feat(llm): pass llm params directly (#1387)

* feat(llm): add llm_params option to llm_call

Extend llm_call to accept an optional llm_params dictionary for passing
configuration parameters (e.g., temperature, max_tokens) to the language
model. This enables more flexible control over LLM behavior during calls.

refactor(llm): replace llm_params context manager with argument

Update all usages of the llm_params context manager to pass llm_params as
an argument to llm_call instead. This simplifies parameter handling and
improves code clarity for LLM calls.

docs: clarify prompt customization and llm_params usage

update LLMChain config usage

Author: Pouyanpi

nemoguardrails/actions/v2_x/generation.py

@@ -457,9 +457,7 @@ async def passthrough_llm_action(
 
         generation_options: GenerationOptions = generation_options_var.get()
 
-        generation_llm_params = (
-            generation_options and generation_options.llm_params
-        ) or {}
+        generation_llm_params = generation_options and generation_options.llm_params
         text = await llm_call(
             llm,
             user_message,