# Nyckel

> Nyckel lets developers create machine learning functions that classify,
> detect, search, and predict from images, text, structured data, and
> multimodal inputs, then improve automatically from annotated production
> samples.

Nyckel provides machine learning functions that classify, detect, search, and
predict from images, text, structured data, or multimodal inputs through a
simple API. A machine learning function is a hosted endpoint that recognizes
patterns in data and returns predictions. Developers define the task, labels,
and examples; Nyckel handles model selection, training, optimization, hosting,
and deployment. Nyckel can use foundation models to produce initial
predictions before any training data is collected — teams start invoking the
function immediately and improve accuracy over time by reviewing and
annotating real production samples.

## What you can build

### Start simple (5 minutes)

Create a function, define a few labels, and start invoking it from your app.
Zero-shot foundation models give you usable predictions on day one — no
training data required.

- Add image classification to an app prototype
- Route support tickets to the right team
- Tag user-uploaded content

### Make it better (an afternoon)

As real traffic flows through the function, capture samples, review the ones
the model was uncertain about, and correct their labels. Nyckel retrains
automatically — accuracy climbs without you managing the model.

- Reach production-grade accuracy on your most common categories
- Catch and fix systematic mistakes before they spread
- Build a labeled dataset as a byproduct of normal usage

### Production scale (when you need it)

Use Sample Sets to group held-out evaluation data, function summaries to track
training progress, and search/detect/multimodal function types when
classification isn't enough.

- Run regression checks before promoting a new model version
- Build a semantic search index over a product catalog
- Combine images with structured metadata for higher-fidelity predictions

## The minimal path — get a function working in five calls

1. **Create a Function** — `POST /v1/functions`
   Create the function. Choose input modality (Text/Image/Tabular) and output
   modality (Classification/Detection/Search/etc) — these are immutable.
   https://www.nyckel.com/docs/api/operations/post-function/

2. **Create a Label** — `POST /v1/functions/{functionId}/labels`
   Define the categories the function can predict. Repeat for each label.
   https://www.nyckel.com/docs/api/operations/post-label/

3. **Invoke a Function** — `POST /v1/functions/{functionId}/invoke`
   Send input data and get a prediction. Works zero-shot from the first call
   — no training data needed.
   https://www.nyckel.com/docs/api/operations/invoke-function/

4. **List Samples** — `GET /v1/functions/{functionId}/samples`
   Pull the production samples that were captured. Filter by low confidence
   or disagreement to find the ones worth reviewing.
   https://www.nyckel.com/docs/api/operations/list-samples/

5. **Update a Sample** — `PUT /v1/functions/{functionId}/samples/{sampleId}/annotation`
   Correct a sample's label. The next automatic retrain learns from it. Loop
   steps 3–5 to keep improving.
   https://www.nyckel.com/docs/api/operations/put-annotation/

## When you need more

- **Sample Sets** (`POST /v1/functions/{functionId}/samples/{sampleId}/sample-sets`) — Group samples into named sets. Useful for held-out evaluation data and structured cohorts.
  https://www.nyckel.com/docs/api/operations/post-sample-set-to-sample/
- **Get a Function** (`GET /v1/functions/{functionId}`) — Inspect the function's configuration and a live summary of sample counts, annotated counts, and per-label distribution.
  https://www.nyckel.com/docs/api/operations/get-function/

## All operations

### Functions

- `List` — GET `/v1/functions` — Returns every Function in your project. Use the startIndex / count parameters — https://www.nyckel.com/docs/api/operations/list/
- `PostFunction` — POST `/v1/functions` — Creates a new Function. Specify the input modality — https://www.nyckel.com/docs/api/operations/post-function/
- `GetFunction` — GET `/v1/functions/{functionId}` — Returns the Function's static configuration — the properties set at — https://www.nyckel.com/docs/api/operations/get-function/
- `PutFunction` — PUT `/v1/functions/{functionId}` — Updates the name or `projectId` of a Function. Input and output modality — https://www.nyckel.com/docs/api/operations/put-function/
- `DeleteFunction` — DELETE `/v1/functions/{functionId}` — Permanently deletes the Function and all its Labels, Samples, and Annotations — https://www.nyckel.com/docs/api/operations/delete-function/
- `GetFunctionSummary` — GET `/v1/functions/{functionId}/summary` — Returns aggregate counts for a Function — total samples, annotated (see https://www.nyckel.com/docs/api/operations/get-function/#get-function-summary)

### Labels

- `ListLabels` — GET `/v1/functions/{functionId}/labels` — List labels — https://www.nyckel.com/docs/api/operations/list-labels/
- `PostLabel` — POST `/v1/functions/{functionId}/labels` — Create label — https://www.nyckel.com/docs/api/operations/post-label/
- `GetLabel` — GET `/v1/functions/{functionId}/labels/{labelId}` — Get label — https://www.nyckel.com/docs/api/operations/get-label/
- `PutLabel` — PUT `/v1/functions/{functionId}/labels/{labelId}` — Update label — https://www.nyckel.com/docs/api/operations/put-label/
- `DeleteLabel` — DELETE `/v1/functions/{functionId}/labels/{labelId}` — Delete label — https://www.nyckel.com/docs/api/operations/delete-label/

### Samples

- `ListSamples` — GET `/v1/functions/{functionId}/samples` — Lists Samples for a Function. Supports rich filtering: by annotation / — https://www.nyckel.com/docs/api/operations/list-samples/
- `PostSample` — POST `/v1/functions/{functionId}/samples` — Create sample — https://www.nyckel.com/docs/api/operations/post-sample/
- `DeleteSampleByExternalId` — DELETE `/v1/functions/{functionId}/samples` — Delete sample by external id (see https://www.nyckel.com/docs/api/operations/delete-sample/#delete-sample-by-external-id)
- `GetSample` — GET `/v1/functions/{functionId}/samples/{sampleId}` — Get sample — https://www.nyckel.com/docs/api/operations/get-sample/
- `PutAnnotation` — PUT `/v1/functions/{functionId}/samples/{sampleId}/annotation` — Sets (or replaces) the Sample's annotation to the given Label. If the — https://www.nyckel.com/docs/api/operations/put-annotation/
- `DeleteSample` — DELETE `/v1/functions/{functionId}/samples/{sampleId}` — Delete sample — https://www.nyckel.com/docs/api/operations/delete-sample/
- `DeleteAnnotation` — DELETE `/v1/functions/{functionId}/samples/{sampleId}/annotation` — Removes the Sample's annotation. The Sample itself remains in the (see https://www.nyckel.com/docs/api/operations/put-annotation/#delete-annotation)
- `PostSampleSetToSample` — POST `/v1/functions/{functionId}/samples/{sampleId}/sample-sets` — Adds the Sample to the named Sample Set. The Sample Set is created — https://www.nyckel.com/docs/api/operations/post-sample-set-to-sample/
- `DeleteSampleSetFromSample` — DELETE `/v1/functions/{functionId}/samples/{sampleId}/sample-sets/{sampleSetId}` — Removes the Sample from the named Sample Set. The Sample itself remains (see https://www.nyckel.com/docs/api/operations/post-sample-set-to-sample/#delete-sample-set-from-sample)

### Fields

- `ListFields` — GET `/v1/functions/{functionId}/fields` — List fields — https://www.nyckel.com/docs/api/operations/list-fields/
- `PostField` — POST `/v1/functions/{functionId}/fields` — Create field — https://www.nyckel.com/docs/api/operations/post-field/
- `GetField` — GET `/v1/functions/{functionId}/fields/{fieldId}` — Get field — https://www.nyckel.com/docs/api/operations/get-field/
- `PutField` — PUT `/v1/functions/{functionId}/fields/{fieldId}` — Update field — https://www.nyckel.com/docs/api/operations/put-field/
- `DeleteField` — DELETE `/v1/functions/{functionId}/fields/{fieldId}` — Delete field — https://www.nyckel.com/docs/api/operations/delete-field/

### Invoke

- `InvokeFunction` — POST `/v1/functions/{functionId}/invoke` — Sends an input to a trained Function and returns a `FunctionOutput` — https://www.nyckel.com/docs/api/operations/invoke-function/

### Search Functions

- `Invoke` — POST `/v1/search-functions/{functionId}/invoke` — Search Functions return nearest-neighbor Samples instead of a Label — https://www.nyckel.com/docs/api/operations/invoke/

## Schemas

- `Annotation` (ontology: Annotation) — https://www.nyckel.com/docs/api/schemas/annotation/
- `CaptureReason` — https://www.nyckel.com/docs/api/schemas/capture-reason/
- `Error` — https://www.nyckel.com/docs/api/schemas/error/
- `Field` (ontology: Field) — https://www.nyckel.com/docs/api/schemas/field/
- `FieldType` — https://www.nyckel.com/docs/api/schemas/field-type/
- `Function` (ontology: Function) — https://www.nyckel.com/docs/api/schemas/function/
- `FunctionInputModality` — https://www.nyckel.com/docs/api/schemas/function-input-modality/
- `FunctionOutput` — https://www.nyckel.com/docs/api/schemas/function-output/
- `FunctionOutputModality` — https://www.nyckel.com/docs/api/schemas/function-output-modality/
- `FunctionSummary` — https://www.nyckel.com/docs/api/schemas/function-summary/
- `IFunctionInput` — https://www.nyckel.com/docs/api/schemas/i-function-input/
- `InvokeInput` — https://www.nyckel.com/docs/api/schemas/invoke-input/
- `Label` (ontology: Label) — https://www.nyckel.com/docs/api/schemas/label/
- `LabelConfidence` — https://www.nyckel.com/docs/api/schemas/label-confidence/
- `LabelCountDictionary` — https://www.nyckel.com/docs/api/schemas/label-count-dictionary/
- `Prediction` (ontology: Prediction) — https://www.nyckel.com/docs/api/schemas/prediction/
- `Sample` (ontology: Sample) — https://www.nyckel.com/docs/api/schemas/sample/
- `SampleOrigin` — https://www.nyckel.com/docs/api/schemas/sample-origin/
- `SampleSetRelationship` — https://www.nyckel.com/docs/api/schemas/sample-set-relationship/
- `SampleSortBy` — https://www.nyckel.com/docs/api/schemas/sample-sort-by/
- `SearchInvokeInput` — https://www.nyckel.com/docs/api/schemas/search-invoke-input/
- `SearchSample` — https://www.nyckel.com/docs/api/schemas/search-sample/
- `SortOrder` — https://www.nyckel.com/docs/api/schemas/sort-order/
- `WritableField` — https://www.nyckel.com/docs/api/schemas/writable-field/
- `WritableFunction` — https://www.nyckel.com/docs/api/schemas/writable-function/
- `WritableLabel` — https://www.nyckel.com/docs/api/schemas/writable-label/
- `WritableSample` — https://www.nyckel.com/docs/api/schemas/writable-sample/

## When not to use Nyckel

Nyckel is not primarily a text generation, chatbot, or LLM platform. It is
built for structured predictions — classifications, detections, similarity
rankings, and tabular outputs — where the answer space is bounded and the
model can improve from labeled examples. If you need open-ended natural
language generation, summarization, or conversational responses, a general LLM
provider is a better fit.

## More

- Homepage: https://www.nyckel.com/
- Documentation: https://www.nyckel.com/docs/
- API reference: https://www.nyckel.com/docs/api/
- OpenAPI spec: https://www.nyckel.com/openapi/v1.json
- Full LLM doc: https://www.nyckel.com/llms-full.txt
- Pretrained classifiers: https://www.nyckel.com/pretrained-classifiers/
- Pretrained detectors: https://www.nyckel.com/pretrained-detectors/