The Hugging Face Inference Client in Golang is a modul designed to interact with the Hugging Face model repository and perform inference tasks using state-of-the-art natural language processing models. Developed in Golang, it provides a seamless and efficient way to integrate Hugging Face models into your Golang applications.
go get github.com/hupe1980/go-huggingface
package main
import (
"context"
"fmt"
"log"
"os"
"github.com/hupe1980/go-huggingface"
)
func main() {
ic := huggingface.NewInferenceClient(os.Getenv("HUGGINGFACEHUB_API_TOKEN"))
res, err := ic.ZeroShotClassification(context.Background(), &huggingface.ZeroShotClassificationRequest{
Inputs: []string{"Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!"},
Parameters: huggingface.ZeroShotClassificationParameters{
CandidateLabels: []string{"refund", "faq", "legal"},
},
})
if err != nil {
log.Fatal(err)
}
fmt.Println(res[0].Sequence)
fmt.Println("Labels:", res[0].Labels)
fmt.Println("Scores:", res[0].Scores)
}
Output:
Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!
Labels: [refund faq legal]
Scores: [0.8777876496315002 0.10522633790969849 0.016985949128866196]
For more example usage, see _examples.