4 个版本 (2 个破坏性版本)
0.5.0 | 2023 年 7 月 3 日 |
---|---|
0.4.0 | 2023 年 6 月 29 日 |
0.3.1 | 2023 年 6 月 28 日 |
0.3.0 | 2023 年 6 月 28 日 |
#758 在 机器学习 中
每月 21 次下载
17KB
291 行
Hugging face API 封装器
这是什么?
我使用 hugging face 推理 API。我为这个 API 写了一个封装器。目前它可以检测文本中的情绪,检测文本中的地点和人,并回答关于文本的问题。
示例用途
[dependencies]
huggingface_inference_rs = "0.3.0"
tokio = { version = "1.28.2", features = ["rt-multi-thread", "macros"] }
#[tokio::main]
async fn main() {
let mut config = hg_api::Config::default();
config.key = "hf_key".to_string();
let client = hg_api::Client::new(config);
let test_string = "This is the story of a man named Stanley. Stanley worked for a company in a big building where he was Employee #427. Employee #427's job was simple: he sat at his desk in Room 427 and he pushed buttons on a keyboard. ".to_string();
let emotions = client.get_emotions(test_string.to_owned()).await;
let classifications = client.get_classifications(test_string.to_owned()).await;
let answer = client
.get_question(
test_string,
"what employee number does stanly have?".to_string(),
)
.await;
match emotions {
Ok(emotions) => {
for emotion in emotions {
println!("{},{}", emotion.label, emotion.score);
}
}
Err(e) => {
println!("{}", e);
}
}
match classifications {
Ok(classifications) => {
for classification in classifications {
println!("{},{}", classification.entity_group, classification.word);
}
}
Err(e) => {
println!("{}", e);
}
}
match answer {
Ok(answer) => {
println!("{}", answer.answer)
}
Err(e) => {
println!("{}", e);
}
}
}
依赖关系
~8–24MB
~341K SLoC