https://github.com/messense/fasttext-serving

fastText model serving service
https://github.com/messense/fasttext-serving

fasttext model-server model-serving nlp

Last synced: 6 months ago
JSON representation

fastText model serving service

• Host: GitHub
• URL: https://github.com/messense/fasttext-serving
• Owner: messense
• License: other
• Created: 2018-01-22T05:48:05.000Z (over 7 years ago)
• Default Branch: main
• Last Pushed: 2024-11-13T01:42:35.000Z (11 months ago)
• Last Synced: 2025-03-28T15:08:40.292Z (6 months ago)
• Topics: fasttext, model-server, model-serving, nlp
• Language: Rust
• Size: 5.8 MB
• Stars: 59
• Watchers: 5
• Forks: 13
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

          
# fasttext-serving

[![GitHub Actions](https://github.com/messense/fasttext-serving/workflows/CI/badge.svg)](https://github.com/messense/fasttext-serving/actions?query=workflow%3ACI)

[![Crates.io](https://img.shields.io/crates/v/fasttext-serving.svg)](https://crates.io/crates/fasttext-serving)

[![Docker Pulls](https://img.shields.io/docker/pulls/messense/fasttext-serving)](https://hub.docker.com/r/messense/fasttext-serving)

fastText model serving service

## Installation

You can download prebuilt binary from [GitHub releases](https://github.com/messense/fasttext-serving/releases),

or install it using Cargo:

```bash

cargo install fasttext-serving

```

Using Docker:

```bash

docker pull messense/fasttext-serving

```

## Usage

```bash

$ fasttext-serving --help

USAGE:

    fasttext-serving [OPTIONS] --model 

FLAGS:

        --grpc       Serving gRPC API instead of HTTP API

    -h, --help       Prints help information

    -V, --version    Prints version information

OPTIONS:

    -a, --address 
    Listen address [default: 127.0.0.1]

    -m, --model         Model path

    -p, --port           Listen port [default: 8000]

    -w, --workers     Worker thread count, defaults to CPU count

```


### Serve HTTP REST API

HTTP API endpoint:

```

POST /predict

```

Post data should be JSON array of string, for example `["abc", "def"]`

CURL example:

```bash

$ 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](./python).

## License

This work is released under the MIT license. A copy of the license is provided in the [LICENSE](./LICENSE) file.