use cosine_similarity

README.md

@@ -2614,7 +2614,7 @@ language:
 **🤝 Follow us on:**
 
 - GitHub: https://github.com/SeanLee97/AnglE.
-- Arxiv: https://arxiv.org/abs/2309.12871
+- Arxiv: https://arxiv.org/abs/2309.12871 (ACL24)
 - 📘 Document: https://angle.readthedocs.io/en/latest/index.html
 
 Welcome to using AnglE to train and infer powerful sentence embeddings.
@@ -2645,18 +2645,18 @@ There is no need to specify any prompts.
 
 ```python
 from angle_emb import AnglE
-from scipy import spatial
+from angle_emb.utils import cosine_similarity
 
 angle = AnglE.from_pretrained('WhereIsAI/UAE-Large-V1', pooling_strategy='cls').cuda()
 doc_vecs = angle.encode([
     'The weather is great!',
     'The weather is very good!',
     'i am going to bed'
-])
+], normalize_embedding=True)
 
 for i, dv1 in enumerate(doc_vecs):
     for dv2 in doc_vecs[i+1:]:
-        print(1 - spatial.distance.cosine(dv1, dv2))
+        print(cosine_similarity(dv1, dv2))
 ```
 
 2) Retrieval Tasks
@@ -2665,7 +2665,7 @@ For retrieval purposes, please use the prompt `Prompts.C` for query (not for doc
 
 ```python
 from angle_emb import AnglE, Prompts
-from scipy import spatial
+from angle_emb.utils import cosine_similarity
 
 angle = AnglE.from_pretrained('WhereIsAI/UAE-Large-V1', pooling_strategy='cls').cuda()
 qv = angle.encode(Prompts.C.format(text='what is the weather?'))
@@ -2676,7 +2676,7 @@ doc_vecs = angle.encode([
 ])
 
 for dv in doc_vecs:
-    print(1 - spatial.distance.cosine(qv[0], dv))
+    print(cosine_similarity(qv[0], dv))
 ```
 
 ## 2. sentence transformer