This sample script utilizes @grpc/proto-loader to dynamically load .proto
files at runtime, and @grpc/grpc-js to implement gRPC functionality for Node.js.
Node 12+ is recommended
Clone the triton-inference-server/common repository:
git clone https://github.com/triton-inference-server/common/ -b <common-repo-branch> common-repo
<common-repo-branch> should be the version of the Triton server that you intend to use (e.g. r21.05).
Copy *.proto files to ./proto
mkdir proto
cp common-repo/protobuf/*.proto ./proto/
Install dependencies with
npm install
Finally, run with
node client.js <host> <port>
hostis the server where triton inference server is running. Default islocalhost.portis the grpc port of triton inference server. Default is8001.