 10MB and 100 pages. The drawing is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Export the fields and tables as CSV, XLSX, or JSON.

Doing this to one file, or to ten thousand?

The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.

See PDF to Markdown if you run this for data and platform teams, or the extraction API if you are building it in.