Add README

Signed-off-by: shiyu22 <shiyu.chen@zilliz.com>

README.md

@@ -10,7 +10,7 @@
 
 ## Code Example
 
-- **Create Milvus Collection**
+### **Create Milvus collection**
 
 Before running the pipeline, please create Milvus collection first.
 
@@ -41,7 +41,7 @@ index_params = {
 collection.create_index(field_name="embedding", index_params=index_params)
 ```
 
-- **Create image embedding pipeline and set the configuration**
+### **Create pipeline and set the configuration**
 
 > More parameters refer to the Configuration.
 
@@ -69,7 +69,7 @@ Then you can run `collection.num_entities` to check the number of the data in Mi
 
 ### **EnhancedQAInsertConfig**
 
-**Configuration for [Text Loader](https://towhee.io/towhee/text-loader):**
+#### **Configuration for [Text Loader](https://towhee.io/towhee/text-loader):**
 
 ***chunk_size: int***
 The size of each chunk, defaults to 300.
@@ -77,7 +77,7 @@ The size of each chunk, defaults to 300.
 ***source_type: str***
 The type of the soure, defaults to `'file'`, you can also set to `'url'` for you url of your documentation. 
 
-**Configuration for Sentence Embedding:**
+#### **Configuration for Sentence Embedding:**
 
 ***model: str***
 The model name in the sentence embedding pipeline, defaults to `'all-MiniLM-L6-v2'`.
@@ -97,7 +97,7 @@ Whether to normalize the embedding vectors, defaults to `True`.
 The number of devices, defaults to `-1`, which means using the CPU. 
 If the setting is not `-1`, the specified GPU device will be used.
 
-**Configuration for [Milvus](https://towhee.io/ann-insert/milvus-client):**
+#### **Configuration for [Milvus](https://towhee.io/ann-insert/milvus-client):**
 
 ***host: str***
 Host of Milvus vector database, default is `'127.0.0.1'`.