openai_embedding_client.py

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    # defaults to os.environ.get("OPENAI_API_KEY")
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

responses = client.embeddings.create(input=[
    "Hello my name is",
    "The best thing about vLLM is that it supports many different models"
],
                                     model=model)

for data in responses.data:
    print(data.embedding)  # list of float of len 4096