flinq
DE Login Sign up
What you build

Applications made possible with flinq

On the API you build search, matching and RAG applications over construction data. The examples below show one possible workflow per application. These are applications made possible with flinq, not products flinq ships.

01

LV matching

Match bill-of-quantities line items across projects and catalogues, even when wording differs.

Relevant for TradesConstruction firmsWholesalersManufacturers

Worked example in the docs
A bill of quantities from an external tender and the internal product catalogue are embedded, stored in a vector database and matched to one another via the LV-matching function. The result is matched line items with a similarity score.
Bill of quantities External tender GAEBPDF
Internal product catalogue Your positions CSV
LV matching Function
Embedding
POST /v1/embeddings
POST /v1/embeddings
{
  "input": "Cement screed CT-C25-F4, 60 mm",
  "model":  "flinq-small"
}

Conceptual example. Runnable code in the docs.

Vector database
Stored vectors
IDSourceDim
vec_8a1fBoQ item 01.401024
vec_3c2bIfcWall1024
vec_9d70Datasheet1024
Output
Example output
Line itemMatchScore
Cement screed 60 mmScreed CT-C25-F40.94
Drywall GK 12.5Gypsum board wall F900.88
Rebar Q335AReinforcing mesh0.86
02

Early-phase cost prediction

Derive cost figures from semantically similar line items and reference projects that have already been costed.

Relevant for Planners/ArchitectsConstruction firms

Worked example in the docs
Reference objects are embedded and stored in a vector database; from these an ML model is built. A new project is embedded individually and scored by the same model. The result is a cost figure per square metre.
Reference objects External or internal
Embedding Single object
ML model Trained on references
Embedding
POST /v1/embeddings
POST /v1/embeddings
{
  "input": [ "Office building, 4 floors, KG 300", … ],
  "model": "flinq-small"
}

Conceptual example. Runnable code in the docs.

Vector database
Stored vectors
IDSourceDim
vec_8a1fBoQ item 01.401024
vec_3c2bIfcWall1024
vec_9d70Datasheet1024
New project
Project attributes
AttributeValue
TypeOffice building
Floors4
GFA3,200 m²
Cost groupKG 300
Output
Example output (cost figure)
Reference projectSimilarity€/m²
Admin building Ulm 20230.911,840
Office Stuttgart 20220.871,760
Prediction (weighted)1,805
03

RAG & knowledge management over construction data

Retrieval-augmented generation for company-wide knowledge management: search standards, bills of quantities and project documents with reliable hits.

Relevant for Planners/ArchitectsTradesConstruction firmsWholesalersManufacturers

Worked example in the docs
Internal documents are embedded and stored in a vector database. For a search query, the RAG-retrieval function delivers the most relevant sections to the connected language model, which produces a grounded answer.
Internal documents Your files PDFFotoIFCtxt
LLM Your language model
Output Grounded answer
Embedding
POST /v1/embeddings
POST /v1/embeddings
{
  "input": "Acoustic insulation in drywall",
  "model": "flinq-small"
}

Conceptual example. Runnable code in the docs.

Vector database
Stored vectors
IDSourceDim
vec_8a1fBoQ item 01.401024
vec_3c2bIfcWall1024
vec_9d70Datasheet1024
RAG retrieval
Retrieved sections
SourceSectionScore
DIN 4109-1Sound insulation in buildings0.92
Project file A12Partition walls 1st floor0.81
Tender textStud wall GK0.79
Search query
POST /v1/embeddings
POST /v1/embeddings
{
  "input": "How is sound insulation in drywall regulated?",
  "model": "flinq-small"
}

The query is embedded like the documents and matched over the vectors.

Working examples with real code live in the docs.

More applications

Further applications built on the same embeddings. Filter by audience.

Find the relevant DIN standards

flinq matches your tender text against your own collection of standards and surfaces the relevant DIN standards.

Planners/ArchitectsTradesConstruction firmsManufacturers

Product search and comparison

flinq searches and compares manufacturer products by technical specification and compatibility.

Planners/ArchitectsTradesConstruction firmsWholesalersManufacturers

In progress

Quantities and costs from the BIM model

flinq reads building elements and their quantities directly from the IFC model, as a basis for take-off, costing and billing.

Planners/ArchitectsConstruction firms

Bid comparison (price mirror)

flinq recognises which line items across different bids describe the same work, even when the wording differs, for a real price comparison.

Planners/ArchitectsConstruction firms

Calculation and calculation checking

flinq prices tendered line items using comparable line items from your own project history or external cost databases.

TradesConstruction firms

In progress

From a photo to the product or line item

From a photo of a component, flinq finds the matching product in a catalogue or the corresponding bill-of-quantities item.

TradesConstruction firmsWholesalersManufacturers

Equivalent alternatives on supply shortages

If a product is unavailable, flinq finds technically equivalent alternatives from the range.

TradesConstruction firmsWholesalers

In progress

ETIM/ECLASS classification

flinq classifies products automatically by ETIM or eCl@ss from their description text.

WholesalersManufacturers

Consolidate the product catalogue

flinq detects duplicates and equivalent products from different manufacturers and helps clean up the catalogue.

WholesalersManufacturers

Visibility in tenders

flinq shows which line items your products fit, and where the product description does not yet match the language of tendering.

Manufacturers

These are examples of what is possible with the model. We are continuously working on more. Try it out and read more in the docs.

Get started in the docs