Custom Detectors
Custom Detectors
Custom detectors let you extend Classifyre with signals that are specific to your team, domain, or compliance requirements. You define what to detect — a business policy, a content category, an image label — and pick the method that fits the job.
Each custom detector runs one of seven detection engines. This page describes each engine and links to its configuration reference.
Detection methods
Define entities to extract and classification tasks — all run in a single model pass. Ideal for structured information extraction from unstructured text, with no training data required.
Define precise pattern-matching rules using regular expressions. Fast, deterministic, zero ML overhead. Perfect for codes, IDs, and structured formats like IBANs or order numbers.
Use a large language model with a natural-language prompt to classify content and extract structured fields. Best for nuanced, context-dependent detection where examples and rules are hard to define explicitly.
Run any HuggingFace text-classification model. Map predicted labels to severity levels. Ideal for spam detection, toxicity, sentiment, and custom topic classifiers.
Classify images with any HuggingFace vision model. Useful for NSFW detection, harmful content filtering, and custom image category labelling.
Embed text into dense vectors using any HuggingFace sentence-transformer. Store embeddings as findings for downstream semantic search or clustering.
Run any HuggingFace object-detection model on images. Findings include bounding boxes, confidence scores, and label-based severity mapping.
Quick comparison
| Method | Modality | ML required | Best for |
|---|---|---|---|
| GLiNER2 | Text | Pretrained (zero-shot) | Entity extraction without labelled data |
| Regex | Text | No | Codes, IDs, structured patterns |
| AI Detector | Text | LLM (via provider) | Nuanced classification, structured extraction |
| Text Classification | Text | Fine-tuned HF model | Spam, toxicity, sentiment, topic labels |
| Image Classification | Image | Fine-tuned HF model | NSFW, content moderation, custom image categories |
| Feature Extraction | Text | Embedding model | Semantic search, clustering, vector storage |
| Object Detection | Image | Object-detection HF model | Bounding-box localisation, label-based severity |
When to use which method
Start with Regex if you have deterministic patterns — order numbers, internal codes, IBANs. No model, no latency, and the results are exact.
Use GLiNER2 when you need entity extraction (names, places, custom concepts) but you don’t want to manage a labelled training set. It generalises from label names alone.
Use AI Detector for nuanced classification that would be hard to capture with a ruleset — risk signals, renewal intent, escalation tone, or any case where the context matters as much as the words.
Use Text or Image Classification when you have a specific HuggingFace model already suited to your task. You get full control over the model checkpoint, device, and confidence threshold.
Use Feature Extraction when the output is an embedding rather than a label — useful for downstream semantic search or clustering pipelines.
Use Object Detection when you need to locate objects in images with bounding boxes and map specific labels to severity levels.