Build from Source#

Build the Visual Pipeline and Platform Evaluation Tool from source to customize, debug, or extend its functionality. In this guide, the following tasks are covered:

Setting up the development environment.
Compiling the source code and resolving dependencies.
Generating a runnable build for local testing or deployment.

This guide is intended for developers working directly with the source code.

Prerequisites#

Before starting, ensure the following:

System requirements: The system meets the minimum requirements.
Internet access: The host has outbound internet connectivity. Base images, apt and Python packages, npm dependencies, sample videos, and models are downloaded during the build and on first start. Offline or air-gapped installation is not supported. See Network Requirements.
Docker platform: Docker Engine is installed. On Linux, install it from the Docker apt repository, see Install Docker Engine on Ubuntu, then complete the post-installation steps to run Docker as a non-root user.

Note

Do not use Docker Desktop on Linux. It runs the Docker daemon inside a virtual machine that is not forwarding GPU device on Linux (yet).
Dependencies installed:
- Git: Install Git.
- Make: Standard build tool, typically provided by the build-essential (or equivalent) package on Linux.

For GPU and/or NPU usage, appropriate drivers must be installed. The recommended method is to use the DLS installation script, which detects available devices and installs the required drivers. Follow the Prerequisites section in Install Guide Ubuntu.

Note

The same steps apply to Ubuntu 24.04 running under WSL 2 on Windows - run all commands inside the WSL distribution. On WSL, only the CPU and GPU (WSL) variants are supported. See System Requirements.

This guide assumes basic familiarity with Git commands and terminal usage. For more information, see Git Documentation.

Before building, review the Pre-Installation Steps for optional configuration such as the Hugging Face access token used to download models from the Hugging Face Hub.

Steps to Build#

Clone the repository:

git clone https://github.com/open-edge-platform/edge-ai-libraries.git -b main
cd edge-ai-libraries/tools/visual-pipeline-and-platform-evaluation-tool

Build and start the application:
```
make build run
```
Both make build and make run automatically invoke setup_env.sh, which detects the available hardware (CPU/GPU/NPU) and writes the appropriate .env file. They also create the required directories under shared/.
Verify that the application is running:
```
docker compose ps
```
Access the application:

Open a browser and navigate to http://localhost (or http://<HOST-IP>) to access the Visual Pipeline and Platform Evaluation Tool UI.
Access the application API documentation:

Open a browser and navigate to http://localhost/api/v1/docs (or http://<HOST-IP>/api/v1/docs) to access the Swagger UI.

Optional: run pipelines on DL Streamer Pipeline Server 2.0 (experimental)#

By default, pipelines run inside the vippet container. To run them on a separate DL Streamer Pipeline Server 2.0 container instead, add DLSPS2=1:

make build run DLSPS2=1
make stop DLSPS2=1

This builds the server image from microservices/dlstreamer-pipeline-server/dlsps2 in the same repository, gives it the same devices as vippet, and sets VIPPET_EXECUTION_BACKEND=dlsps2. Current limitations:

Only pipeline validation and single-stream performance tests run on the server. Density tests, multi-stream performance tests and tests with latency metrics still run inside vippet.
A pipeline that finishes in less than about one second reports 0 FPS.

The server is not part of compose.yml, so docker compose logs does not show it. Use docker logs -f dlstreamer-pipeline-server to follow its log, or make shell-dlsps to open a shell in it.

Stop the application#

Stop and remove all running containers:

make stop

Downloaded models and videos under shared/ are preserved. To also remove those artifacts, run:

make clean