Merge branch 'main' into chore/update_approx_size

Cargo.toml

@@ -108,7 +108,6 @@ members = [
 sled = { git = "https://github.com/datafuse-extras/sled", tag = "v0.34.7-datafuse.1", default-features = false }
 opendal = { version = "0.39", features = [
     "layers-minitrace",
-    "layers-metrics",
     "services-ipfs",
     "services-moka",
     "services-redis",

docs/doc/13-sql-reference/99-ansi-sql.md

@@ -95,7 +95,7 @@ Databend aims to conform to the SQL standard, with particular support for ISO/IE
 | E121-17    	| WITH HOLD cursors                                                                                                        	| <span class="text-red">No</span>         	|                                                                                                              	|
 | **E131**   	| **Null value support (nulls in lieu of values)**                                                                         	| <span class="text-blue">Yes</span>        	|                                                                                                              	|
 | **E141**   	| **Basic integrity constraints**                                                                                          	| <span class="text-red">No</span>         	|                                                                                                              	|
-| E141-01    	| NOT NULL constraints                                                                                                     	| <span class="text-blue">Yes</span>        	| Default in Databend: All columns are non-nullable (NOT NULL).                                                	|
+| E141-01    	| NOT NULL constraints                                                                                                     	| <span class="text-blue">Yes</span>        	| Default in Databend: All columns are nullable.                                                	|
 | E141-02    	| UNIQUE constraint of NOT NULL columns                                                                                    	| <span class="text-red">No</span>         	|                                                                                                              	|
 | E141-03    	| PRIMARY KEY constraints                                                                                                  	| <span class="text-red">No</span>         	|                                                                                                              	|
 | E141-04    	| Basic FOREIGN KEY constraint with the NO ACTION default for both referential delete action and referential update action 	| <span class="text-red">No</span>         	|                                                                                                              	|

docs/doc/14-sql-commands/00-ddl/50-udf/_category_.json

@@ -1,7 +1,3 @@
 {
-  "label": "User-Defined Function",
-  "link": {
-    "type": "generated-index",
-    "slug": "/sql-commands/ddl/udf"
-  }
+  "label": "User-Defined Function"
 }

docs/doc/14-sql-commands/00-ddl/50-udf/ddl-alter-function.md

@@ -3,22 +3,33 @@ title: ALTER FUNCTION
 description:
   Modifies the properties for an existing user-defined function.
 ---
+import FunctionDescription from '@site/src/components/FunctionDescription';
+
+<FunctionDescription description="Introduced or updated: v1.2.116"/>
+
+Alters a user-defined function.
 
 ## Syntax
 
 ```sql
-CREATE FUNCTION <name> AS ([ argname ]) -> '<function_definition>'
+-- Alter UDF created with lambda expression
+ALTER FUNCTION [IF NOT EXISTS] <function_name> 
+    AS (<input_param_names>) -> <lambda_expression> 
+    [DESC='<description>']
+
+-- Alter UDF created with UDF server
+ALTER FUNCTION [IF NOT EXISTS] <function_name> 
+    AS (<input_param_types>) RETURNS <return_type> LANGUAGE <language_name> 
+    HANDLER = '<handler_name>' ADDRESS = '<udf_server_address>' 
+    [DESC='<description>']
 ```
 
 ## Examples
 
 ```sql
+CREATE FUNCTION a_plus_3 AS (a) -> a+3+3;
 ALTER FUNCTION a_plus_3 AS (a) -> a+3;
 
-SELECT a_plus_3(2);
-+---------+
-| (2 + 3) |
-+---------+
-|       5 |
-+---------+
-```
+CREATE FUNCTION gcd (INT, INT) RETURNS INT LANGUAGE python HANDLER = 'gcd' ADDRESS = 'http://0.0.0.0:8815';
+ALTER FUNCTION gcd (INT, INT) RETURNS INT LANGUAGE python HANDLER = 'gcd_new' ADDRESS = 'http://0.0.0.0:8815';
+```

docs/doc/14-sql-commands/00-ddl/50-udf/ddl-create-function.md

@@ -3,20 +3,44 @@ title: CREATE FUNCTION
 description:
   Create a new user-defined scalar function.
 ---
+import FunctionDescription from '@site/src/components/FunctionDescription';
 
+<FunctionDescription description="Introduced or updated: v1.2.116"/>
 
-## CREATE FUNCTION
-
-Creates a new UDF (user-defined function), the UDF can contain an SQL expression.
+Creates a user-defined function.
 
 ## Syntax
 
 ```sql
-CREATE FUNCTION [ IF NOT EXISTS ] <name> AS ([ argname ]) -> '<function_definition>'
+-- Create with lambda expression
+CREATE FUNCTION [IF NOT EXISTS] <function_name> 
+    AS (<input_param_names>) -> <lambda_expression> 
+    [DESC='<description>']
+
+
+-- Create with UDF server
+CREATE FUNCTION [IF NOT EXISTS] <function_name> 
+    AS (<input_param_types>) RETURNS <return_type> LANGUAGE <language_name> 
+    HANDLER = '<handler_name>' ADDRESS = '<udf_server_address>' 
+    [DESC='<description>']
 ```
 
+| Parameter             | Description                                                                                       |
+|-----------------------|---------------------------------------------------------------------------------------------------|
+| `<function_name>`     | The name of the function.                                                                        |
+| `<lambda_expression>` | The lambda expression or code snippet defining the function's behavior.                          |
+| `DESC='<description>'`  | Description of the UDF.|
+| `<<input_param_names>`| A list of input parameter names. Separated by comma.|
+| `<<input_param_types>`| A list of input parameter types. Separated by comma.|
+| `<return_type>`       | The return type of the function.                                                                  |
+| `LANGUAGE`            | Specifies the language used to write the function. Available values: `python`.                    |
+| `HANDLER = '<handler_name>'` | Specifies the name of the function's handler.                                               |
+| `ADDRESS = '<udf_server_address>'` | Specifies the address of the UDF server.                                             |
+
 ## Examples
 
+### Creating UDF with Lambda Expression
+
 ```sql
 CREATE FUNCTION a_plus_3 AS (a) -> a+3;
 
@@ -53,3 +77,89 @@ DROP FUNCTION get_v2;
 
 DROP TABLE json_table;
 ```
+
+### Creating UDF with UDF Server (Python)
+
+This example demonstrates how to enable and configure a UDF server in Python:
+
+1. Enable UDF server support by adding the following parameters to the [query] section in the [databend-query.toml](https://github.com/datafuselabs/databend/blob/main/scripts/distribution/configs/databend-query.toml) configuration file.
+
+```toml title='databend-query.toml'
+[query]
+...
+enable_udf_server = true
+# List the allowed UDF server addresses, separating multiple addresses with commas.
+# For example, ['http://0.0.0.0:8815', 'http://example.com']
+udf_server_allow_list = ['http://0.0.0.0:8815']
+...
+```
+
+2. Define your function. This code defines and runs a UDF server in Python, which exposes a custom function *gcd* for calculating the greatest common divisor of two integers and allows remote execution of this function:
+
+:::note
+The SDK package is not yet available. Prior to its release, please download the 'udf.py' file from https://github.com/datafuselabs/databend/blob/main/tests/udf-server/udf.py and ensure it is saved in the same directory as this Python script. This step is essential for the code to function correctly.
+:::
+
+```python title='udf_server.py'
+from udf import *
+
+@udf(
+    input_types=["INT", "INT"],
+    result_type="INT",
+    skip_null=True,
+)
+def gcd(x: int, y: int) -> int:
+    while y != 0:
+        (x, y) = (y, x % y)
+    return x
+
+if __name__ == '__main__':
+    # create a UDF server listening at '0.0.0.0:8815'
+    server = UdfServer("0.0.0.0:8815")
+    # add defined functions
+    server.add_function(gcd)
+    # start the UDF server
+    server.serve()
+```
+
+`@udf` is a decorator used for defining UDFs in Databend, supporting the following parameters:
+
+| Parameter    | Description                                                                                         |
+|--------------|-----------------------------------------------------------------------------------------------------|
+| input_types  | A list of strings or Arrow data types that specify the input data types.                          |
+| result_type  | A string or an Arrow data type that specifies the return value type.                                |
+| name         | An optional string specifying the function name. If not provided, the original name will be used. |
+| io_threads   | Number of I/O threads used per data chunk for I/O bound functions.                                    |
+| skip_null    | A boolean value specifying whether to skip NULL values. If set to True, NULL values will not be passed to the function, and the corresponding return value is set to NULL. Default is False. |
+
+This table illustrates the correspondence between Databend data types and their corresponding Python equivalents:
+
+| Databend Type         | Python Type          |
+|-----------------------|-----------------------|
+| BOOLEAN               | bool                  |
+| TINYINT (UNSIGNED)    | int                   |
+| SMALLINT (UNSIGNED)   | int                   |
+| INT (UNSIGNED)        | int                   |
+| BIGINT (UNSIGNED)     | int                   |
+| FLOAT                 | float                 |
+| DOUBLE                | float                 |
+| DECIMAL               | decimal.Decimal       |
+| DATE                  | datetime.date         |
+| TIMESTAMP             | datetime.datetime     |
+| VARCHAR               | str                   |
+| VARIANT               | any                   |
+| MAP(K,V)              | dict                  |
+| ARRAY(T)              | list[T]               |
+| TUPLE(T...)           | tuple(T...)           |
+
+3. Run the Python file to start the UDF server:
+
+```shell
+python3 udf_server.py
+```
+
+4. Register the function *gcd* with the [CREATE FUNCTION](ddl-create-function.md) in Databend:
+
+```sql
+CREATE FUNCTION gcd (INT, INT) RETURNS INT LANGUAGE python HANDLER = 'gcd' ADDRESS = 'http://0.0.0.0:8815'；
+```

docs/doc/14-sql-commands/00-ddl/50-udf/ddl-drop-function.md

@@ -4,12 +4,12 @@ description:
   Drop an existing user-defined function.
 ---
 
-Drop an existing user-defined function.
+Drops a user-defined function.
 
 ## Syntax
 
 ```sql
-DROP FUNCTION [IF EXISTS] <name>
+DROP FUNCTION [IF EXISTS] <function_name>
 ```
 
 ## Examples
@@ -19,4 +19,4 @@ DROP FUNCTION a_plus_3;
 
 SELECT a_plus_3(2);
 ERROR 1105 (HY000): Code: 2602, Text = Unknown Function a_plus_3 (while in analyze select projection).
-```
+```