txtai-external-spacy.py

# pip install spacy --upgrade
# python -m spacy download en_core_web_md

import spacy

# Load spacy
nlp = spacy.load("en_core_web_md")

def transform(inputs):
    return [result.vector for result in nlp.pipe(inputs)]

# Index data with spacy pipeline
embeddings = Embeddings({"method": "external", "transform": transform, "content": True})
embeddings.index([(uid, text, None) for uid, text in enumerate(data)])

# Run search
print(embeddings.search("select id, text, score from txtai where similar('nature')", 1))