txtai-external-hf.py

import numpy as np
import requests

def transform(inputs):
  response = requests.post("https://api-inference.huggingface.co/pipeline/feature-extraction/sentence-transformers/nli-mpnet-base-v2",
                           json={"inputs": inputs})

  return np.array(response.json(), dtype=np.float32)

# Index data using vectors from Inference API
embeddings = Embeddings({"method": "external", "transform": transform, "content": True})
embeddings.index([(uid, text, None) for uid, text in enumerate(data)])

print("%-20s %s" % ("Query", "Best Match"))
print("-" * 50)

# Run an embeddings search for each query
for query in ("feel good story", "climate change", "public health story", "war", "wildlife", "asia", "lucky", "dishonest junk"):
    # Extract text field from result
    text = embeddings.search(f"select id, text, score from txtai where similar('{query}')", 1)[0]["text"]

    # Print text
    print("%-20s %s" % (query, text))