> This page is for version 3.3.0 (default).
> For other versions, use one of these documentation indexes:
> - 3.3.0 (default): https://docs.nvidia.com/vss/3.3.0/llms.txt
> - Dev: https://docs.nvidia.com/vss/dev/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/vss/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server.

# API Reference

> REST endpoints for the Real Time Video Intelligence CV (RTVI-CV) microservice.

This page provides API reference for the **Real Time Video Intelligence CV (RTVI-CV) Microservice**.

## Base URL

The API is available at `http://<host>:9000`. All API endpoints are prefixed with `/api/v1`.

## Endpoint catalog

| Method | Endpoint                           | Description                                                                           |
| ------ | ---------------------------------- | ------------------------------------------------------------------------------------- |
| `GET`  | `/api/v1/live`                     | Liveness probe                                                                        |
| `GET`  | `/api/v1/ready`                    | Readiness probe                                                                       |
| `GET`  | `/api/v1/startup`                  | Startup probe                                                                         |
| `GET`  | `/api/v1/metrics`                  | Prometheus metrics. Optional headers: `X-REFRESH-PERIOD`, `X-OTLP-URL`                |
| `GET`  | `/api/v1/stream/get-stream-info`   | List configured streams                                                               |
| `POST` | `/api/v1/stream/add`               | Add a stream                                                                          |
| `POST` | `/api/v1/generate_text_embeddings` | Generate vector embeddings from text. Registered only when `[text-embedder] enable=1` |

> **Note**
>
> Stock warehouse object-detection configs leave `[text-embedder] enable=0`, so `POST /api/v1/generate_text_embeddings` is not registered and returns an endpoint-not-found response until you enable the module. Search-profile configs enable it by default. Refer to [Text embedder (config)](/system-components/vision-microservices/object-detection-and-tracking#text-embedder-config) for the enable flag, model paths, and request examples.

Request and response examples for stream management and embeddings are on [Object Detection and Tracking](/system-components/vision-microservices/object-detection-and-tracking).