Release new docs to master

Author: Milvus-doc-bot

v2.6.x/assets/embedding-function-overview.png

@@ -194,6 +194,14 @@ To use an embedding function, create a collection with a specific schema. This s
 
 The following example defines a schema with one scalar field `"document"` for storing textual data and one vector field `"dense"` for storing embeddings to be generated by the Function module. Remember to set the vector dimension (`dim`) to match the output of your chosen embedding model.
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 from pymilvus import MilvusClient, DataType, Function, FunctionType
 
@@ -212,18 +220,42 @@ schema.add_field("id", DataType.INT64, is_primary=True, auto_id=False)
 schema.add_field("document", DataType.VARCHAR, max_length=9000)
 
 # Add vector field "dense" for storing embeddings.
-# IMPORTANT: Set `dim` to match the exact output dimension of the embedding model.
+# IMPORTANT: Set dim to match the exact output dimension of the embedding model.
 # For instance, OpenAI's text-embedding-3-small model outputs 1536-dimensional vectors.
 # For dense vector, data type can be FLOAT_VECTOR or INT8_VECTOR
 schema.add_field("dense", DataType.FLOAT_VECTOR, dim=1536)
 ```
 
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
+```
+
 ### Step 2: Add embedding function to schema
 
 The Function module in Milvus automatically converts raw data stored in a scalar field into embeddings and stores them into the explicitly defined vector field.
 
 The example below adds a Function module (`openai_embedding`) that converts the scalar field `"document"` into embeddings, storing the resulting vectors in the `"dense"` vector field defined earlier.
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 # Define embedding function (example: OpenAI provider)
 text_embedding_function = Function(
@@ -245,6 +277,22 @@ text_embedding_function = Function(
 schema.add_function(text_embedding_function)
 ```
 
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
+```
+
 <table>
    <tr>
      <th><p>Parameter</p></th>
@@ -258,7 +306,7 @@ schema.add_function(text_embedding_function)
    </tr>
    <tr>
      <td><p><code>function_type</code></p></td>
-     <td><p>Type of function used. For text embedding, set the value to <code>FunctionType.TEXTEMBEDDING</code>.<br><strong>Note:</strong> Milvus accepts <code>FunctionType.BM25</code> (for sparse-embedding transformation) and <code>FunctionType.RERANK</code> (for reranking) for this parameter. Refer to <a href="full-text-search.md">Full Text Search</a> and <a href="decay-ranker-overview.md">Decay Ranker Overview</a> for details.</p></td>
+     <td><p>Type of function used. For text embedding, set the value to <code>FunctionType.TEXTEMBEDDING</code>.</p><p><strong>Note</strong>: Milvus accepts <code>FunctionType.BM25</code> (for sparse-embedding transformation) and <code>FunctionType.RERANK</code> (for reranking) for this parameter. Refer to <a href="full-text-search.md">Full Text Search</a> and <a href="decay-ranker-overview.md">Decay Ranker Overview</a> for details.</p></td>
      <td><p><code>FunctionType.TEXTEMBEDDING</code></p></td>
    </tr>
    <tr>
@@ -288,18 +336,12 @@ schema.add_function(text_embedding_function)
    </tr>
    <tr>
      <td><p><code>credential</code></p></td>
-     <td><p>The label of a credential defined in the top-level <code>credential:</code> section of <code>milvus.yaml</code>. </p>
-<ul>
-<li><p>When provided, Milvus retrieves the matching key pair or API token and signs the request on the server side.</p></li>
-<li><p>When omitted (<code>None</code>), Milvus falls back to the credential explicitly configured for the target model provider in <code>milvus.yaml</code>.</p></li>
-<li><p>If the label is unknown or the referenced key is missing, the call fails.</p></li>
-</ul></td>
+     <td><p>The label of a credential defined in the top-level <code>credential:</code> section of <code>milvus.yaml</code>. </p><ul><li><p>When provided, Milvus retrieves the matching key pair or API token and signs the request on the server side.</p></li><li><p>When omitted (<code>None</code>), Milvus falls back to the credential explicitly configured for the target model provider in <code>milvus.yaml</code>.</p></li><li><p>If the label is unknown or the referenced key is missing, the call fails.</p></li></ul></td>
      <td><p><code>"apikey1"</code></p></td>
    </tr>
    <tr>
      <td><p><code>dim</code></p></td>
-     <td><p>The number of dimensions for the output embeddings. For OpenAI's third-generation models, you can shorten the full vector to reduce cost and latency without a significant loss of semantic information. For more information, refer to <a href="https://openai.com/blog/new-embedding-models-and-api-updates">OpenAI announcement blog post</a>.<br>
- <strong>Note:</strong> If you shorten the vector dimension, ensure the <code>dim</code> value specified in the schema's <code>add_field</code> method for the vector field matches the final output dimension of your embedding function.</p></td>
+     <td><p>The number of dimensions for the output embeddings. For OpenAI's third-generation models, you can shorten the full vector to reduce cost and latency without a significant loss of semantic information. For more information, refer to <a href="https://openai.com/blog/new-embedding-models-and-api-updates">OpenAI announcement blog post</a>.</p><p><strong>Note:</strong> If you shorten the vector dimension, ensure the <code>dim</code> value specified in the schema's <code>add_field</code> method for the vector field matches the final output dimension of your embedding function.</p></td>
      <td><p><code>"1536"</code></p></td>
    </tr>
    <tr>
@@ -319,6 +361,14 @@ For collections with multiple scalar fields requiring text-to-vector conversion,
 
 After defining the schema with necessary fields and the built-in function, set up the index for your collection. To simplify this process, use `AUTOINDEX` as the `index_type`, an option that allows Milvus to choose and configure the most suitable index type based on the structure of your data.
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 # Prepare index parameters
 index_params = client.prepare_index_params()
@@ -331,10 +381,34 @@ index_params.add_index(
 )
 ```
 
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
+```
+
 ### Step 4: Create collection
 
 Now create the collection using the schema and index parameters defined.
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 # Create collection named "demo"
 client.create_collection(
@@ -344,10 +418,34 @@ client.create_collection(
 )
 ```
 
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
+```
+
 ### Step 5: Insert data
 
 After setting up your collection and index, you're ready to insert your raw data. In this process, you need only to provide the raw text. The Function module we defined earlier automatically generates the corresponding sparse vector for each text entry.
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 # Insert sample documents
 client.insert('demo', [
@@ -357,10 +455,34 @@ client.insert('demo', [
 ])
 ```
 
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
+```
+
 ### Step 6: Perform vector search
 
 After data insertion, perform a semantic search using raw query text. Milvus automatically converts your query into an embedding vector, retrieves relevant documents based on similarity, and returns the top-matching results.
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 # Perform semantic search
 results = client.search(
@@ -377,6 +499,22 @@ print(results)
 # data: ["[{'id': 1, 'distance': 0.8821347951889038, 'entity': {'document': 'Milvus simplifies semantic search through embeddings.'}}]"]
 ```
 
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
+```
+
 For more information about search and query operations, refer to [Basic Vector Search](single-vector-search.md) and [Query](get-and-scalar-query.md).
 
 ## FAQ
@@ -403,10 +541,18 @@ You can check by:
 
 ### When I perform a similarity search, can I use a query vector rather than raw text?
 
-Yes, you can use pre-computed query vectors instead of raw text for similarity search. While the Function module automatically converts raw text queries to embeddings, you can also directly provide vector data to the data parameter in your search operation. Note: The dimension size of your provided query vector must be consistent with the dimension size of the vector embeddings generated by your Function module.
+Yes, you can use pre-computed query vectors instead of raw text for similarity search. While the Function module automatically converts raw text queries to embeddings, you can also directly provide vector data to the `data` parameter in your search operation. **Note**: The dimension size of your provided query vector must be consistent with the dimension size of the vector embeddings generated by your Function module.
 
 **Example**:
 
+<div class="multipleCode">
+    <a href="#python">Python</a>
+    <a href="#java">Java</a>
+    <a href="#javascript">NodeJS</a>
+    <a href="#go">Go</a>
+    <a href="#bash">cURL</a>
+</div>
+
 ```python
 # Using raw text (Function module converts automatically)
 results = client.search(
@@ -424,4 +570,20 @@ results = client.search(
     anns_field='dense',
     limit=1
 )
+```
+
+```java
+// java
+```
+
+```javascript
+// nodejs
+```
+
+```go
+// go
+```
+
+```bash
+# restful
 ```