Huggingface Inference Guide

export HF_API_TOKEN=$HF_API_TOKEN

curl -X POST "https://api-inference.huggingface.co/models/bert-base-uncased" \
  -H "Authorization: Bearer $HF_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"inputs": "The goal of life is [MASK]."}'

POST https://api-inference.huggingface.co/models/{model_id}

curl -s -X POST \
  "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english" \
  -H "Authorization: Bearer $HF_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"inputs": "This research methodology provides robust and reproducible results."}' \
  | python3 -m json.tool

curl -s -X POST \
  "https://api-inference.huggingface.co/models/dslim/bert-base-NER" \
  -H "Authorization: Bearer $HF_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"inputs": "Dr. Marie Curie conducted research at the University of Paris on radioactivity."}' \
  | python3 -m json.tool

curl -s -X POST \
  "https://api-inference.huggingface.co/models/facebook/bart-large-cnn" \
  -H "Authorization: Bearer $HF_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": "The study of quantum computing has seen tremendous advances in the past decade. Researchers have demonstrated quantum supremacy with processors containing over 100 qubits. Error correction remains a significant challenge, but recent breakthroughs in topological qubits and surface codes suggest viable paths forward. Applications in drug discovery, materials science, and cryptography are expected to be among the first practical use cases.",
    "parameters": {"max_length": 80, "min_length": 30}
  }' | python3 -m json.tool

curl -s -X POST \
  "https://api-inference.huggingface.co/models/facebook/bart-large-mnli" \
  -H "Authorization: Bearer $HF_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": "New CRISPR technique enables precise gene editing in human stem cells",
    "parameters": {"candidate_labels": ["biology", "computer science", "physics", "economics"]}
  }' | python3 -m json.tool

import requests
import os
import time

API_URL = "https://api-inference.huggingface.co/models/distilbert-base-uncased-finetuned-sst-2-english"
HEADERS = {"Authorization": f"Bearer {os.environ['HF_API_TOKEN']}"}

def classify_sentiment(texts):
    """Classify sentiment for a batch of texts."""
    response = requests.post(API_URL, headers=HEADERS, json={"inputs": texts})
    if response.status_code == 503:
        # Model is loading, wait and retry
        wait_time = response.json().get("estimated_time", 20)
        print(f"Model loading, waiting {wait_time:.0f}s...")
        time.sleep(wait_time)
        response = requests.post(API_URL, headers=HEADERS, json={"inputs": texts})
    response.raise_for_status()
    return response.json()

abstracts = [
    "Our results demonstrate a significant improvement over baseline methods.",
    "The proposed approach failed to achieve meaningful gains on the benchmark.",
    "We present preliminary findings that warrant further investigation.",
]

results = classify_sentiment(abstracts)
for abstract, result in zip(abstracts, results):
    top = max(result, key=lambda x: x["score"])
    print(f"Sentiment: {top['label']} ({top['score']:.3f})")
    print(f"  Text: {abstract[:80]}...")
    print()

import requests
import os

ZSC_URL = "https://api-inference.huggingface.co/models/facebook/bart-large-mnli"
HEADERS = {"Authorization": f"Bearer {os.environ['HF_API_TOKEN']}"}

def classify_paper(abstract, categories):
    """Classify a paper abstract into research categories."""
    payload = {
        "inputs": abstract,
        "parameters": {"candidate_labels": categories}
    }
    resp = requests.post(ZSC_URL, headers=HEADERS, json=payload)
    resp.raise_for_status()
    return resp.json()

categories = [
    "machine learning",
    "computational biology",
    "natural language processing",
    "computer vision",
    "reinforcement learning",
    "quantum computing"
]

abstract = "We propose a novel transformer architecture for protein structure prediction that achieves state-of-the-art results on CASP benchmarks."
result = classify_paper(abstract, categories)

print("Topic classification:")
for label, score in zip(result["labels"], result["scores"]):
    bar = "#" * int(score * 40)
    print(f"  {label:<30} {score:.3f} {bar}")