Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
fasttext-serving
fastText model serving service
Installation
You can download prebuilt binary from GitHub releases, or install it using Cargo:
cargo install fasttext-servingUsing Docker:
docker pull messense/fasttext-servingUsage
$ fasttext-serving --help
USAGE:
fasttext-serving [OPTIONS] --model <model>
FLAGS:
--grpc Serving gRPC API instead of HTTP API
-h, --help Prints help information
-V, --version Prints version information
OPTIONS:
-a, --address <address> Listen address [default: 127.0.0.1]
-m, --model <model> Model path
-p, --port <port> Listen port [default: 8000]
-w, --workers <workers> Worker thread count, defaults to CPU countServe HTTP REST API
HTTP API endpoint:
POST /predict
Post data should be JSON array of string, for example ["abc", "def"]
CURL example:
$ curl -X POST -H 'Content-Type: application/json' \
--data "[\"Which baking dish is best to bake a banana bread?\", \"Why not put knives in the dishwasher?\"]" \
'http://localhost:8000/predict'
[[["baking"],[0.7152988]],[["equipment"],[0.73479545]]]Serve gRPC API
Run the command with --grpc to serve gRPC API instead of HTTP REST API.
Please refer to gRPC Python client documentation here.
License
This work is released under the MIT license. A copy of the license is provided in the LICENSE file.