> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/reference/inference/choosing-the-right-tool.md).

# Choosing the Right Tool

[Inference](https://github.com/roboflow/inference) is the open source computer vision deployment framework behind Roboflow's hosted APIs. It ships as four pieces that work together. Most projects run the server and talk to it with the SDK.

| Component                                                                             | What it is                                                                                         | When to use it                                                                                                          |
| ------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| [Inference server](https://docs.roboflow.com/deployment/self-hosted/inference-server) | A Docker container that exposes models and Workflows over an HTTP API.                             | You want one deployment that many clients, languages, or video streams can call.                                        |
| [`inference` package](/reference/inference/inference-python.md)                       | The Python library that loads and runs models directly in your own process.                        | Lowest latency, no HTTP hop; your app is Python and runs on the same machine as the model.                              |
| [`inference-sdk` package](/reference/inference/inference-sdk.md)                      | A lightweight Python HTTP client for the server.                                                   | The standard way to call a local server, the Serverless Hosted API, or a Dedicated Deployment - only `api_url` changes. |
| [`inference-cli` package](/reference/inference/inference-cli.md)                      | The command line tool that starts servers, runs models and Workflows, and benchmarks a deployment. | Installing and managing the server, quick one-off predictions, benchmarking.                                            |

For the architecture of a running server (how requests, video streams, and Workflows flow through it), see [Inference Architecture](https://docs.roboflow.com/deployment/self-hosted/inference-server/architecture). To install and run the server on your own hardware, start with [Self-Hosted Deployment](https://docs.roboflow.com/deployment/self-hosted/self-hosted).

## Example notebooks

Runnable notebooks that solve a specific problem with Inference:

* [Use CLIP to classify videos](https://github.com/roboflow/inference/blob/main/docs/notebooks/clip_classification.ipynb) - identify the similarity of frames in a video to arbitrary text prompts.
* [Stream video with WebRTC](/reference/inference/inference-sdk/webrtc.md) - process a webcam, RTSP stream, or video file with a model or Workflow.
* [RGB anomaly detection](https://github.com/roboflow/inference/blob/main/docs/notebooks/rgb_anomaly_detection.ipynb) - verify that the color in a segmentation mask is correct.

The [Roboflow Notebooks](https://github.com/roboflow/notebooks) repository has many more training and deployment examples.

## Community and source code

* [Inference on GitHub](https://github.com/roboflow/inference) - source code, issues, and feature requests. See [CONTRIBUTING.md](https://github.com/roboflow/inference/blob/main/CONTRIBUTING.md) to contribute.
* [Roboflow Forum](https://discuss.roboflow.com) - get help from and connect with a community of computer vision developers.
* [Roboflow Blog](https://blog.roboflow.com) - tutorials, model releases, and computer vision news.
* [Supervision](https://supervision.roboflow.com) - reusable utilities for annotating, filtering, and tracking predictions.