Greg

When large amount of regions is being processed we received an exception from GRPC. Not able to replicate that currently. ``` [INFO ][2023-10-05 16:10:47.163][186145150 : ][pool-5-thread-10 ][ultAssetGenerationService] Time taken to...

Need to implement gRPC Server Events via `ToastHandler` to provider easier integration with services.

Implement Extractor proposed in : https://arxiv.org/pdf/2309.10952.pdf

Need to be able to handle WebP images

Implements `Levenshtein OCR` - https://arxiv.org/abs/2209.03594 - https://paperswithcode.com/paper/levenshtein-ocr - https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/LevOCR.

Need to convert TrOCR to ONNX version This would be a good start. [Faster_TrOCR_with_ONNX+AutoRegressive_Hack.ipynb ](https://github.com/IlyasMoutawwakil/Faster-TrOCR/blob/main/Faster_TrOCR_with_ONNX%2BAutoRegressive_Hack.ipynb)

When launching a cluster of GPU servers we can exceed number of requests sent to torch.hub and get following error: `HTTPError 403: 'rate limit exceeded'` This is possibly related to...

Inspecting `sudo dmesg | grep 'oom-kill'` we find that the process has a memory leak. ``` [595453.487193] ERAAgent invoked oom-killer: gfp_mask=0x1100cca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=0 [595453.487457] oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=eraagent.service,mems_allowed=0,global_oom,task_memcg=/system.slice/docker-ceaea40258ae16cdce82902830385c73299ca6a69cec4d88fb2bf69b4891f3b9.scope,task=marie,pid=2740,uid=0 [2237411.969010] marie invoked oom-killer: gfp_mask=0x1100dca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO),...

When service goes into invalid state the application returns status code `404` which is not a valid JSON response. So the target application will throw following error. ``` ERROR [182866178...