docs: Add comprehensive Switch transpiler documentation

docs/lakebridge/docs/overview.mdx

@@ -45,10 +45,11 @@ For migrating your SQL workloads we provide transpilers that can:
  - Translate SQL code from a variety of source platforms to Databricks SQL.
  - Translate some orchestration and ETL code to Databricks SQL.
 
-Internally, Lakebridge can use two different transpilers:
+Internally, Lakebridge can use three different transpilers:
 
  - *BladeBridge*, a mature transpiler that can handle a wide range of source dialects as well as some ETL/orchestration.
  - *Morpheus*, a next-generation transpiler that currently handles a smaller set of dialects, but includes experimental support for dbt.
+ - *Switch*, an LLM-powered transpiler that uses Large Language Models to convert SQL and other source formats to Databricks notebooks.
 
 The table below summarizes the source platforms that we currently support:
 

docs/lakebridge/docs/transpile/overview.mdx

@@ -133,6 +133,20 @@ Whether you're migrating a single job or thousands, BladeBridge delivers predict
 
 More details about the BladeBridge converter [here](/docs/transpile/pluggable_transpilers/bladebridge_overview)
 
+### Switch
+
+Switch is an LLM-powered Lakebridge transpiler that extends beyond SQL to convert various source formats into Databricks-compatible outputs. Using [Mosaic AI Model Serving](https://docs.databricks.com/aws/en/machine-learning/model-serving/), it understands code intent and semantics to handle complex transformations.
+
+Key characteristics:
+- **LLM-powered extensibility** - Built-in prompts for multiple SQL dialects (T-SQL, Snowflake, Teradata, Oracle, etc.) and generic formats (Python, Scala, Airflow)
+- **Custom prompt support** - Add YAML prompts to handle any source format not covered by built-in options
+- **Flexible outputs** - Python notebooks with Spark SQL (default), SQL notebooks (experimental), or any text-based format
+- **Databricks-native processing** - Executes as scalable Lakeflow Jobs with serverless compute
+- **Model flexibility** - Uses Databricks Foundation Model APIs with configurable endpoint selection
+- **Complex logic handling** - Excels at stored procedures and business logic beyond ANSI SQL/PSM standards
+
+Switch's LLM-based approach enables support for any source format through custom prompts. For built-in prompt details and custom prompt creation, see the [Switch documentation](/docs/transpile/pluggable_transpilers/switch).
+
 ### Supported dialects
 
 | Source Platform              | Converter: BladeBridge | Converter: Morpheus | Output: SQL | Output: SparkSql | Output: PySpark |   Other features available    |

docs/lakebridge/docs/transpile/pluggable_transpilers/index.mdx

@@ -64,10 +64,11 @@ custom: # this section is optional, it is passed to the transpiler at startup
     <key 1>: <value 1> # can be pretty much anything
 ```
 
-Databricks provides 2 transpilers: _Morpheus_, its AST-based transpiler, and _BladeBridge_, a pattern-based transpiler.
+Databricks provides 3 transpilers: _Morpheus_, its AST-based transpiler, _BladeBridge_, a pattern-based transpiler, and _Switch_, an LLM-powered transpiler.
 These transpilers are installed by `Lakebridge` itself as part of running the `install-transpile` command, as follows:
  - the latest _Morpheus_ is fetched from [Maven Central](https://central.sonatype.com/), and installed at `.databricks/labs/remorph-transpilers/databricks-morph-plugin/`.
  - the latest _BladeBridge_ is fetched from [PyPi](https://pypi.org/), and installed at `.databricks/labs/remorph-transpilers/bladebridge/`.
+ - the latest _Switch_ is fetched from [PyPi](https://pypi.org/), and installed as an optional direct dependency (enabled with `--include-llm-transpiler true`).
 
 Installing 3rd party transpilers is the responsibility of their provider.