Fixing variable names and cosine_similarity is imported in the example code.

README.md

@@ -32,17 +32,20 @@ Here is how to use this model to get the features of a given text using [Sentenc
 
 ```python
 from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
 
 model_Q = SentenceTransformer('flax-sentence-embeddings/multi-QA_v1-mpnet-asymmetric-Q')
 model_A = SentenceTransformer('flax-sentence-embeddings/multi-QA_v1-mpnet-asymmetric-A')
 
 question = "Replace me by any question you'd like."
-question_embbedding = model_Q.encode(text)
+question_embedding = model_Q.encode(question)
 
 answer = "Replace me by any answer you'd like."
-answer_embbedding = model_A.encode(text)
+answer_embedding = model_A.encode(answer)
 
-answer_likeliness = cosine_similarity(question_embedding, answer_embedding)
+answer_likeliness = cosine_similarity([question_embedding], [answer_embedding])
+
+print(answer_likeliness)
 ```
 
 # Training procedure