A Docker setup for running Typesense with GPU support using the NVIDIA Container Toolkit.
This repository provides a Docker setup for running Typesense with GPU support. It leverages the NVIDIA Container Toolkit to utilize the GPU for Typesense operations.
Before you start, ensure you have the following installed:
Clone the repository:
git clone https://github.com/0x4139/typesense-gpu.git
cd typesense-gpu
To start the Typesense service, run the following command:
docker-compose up -d
This command will build and run the Typesense container with GPU support.
You can specify different versions of Typesense and CUDA by modifying the .env file in the repository. Create a .env file in the root directory if it doesn't exist and add the following content:
TYPESENSE_VERSION=your_typesense_version
CUDA_VERSION=your_cuda_version
API_KEY=your_api_key
Replace your_typesense_version, your_cuda_version, and your_api_key with the desired versions and API key.
The following environment variables can be configured in the .env file:
TYPESENSE_VERSION: The version of Typesense to use.CUDA_VERSION: The version of CUDA to use.API_KEY: The API key for Typesense.Ensure you have the NVIDIA Container Toolkit installed and configured. Follow the NVIDIA Container Toolkit Installation Guide to set up the toolkit.
Additionally, make sure your system has the appropriate NVIDIA drivers installed that are compatible with your desired CUDA version.
Contributions are welcome! Please submit a pull request or open an issue to discuss any changes or enhancements.
This project is licensed under the MIT License. See the LICENSE file for details.
By following these instructions, you should be able to successfully run Typesense with GPU support on your machine. If you encounter any issues, feel free to open an issue in the repository.
Content type
Image
Digest
sha256:f746f4e3c…
Size
2.4 GB
Last updated
7 months ago
docker pull 0x4139/typesense-gpu:29.0-cuda11.8.0-cudnn8-runtime-ubuntu22.04