Release new docs

v2.3.x/site/en/faq/product_faq.md

@@ -130,7 +130,7 @@ Current Milvus release does not support Apple M1 CPU.
 
 #### What data types does Milvus support on the primary key field?
 
-In current release, Milvus support both INT64 and string.
+In current release, Milvus supports both INT64 and string.
 
 #### Is Milvus scalable?
 
@@ -152,7 +152,7 @@ Data in MinIO is designed to remain for a certain period of time for the conveni
 
 Yes. Kafka is supported in Milvus 2.1.0.
 
-#### What's the diference between a search and a query?
+#### What's the difference between a search and a query?
 
 In Milvus, a vector similarity search retrieves vectors based on similarity calculation and vector index acceleration. Unlike a vector similarity search, a vector query retrieves vectors via scalar filtering based on a boolean expression. The boolean expression filters on scalar fields or the primary key field, and it retrieves all results that match the filters. In a query, neither similarity metrics nor vector index is involved.
 

v2.3.x/site/en/integrations/integrate_with_cohere.md

@@ -118,12 +118,12 @@ In this example, the data includes the original question, the original question'
 # Set up a co:here client.
 cohere_client = cohere.Client(COHERE_API_KEY)
 
-# Extract embedings from questions using Cohere
+# Extract embeddings from questions using Cohere
 def embed(texts):
     res = cohere_client.embed(texts, model='multilingual-22-12')
     return res.embeddings
 
-# Insert each question, answer, and qustion embedding
+# Insert each question, answer, and question embedding
 total = pandas.DataFrame()
 for batch in tqdm(np.array_split(simplified_records, (COUNT/BATCH_SIZE) + 1)):
     questions = batch['question'].tolist()
@@ -162,7 +162,7 @@ def search(text, top_k = 5):
 
     results = collection.search(
         data = embed([text]),  # Embeded the question
-        anns_field="original_question_embedding",  # Search across the original original question embeddings
+        anns_field="original_question_embedding",  # Search across the original question embeddings
         param=search_params,
         limit = top_k,  # Limit to top_k results per search
         output_fields=['original_question', 'answer']  # Include the original question and answer in the result
@@ -207,4 +207,4 @@ Answer, Distance, Original Question
 ['part of the family', 7904.853515625, 'Most people today describe their dogs as what?']
 ['77.5 million', 8752.98828125, 'How many people in the United States are said to own dog?']
 ['Iditarod Trail Sled Dog Race', 9251.58984375, 'Which dog-sled race in Alaska is the most famous?']
-```
+```

v2.3.x/site/en/integrations/integrate_with_hugging-face.md

@@ -31,7 +31,7 @@ Here we can find the parameters used in the following snippets. Some of them nee
 ```python
 DATASET = 'squad'  # Huggingface Dataset to use
 MODEL = 'bert-base-uncased'  # Transformer to use for embeddings
-TOKENIZATION_BATCH_SIZE = 1000  # Batch size for tokenizing operaiton
+TOKENIZATION_BATCH_SIZE = 1000  # Batch size for tokenizing operation
 INFERENCE_BATCH_SIZE = 64  # batch size for transformer
 INSERT_RATIO = .001  # How many titles to embed and insert
 COLLECTION_NAME = 'huggingface_db'  # Collection name

v2.3.x/site/en/integrations/integrate_with_langchain.md

@@ -66,7 +66,7 @@ Created a chunk of size 1278, which is longer than the specified 1024
 Once the documents are ready, we need to convert them into vector embeddings and save them into the vector store.
 
 ```python
-# Set up an embedding model to covert document chunks into vector embeddings.
+# Set up an embedding model to convert document chunks into vector embeddings.
 embeddings = OpenAIEmbeddings()
 
 # Set up a vector store used to save the vector embeddings. Here we use Milvus as the vector store.

v2.3.x/site/en/integrations/integrate_with_sentencetransformers.md

@@ -132,7 +132,7 @@ def csv_load(file):
             yield (row[1], row[7])
 
 
-# Extract embeding from text using OpenAI
+# Extract embedding from text using OpenAI
 def embed_insert(data):
     embeds = transformer.encode(data[1]) 
     ins = [