get_text_embeddings.py

# FIXME: This use-case is not yet supported.
from typing import List, Optional

import vertexai
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor
from vertexai.language_models import TextEmbeddingInput, TextEmbeddingModel

from openinference.instrumentation.vertexai import VertexAIInstrumentor

endpoint = "http://127.0.0.1:4317"
tracer_provider = TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))

VertexAIInstrumentor().instrument(tracer_provider=tracer_provider)

vertexai.init(location="us-central1")


def embed_text(
    texts: List[str] = ["banana muffins? ", "banana bread? banana muffins?"],
    task: str = "RETRIEVAL_DOCUMENT",
    model_name: str = "text-embedding-004",
    dimensionality: Optional[int] = 256,
) -> List[List[float]]:
    """Embeds texts with a pre-trained, foundational model."""
    model = TextEmbeddingModel.from_pretrained(model_name)
    inputs = [TextEmbeddingInput(text, task) for text in texts]
    kwargs = dict(output_dimensionality=dimensionality) if dimensionality else {}
    embeddings = model.get_embeddings(inputs, **kwargs)
    return [embedding.values for embedding in embeddings]


if __name__ == "__main__":
    print(embed_text())