text fixes

Author: jcatt-sf

CHANGELOG.md

@@ -6,7 +6,7 @@
 
 - **`llm_gateway_generate_text()` UDF wrapper for AI-powered DataFrame transformations.**
 
-  New method on proxy providers to generate AI completions in DataFrame operations via the `llm_gateway_generate` UDF.
+  New method on proxy providers to generate AI completions in DataFrame operations via a built-in UDF.
 
   ```python
   from datacustomcode import Client
@@ -31,13 +31,13 @@
   ```
 
   **Local Development:** Returns placeholder string (doesn't execute)  
-  **BYOC Production:** Calls real `llm_gateway_generate` UDF
+  **Production:** Calls a built-in UDF
 
   **Parameters:**
   - `template` (str): Prompt template with {placeholder} syntax
   - `values` (dict or Column): Dict mapping placeholders to Columns, or pre-built named_struct
   - `llmModelId` (str): Model identifier (required, e.g., "sfdc_ai__DefaultGPT4Omni")
-  - `maxTokens` (int): Maximum response length (required, e.g., 200)
+  - `maxTokens` (int): Maximum tokens that will be spent on this query
 
 
 ## 1.0.0

README.md

@@ -166,6 +166,9 @@ sdf = client.read_dlo('my_DLO')
 client.write_to_dlo('output_DLO')
 ```
 
+> [!WARNING]
+> Currently we only support reading from DMOs and writing to DMOs or reading from DLOs and writing to DLOs, but they cannot mix.
+
 ### LLM Gateway
 
 Generate AI completions in DataFrame transformations using the LLM gateway UDF.
@@ -193,7 +196,7 @@ df = df.withColumn(
 ```
 
 > [!WARNING]
-> This method returns a placeholder string in local development and won't execute. It only works when deployed, where it calls the real LLM Gateway service via the `llm_gateway_generate` UDF.
+> This method returns a placeholder string in local development. It only makes a LLM call and spends tokens when deployed, where it calls the real LLM Gateway service via a UDF.
 
 ## CLI