INVOICE, NATIONAL_ID, or BANK_STATEMENT, so a workflow can route each page to the right handling. Classification is deterministic: the same page always gets the same result, and no large language model runs at inference time.
Document Classifiers live in your project under Integrations → Document Classifiers, alongside Data Sources, Workflows, and Proxy Connections.
When to use a Document Classifier
FlowX offers two ways to classify documents. Pick based on how well-defined your document types are and how much labeled data you have:Two other features have similar names but do different things: Document Intelligence ingests documents into a knowledge base for AI retrieval, and the Extract Data from File workflow node extracts field values from a document. A Document Classifier only answers one question per page: which category is this?
Create a Document Classifier
1
Open Document Classifiers
In your project, go to Integrations → Document Classifiers and click +.
2
Name the classifier
Enter a Name and an optional Description.
3
Choose how the model gets trained
Leave Use preexisting model bundle toggled OFF to create an empty classifier and train it in FlowX (the usual path). Toggle it ON to import a model bundle exported from another FlowX environment. See Import a pre-trained bundle.
Define classes
Classes are the categories the model sorts pages into. Open the Classes tab and click New class.Must be UPPER_SNAKE_CASE (letters, digits, underscores, starting with a letter, such as
NATIONAL_ID) and unique within the classifier.Describe what differentiates this class from the others. The description guides automatic pre-labeling when you upload unlabeled documents.
UNKNOWN instead of landing in a wrong category.
Build the corpus
The unit of classification is a page, not a file. The Data tab is where labeled pages accumulate into the training corpus. There are two ways to add pages:- Upload unlabeled batch: drop ZIP, PDF, or Word files. Source files can be up to 20 MB each. The pages are pre-labeled automatically and queued for your review; each page needs review before it joins the corpus.
- Upload sorted by class: drop files that are already sorted per class; the pages join the corpus directly, without review.
UNKNOWN go entirely to the test pool. The corpus table shows every page with its class, split, and upload batch. You can remove pages, but not relabel them in place.
Train a model
In the Data tab, select the training pages to use and click Train model. Training requires at least 10 training pages for every class; the lockedUNKNOWN class is exempt. A warning appears when the corpus is heavily imbalanced: when one class has far more pages than another, the model tends to over-predict the bigger one.
Training runs asynchronously. Each successful run produces an immutable model version in the Trained Models tab, with its accuracy metrics, per-class results, and a confusion matrix. You can compare any two versions to see what changed between training runs.
The main version is the one workflows use. The first trained version becomes main automatically; promote a different version when it performs better.
Training and promotion work on the draft (WIP) version of your project. Committing a project version freezes the classifier’s corpus and training for that version. Editing a committed classifier continues on a new draft.
What travels between environments
When you export or build a project, the classifier’s class taxonomy travels with it as part of the versioned configuration. The corpus and trained models do not travel with a project export or build: the target environment receives the classes and trains against its own data. The corpus itself can now move between environments: export a classifier’s corpus and import it into the classifier in the target environment. An imported corpus appears in a read-only view in the classifier’s Data tab, so you can inspect the pages it was trained on without editing them there. Exporting a corpus requires the ML models permission. To move a trained model, use the pre-trained bundle flow described below.Manage trained versions at runtime
Each workspace keeps its own trained versions of a classifier, so a running environment can take a new version without a new build. Open the project, switch to the Runtime view, and select Runtime Content → Document Classifiers. The list shows each classifier’s Name, Defined in, Used by builds, Main version, and Status. Open a classifier to see its Trained Models, Data, and Classes tabs.Promote a version to main
The Trained Models tab lists every version this environment holds for the classifier. One is main: the version served whenever a live workflow calls the classifier. To change it, promote another version and confirm. Promotion takes effect immediately, on every build that runs the classifier, with no rebuild. FlowX compares the version’s classes with the classes your running builds branch on. If they don’t line up, a warning lists:- Classes the builds route on that the version can’t produce: those branches never fire.
- Classes the version produces that no build handles: those pages take the default path.
Import a trained model or a corpus
- Import trained model uploads a trained version exported from another environment. It’s added to the Trained Models list; promote it to serve it in workflows. If the version was already imported, or was exported from a different classifier, FlowX shows a warning first: click Import anyway to continue.
- Import corpus loads labelled pages from an exported corpus (a ZIP file up to 10 MB) into the Data tab. If the file uses classes the classifier doesn’t have, map each one to an existing class or skip its pages: classes can’t be added at runtime. If an import waits for your review, select Finish import.
Import a pre-trained bundle
If you already have a model trained in another FlowX environment, toggle Use preexisting model bundle ON when creating the classifier and upload the exported bundle: a ZIP with the model metadata and binary. FlowX validates the bundle on upload and adds it as an uploaded candidate version:- It must define at least two classes, named in UPPER_SNAKE_CASE, without duplicates.
- Its training metrics must be present and consistent with the declared class set.
- FlowX rejects a bundle that fails validation; nothing is created. A bundle that uploads but fails processing leaves the classifier in a Failed state with a Retry option.
Classify pages in a workflow
Consume the trained model with the Document Classification node from the workflow node palette. The node is a pure classifier: it labels pages and writes the result. Routing happens in a downstream condition node.Output
The node classifies each page independently and writes one result object:predictedLabelis the highest-probability class;classeslists all class probabilities in descending order.low_confidenceistruewhenpredictedProbabilityis below the configured threshold. A low-confidence prediction is still a successful result. Use the condition node to route those pages to human review instead of treating them as failures.- A single page failing to classify populates that page’s
errorand the node still succeeds; the other pages classify normally. - Whole-node failures set the top-level
errorand route to the node’s error output. The error codes:
Route by label
Add a Condition node after the Document Classification node and branch on the result: typically iteratingpages and switching on predictedLabel, with a separate branch for low_confidence pages.
Related resources
Integration Designer
Build workflows that combine classifiers with REST calls, data operations, and AI nodes
Custom Agent node
LLM-based alternative for classification without training data

