item · 2019 × 401
Project Identification Block
not analysedproject_identification_block_p03_r02
Not read yet. Press Analyse crops, or read this one on its own.
Mindmap builder
GDOT 21
1Read the crops52 crops · 0 readconfigured openai/gpt-5.6-terra-pro · about 30¢ for 52 crops · default
Every cropped image from the cropping run, page by page, with what the model read off it: view, objects, measurements, notes and labels. Click a crop to see it beside its JSON.
52 crops, none read yet.
Page 34 crops · 0 read
item · 1745 × 3172
Railroad And Access Road Cross Sections
not analysedrailroad_and_access_road_cross_sections_p03_r03Substructurecross section
Not read yet. Press Analyse crops, or read this one on its own.
item · 1647 × 1516
Surveyed Top Of Rail Elevations
not analysedsurveyed_top_of_rail_elevations_p03_r04
Not read yet. Press Analyse crops, or read this one on its own.
item · 2167 × 1423
Title Block
not analysedtitle_block_p03_r05Substructure
Not read yet. Press Analyse crops, or read this one on its own.
2Map the itemsnot mapped yetconfigured openai/gpt-5.6-terra-pro · $1.00 → $6.00 per M · default
One set of distinct items across every page. The same bent read as “BENT”, “Interior bent” and “Bent No. 2” is one item here, carrying every page and crop it was seen in. One model call over all of step 1’s readings; the page mapping is resolved from its grouping rather than retyped by it.
Read the crops in step 1 first — there is nothing to group yet.
No items yet. Read the crops in step 1, then map them.
3Match the ontologynot matched yetconfigured openai/gpt-5.6-terra-pro · $1.00 → $6.00 per M · default
Every item from step 2 compared against the project’s engineering ontology, and then, for each one that lands in a class, a take-off of what that class asks for. The class list goes up as a closed vocabulary, so regional wording resolves without a synonym table — BENT to a pier system, PSC BEAM to a prestressed girder. Any class id that is not in the ontology is rejected rather than stored. The take-off reads every crop behind an item, derives what the drawings imply, shows its arithmetic, and says plainly when a number is not there.
Map the items in step 2 first — there is nothing to classify yet.
Nothing classified yet. Map the items in step 2, then match them here.
◈Index for the agentnot indexed · 0 points ready
Everything steps 1 and 2 know, written to the vector store for a chat agent to answer from. Cut fine — a point for each object, each measurement and each note, not one per crop — with the page, the crop and the drawing written into every one, so a retrieved number arrives with enough context to be an answer. The readings as a whole and step 2’s items are indexed too, for the questions that are about a drawing rather than a figure.
Re-runnable at any time: each point is keyed to the record it came from, so re-indexing replaces what changed, adds what is new, and drops what the drawings no longer support. Re-read a crop or correct one by hand, then press this.
Nothing to index yet — read the crops in step 1 first.
Collection mindmap_vectors, filtered on projectId = gdot_plan-da748de8ea75458d89b8b2375abd25cc.