txtai-onnx-export.py

from txtai import Embeddings
from txtai.pipeline import HFOnnx

# Export as quantized onnx model
# Model Size = 1.1 MB!
path = HFOnnx()( 
  "neuml/biomedbert-hash-nano-embeddings",
  "pooling", "model.onnx", True
)

# Load onnx model for similarity
# No custom code anymore
embeddings = Embeddings(
  path=path,
  tokenizer="neuml/biomedbert-hash-nano-embeddings"
)

embeddings.similarity("cancer", ["tumor", "diabetes"])
# [(0, 0.8546434640884399), (1, -0.027852479368448257)]