From a150d02d7ac48a024723998a19e6fd6d2723eefa Mon Sep 17 00:00:00 2001 From: mxr612 Date: Tue, 14 May 2024 02:43:50 +0800 Subject: [PATCH] embedding.py --- embedding.py | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 embedding.py diff --git a/embedding.py b/embedding.py new file mode 100644 index 0000000..5306bfd --- /dev/null +++ b/embedding.py @@ -0,0 +1,25 @@ +import os +os.environ["OPENAI_API_KEY"]= "sk-PRJ811XeKzEy20Ug3dA98a34Af8b40B5816dE15503D33599" +os.environ["OPENAI_BASE_URL"]= "http://154.9.28.247:3000/v1/" + +from openai import OpenAI +client = OpenAI() + +from sklearn.metrics.pairwise import cosine_similarity + +def embedding(s:str): + if len(s)==0: + return + else: + return client.embeddings.create( + input=s, model="text-embedding-3-large" # nomic-embed-text text-embedding-3-small + ).data[0].embedding + +a=embedding("I tend to draw fine distinctions between similar feelings (e.g., depressed and blue; annoyed and irritated).") +# b=embedding("我喜欢界定两种相似的情绪（如沮丧和忧伤，烦恼和被激怒）。") +# c=embedding("I like to define two similar emotions (e.g., frustration and sadness, annoyance and irritation).") + +print(a,"\n",len(a)) + +# s = cosine_similarity([a, b, c]) +# print(s) \ No newline at end of file