Update README.md

README.md

@@ -86,6 +86,52 @@ Full set of evaluation numbers for our model
 #### With Sentence Transformers:
 
 ```python
+from sentence_transformers import SentenceTransformer
+import scipy.spatial
+
+
+model = SentenceTransformer('prithivida/miniMiracle_zh_v1')
+
+corpus = [
+    '一个男人正在吃东西',
+    '人们正在吃一块面包',
+    '女孩抱着婴儿',
+    '一个男人正在骑马',
+    '一个女人正在弹吉他',
+    '两个人推着马车穿过树林',
+    '一个人骑着一匹白马在一个封闭的田野里',
+    '一只猴子在打鼓',
+    '一只猎豹正在猎物后面奔跑',
+    '他们享受了一顿美味的盛宴'
+]
+
+queries = [
+    '一个人在吃意大利面',
+    '一个穿着大猩猩服装的人在打鼓'
+]
+
+
+corpus_embeddings = model.encode(corpus)
+query_embeddings = model.encode(queries)
+
+# Find the closest 3 sentences of the corpus for each query sentence based on cosine similarity
+closest_n = 3
+for query, query_embedding in zip(queries, query_embeddings):
+    distances = scipy.spatial.distance.cdist([query_embedding], corpus_embeddings, "cosine")[0]
+
+    results = zip(range(len(distances)), distances)
+    results = sorted(results, key=lambda x: x[1])
+
+    print("\n======================\n")
+    print("Query:", query)
+    print("\nTop 3 most similar sentences in corpus:\n")
+
+    for idx, distance in results[0:closest_n]:
+        print(corpus[idx].strip(), "(Score: %.4f)" % (1-distance))
+
+# Optional: How to quantize the embeddings
+# binary_embeddings = quantize_embeddings(embeddings, precision="ubinary")
+
 
 ```