canonical: https://jentic.com/apis/tisane.ai/tisane-api-documentation

# Tisane API Documentation

Tisane is a natural language processing library, providing: * standard NLP functionality * special functions for detection of problematic or abusive content * low-level NLP like morphological analysis and tokenization of no-space languages (Chinese, Japanese, Thai) Tisane has monolithic architecture. All the functions are exposed using the same language models and the same analysis process invoked. The API exposes 6 endpoints.

## For AI agents

Programmatically list hypernyms, list hyponyms. Covers 6 operations.

## Scope

Does not handle payments, communications, or crm - use for ai and machine learning only.

## Capabilities

- List hypernyms
- Get family details
- Integrate Tisane API Documentation into automated workflows
- Query and filter Tisane API Documentation records by parameters
- Monitor Tisane API Documentation operational status and events

## Use cases

### AI and Machine Learning Operations

Use the Tisane API Documentation to perform ai ml operations programmatically. The API provides 6 endpoints covering core functionality including list hypernyms, list hyponyms, list inflected forms.

Example prompt: Call GET /hypernyms to list hypernyms

### Automated NLU / NLP Methods Management

Automate nlu / nlp methods operations by combining multiple Tisane API Documentation endpoints. Agents can list hyponyms and then list inflected forms in a single workflow.

Example prompt: Call GET /hyponyms to list hyponyms, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Tisane API Documentation endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually.

Example prompt: Search Jentic for 'list hypernyms', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/hypernyms` | List hypernyms |
| GET | `/hyponyms` | List hyponyms |
| GET | `/inflections` | List inflected forms |
| GET | `/lm/family` | Get family details |
| GET | `/senses` | List word senses |
| GET | `/values` | List feature values |

## Key resources

- **NLU / NLP Methods** — These are the methods that actually perform the analysis.
- **Language Model Direct Access** — Methods to retrieve and inspect entries from the language models

## Why Jentic

- **Setup:** Wiring the Tisane API by hand means reading its language and lexical endpoints, shaping each query, and handling retries yourself. Through Jentic you install once, import Tisane from the API Directory, and your agent calls it.
- **Permission scoping:** Tisane serves read-only lexical lookups selected by query parameters rather than a resource id in the URL path, so scope the agent by the operations it needs, such as hypernyms or inflections. You choose that set, so lookups you do not name stay unavailable.
- **Credential handling:** Tisane exposes these endpoints without a credential, so there is nothing for Jentic One to store; any account key you add later is held encrypted by your own instance and injected at execution time, never in the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'find hypernyms for a word' or 'get word inflections', and Jentic returns the matching Tisane operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Openai** — Alternative ai ml API
- **Anthropic** — Alternative ai ml API
- **Cohere** — Complementary ai ml API
- **Huggingface** — Complementary ai ml API

## FAQ

### What authentication does the Tisane API Documentation use?

The Tisane API Documentation uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I list hypernyms with the Tisane API Documentation?

Yes. Use the GET /hypernyms endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Tisane API Documentation?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I list hypernyms through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'list hypernyms'. Jentic returns the matching Tisane API Documentation operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Tisane API Documentation have?

The Tisane API Documentation exposes 6 endpoints covering nlu / nlp methods, language model direct access operations.

### Can I limit what my agent is allowed to do with the Tisane API?

Yes. Because you run Jentic One yourself, your own rules decide which Tisane operations and credentials the agent can use. Tisane offers read-only lexical lookups chosen by query parameters, so you can allow only the operations the agent needs, such as GET /hypernyms or GET /inflections, and leave the rest, like GET /senses or GET /values, unavailable. Any lookup you do not grant stays out of the agent's reach.