• Hardware Platform : GPU
• DeepStream Version: 5.1.0
• TensorRT Version: 188.8.131.52
• NVIDIA GPU Driver Version:470.57.02
• Issue Type : new requirement
• Requirement details : I would like to know whether it is possible to call a REST API (custom inferencing service bundled with triton server) from gst-nvinfer plugin in deepstream-app pipeline. This REST API is a custom REST API, which is doing a part of what gst-nvinferserver is doing. Only way for us to access our triton server is through this custom REST API. Attached
data.json (134 Bytes) is a sample of json file which is being utilized by the REST API.
As there is no grpc endpoint accessible from nvinferserver plugin for deepstream-app, we are looking into modifying nvinfer plugin.
Question is → How & where do we invoke this REST API in gst-nvinfer plugin and if we have to pass the buffer, meta info passed by upstream plugins to the custom REST API, how and where do we do that leaving all other pipeline elements intact?