NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)
I'm able to run my nboost container but I can't make an http request.
So this is my docker ps output:
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
07bc9e7b2e4a koursaros/nboost:latest-tf "nboost --uhost elas…" 4 minutes ago Up 4 minutes 0.0.0.0:8000->8000/tcp nboost
And the output of my cURL - curl "http://localhost:8000/travel/_search?pretty&q=passage:vegas&size=2" - is:
curl: (56) Recv failure: Connection reset by peer
And here is my latests outputs of the container:
nboost | 2019-11-27 01:36:57.934037: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
nboost | 2019-11-27 01:36:57.945768: E tensorflow/stream_executor/cuda/cuda_driver.cc:318] failed call to cuInit: UNKNOWN ERROR (-1)
nboost | 2019-11-27 01:36:57.945820: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (07bc9e7b2e4a): /proc/driver/nvidia/version does not exist
nboost | 2019-11-27 01:36:59.531419: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 93763584 exceeds 10% of system memory.
Hi!
I'm able to run my nboost container but I can't make an http request.
So this is my docker ps output:
And the output of my cURL -
curl "http://localhost:8000/travel/_search?pretty&q=passage:vegas&size=2"
- is:And here is my latests outputs of the container:
My docker-compose config is:
And finally I'm seeing the: