Spaces:
Sleeping
Sleeping
File size: 2,032 Bytes
dc4de02 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
from dotenv import load_dotenv
from openai import AsyncOpenAI, OpenAI
import openai
from typing import List
import os
import asyncio
class EmbeddingModel:
def __init__(self, embeddings_model_name: str = "text-embedding-3-small"):
load_dotenv()
self.openai_api_key = os.getenv("OPENAI_API_KEY")
self.async_client = AsyncOpenAI()
self.client = OpenAI()
if self.openai_api_key is None:
raise ValueError(
"OPENAI_API_KEY environment variable is not set. Please set it to your OpenAI API key."
)
openai.api_key = self.openai_api_key
self.embeddings_model_name = embeddings_model_name
async def async_get_embeddings(self, list_of_text: List[str]) -> List[List[float]]:
embedding_response = await self.async_client.embeddings.create(
input=list_of_text, model=self.embeddings_model_name
)
return [embeddings.embedding for embeddings in embedding_response.data]
async def async_get_embedding(self, text: str) -> List[float]:
embedding = await self.async_client.embeddings.create(
input=text, model=self.embeddings_model_name
)
return embedding.data[0].embedding
def get_embeddings(self, list_of_text: List[str]) -> List[List[float]]:
embedding_response = self.client.embeddings.create(
input=list_of_text, model=self.embeddings_model_name
)
return [embeddings.embedding for embeddings in embedding_response.data]
def get_embedding(self, text: str) -> List[float]:
embedding = self.client.embeddings.create(
input=text, model=self.embeddings_model_name
)
return embedding.data[0].embedding
if __name__ == "__main__":
embedding_model = EmbeddingModel()
print(asyncio.run(embedding_model.async_get_embedding("Hello, world!")))
print(
asyncio.run(
embedding_model.async_get_embeddings(["Hello, world!", "Goodbye, world!"])
)
)
|