Update python examples to compute cosine similarity

README.md

@@ -2615,7 +2615,7 @@ Anyone can easily train and control AI.
 
 ## How to get embeddings
 
-Currently, we open the beta version of embedding API v1 and v2. 
+Currently, we open the beta version of embedding APIs. 
 To get embeddings, you should call API endpoint to send your text. 
 You can send either a single sentence or multiple sentences. 
 The embeddings that correspond to the inputs will be returned.
@@ -2681,14 +2681,15 @@ inputs1 = ["first query", "second query"]
 inputs2 = ["third query", "fourth query"]
 embedding1 = get_embedding(inputs1, url=url)
 embedding2 = get_embedding(inputs2, url=url)
-similarity = embedding1 @ embedding2.T
-print(similarity)
+cos_similarity = (embedding1 / np.linalg.norm(embedding1)) @ (embedding2 / np.linalg.norm(embedding1)).T
+print(cos_similarity)
 ```
 
 Using pre-defined [SionicEmbeddingModel](https://huggingface.co/sionic-ai/sionic-ai-v1/blob/main/model_api.py) to obtain embeddings.
 
 ```python
 from model_api import SionicEmbeddingModel
+import numpy as np
 
 inputs1 = ["first query", "second query"]
 inputs2 = ["third query", "fourth query"]
@@ -2696,15 +2697,16 @@ model = SionicEmbeddingModel(url="https://api.sionic.ai/v1/embedding",
                              dimension=2048)
 embedding1 = model.encode(inputs1)
 embedding2 = model.encode(inputs2)
-similarity = embedding1 @ embedding2.T
-print(similarity)
+cos_similarity = (embedding1 / np.linalg.norm(embedding1)) @ (embedding2 / np.linalg.norm(embedding1)).T
+print(cos_similarity)
 ```
 We apply the instruction to encode short queries for retrieval tasks.
-By using `encode_queries()`, you can use instruction to encode queries which is prefixed to each query.
-The instruction to use for both v1 and v2 models is `"query: "`. 
+By using `encode_queries()`, you can use the instruction to encode queries which is prefixed to each query as the following example.
+The recommended instruction for both v1 and v2 models is `"query: "`.
 
 ```python
 from model_api import SionicEmbeddingModel
+import numpy as np
 
 query = ["first query", "second query"]
 passage = ["This is a passage related to the first query", "This is a passage related to the second query"]
@@ -2713,19 +2715,19 @@ model = SionicEmbeddingModel(url="https://api.sionic.ai/v1/embedding",
                              dimension=2048)
 query_embedding = model.encode_queries(query)
 passage_embedding = model.encode_corpus(passage)
-similarity = query_embedding @ passage_embedding.T
-print(similarity)
+cos_similarity = (query_embedding / np.linalg.norm(query_embedding)) @ (passage_embedding / np.linalg.norm(passage_embedding)).T
+print(cos_similarity)
 ```
 
 ## Massive Text Embedding Benchmark (MTEB) Evaluation
 
 Both versions of Sionic AI's embedding show the state-of-the-art performances on the MTEB!
-You can find a code to evaluate MTEB datasets using v1 embedding [here](https://huggingface.co/sionic-ai/sionic-ai-v1/blob/main/mteb_evaluate.py).
+You can find a code to evaluate MTEB datasets [here](https://huggingface.co/sionic-ai/sionic-ai-v1/blob/main/mteb_evaluate.py).
 
 |                               Model Name                                | Dimension | Sequence Length | Average (56) | 
 |:-----------------------------------------------------------------------:|:---------:|:---:|:------------:|
-| [sionic-ai/sionic-ai-v2](https://huggingface.co/sionic-ai/sionic-ai-v2) |   3072    | 512 |  **65.23**   |  
-| [sionic-ai/sionic-ai-v1](https://huggingface.co/sionic-ai/sionic-ai-v1) |   2048    | 512 |    64.92     |  
+| [sionic-ai/sionic-ai-v2](https://huggingface.co/sionic-ai/sionic-ai-v2) |   3072    | 512 |  65.23   |  
+| [sionic-ai/sionic-ai-v1](https://huggingface.co/sionic-ai/sionic-ai-v1) |   2048    | 512 |    **64.92**     |  
 | [bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) |   1024    |       512       |    64.23     |  
 | [gte-large-en](https://huggingface.co/barisaydin/gte-large) |   1024    |       512       |    63.13     |
 | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings/types-of-embedding-models) |   1536    |      8191       |    60.99     |